{"version":"https://jsonfeed.org/version/1.1","title":"JevMade \u2014 the Jev experiment registry","home_page_url":"https://jevmade.com/","feed_url":"https://jevmade.com/feed.json","description":"A public registry of experiments people have built with Jev, TypeSafe AI\u2019s first System One model. Independent community project; not affiliated with TypeSafe AI.","items":[{"id":"typesafe-ai","url":"https://typesafe.ai","title":"TypeSafe AI","content_text":"TypeSafe AI is an AI lab building machine-native intelligence infrastructure for automation, designed to make decisions within software. Try our first System One Model, Jev, in early access.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TypeSafe AI"}],"tags":["official"]},{"id":"documentation","url":"https://docs.typesafe.ai","title":"Documentation","content_text":"Jev is TypeSafe's flagship model and the first System One model. Send state and typed questions; get structured answers your code can use directly.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TypeSafe AI"}],"tags":["official"]},{"id":"quick-start","url":"https://docs.typesafe.ai/introduction/quickstart","title":"Quick start","content_text":"Prefer to just dive in? Here's everything you need to get started immediately.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TypeSafe AI"}],"tags":["official"]},{"id":"playground","url":"https://console.typesafe.ai/playground","title":"Playground","content_text":"TypeSafe","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TypeSafe AI"}],"tags":["official"]},{"id":"http-api-reference","url":"https://docs.typesafe.ai/api","title":"HTTP API reference","content_text":"Full HTTP API reference for the TypeSafe evaluation endpoint.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TypeSafe AI"}],"tags":["official"]},{"id":"primitives","url":"https://docs.typesafe.ai/primitives","title":"Primitives","content_text":"The three TypeSafe question types (Choice, Score, Noul), the typed answers they return, how to choose between them, and how to ask several at once.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TypeSafe AI"}],"tags":["official"]},{"id":"patterns","url":"https://docs.typesafe.ai/patterns","title":"Patterns","content_text":"Architectural patterns for building systems with TypeSafe.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TypeSafe AI"}],"tags":["official"]},{"id":"cookbooks","url":"https://docs.typesafe.ai/cookbooks/parallel_questions","title":"Cookbooks","content_text":"Runs a 13-question regulatory briefing over the GDPR Wikipedia article, showing that batching every question into one TypeSafe call is 12.2x cheaper and 10.0x faster with no change in answers.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TypeSafe AI"}],"tags":["official"]},{"id":"smart-home-demo","url":"https://docs.typesafe.ai/demos/smart-home","title":"Smart home demo","content_text":"Demo code: a smart home assistant that uses TypeSafe to evaluate user requests.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TypeSafe AI"}],"tags":["official"]},{"id":"workflow-evals","url":"https://evals.typesafe.ai","title":"Workflow evals","content_text":"Workflow evals","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TypeSafe AI"}],"tags":["official"]},{"id":"jev-1-13-jaggedness","url":"https://docs.typesafe.ai/model-jaggedness/jev-1.13","title":"Jev 1.13 jaggedness","content_text":"Jev isn't perfect. Here are some jagged edges we are aware of with jev-1.13. Many of these will be fixed in later versions.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TypeSafe AI"}],"tags":["official"]},{"id":"introducing-system-one-models-and-jev","url":"https://typesafe.ai/blog/introducing-system-one-models-and-jev","title":"Introducing System One Models and Jev","content_text":"TypeSafe AI is an AI lab building machine-native intelligence infrastructure for automation, designed to make decisions within software. Try our first System One Model, Jev, in early access.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TypeSafe AI"}],"tags":["official"]},{"id":"manifesto","url":"https://typesafe.ai/manifesto","title":"Manifesto","content_text":"TypeSafe AI is an AI lab building machine-native intelligence infrastructure for automation, designed to make decisions within software. Try our first System One Model, Jev, in early access.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TypeSafe AI"}],"tags":["official"]},{"id":"discord","url":"https://discord.gg/typesafe","title":"Discord","content_text":"The home of Jev, the first public System One model | 64361 members","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TypeSafe AI"}],"tags":["official"]},{"id":"typesafeai-on-x","url":"https://x.com/typesafeai","title":"@typesafeai on X","content_text":"TypeSafe AI (@typesafeai) / X","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TypeSafe AI"}],"tags":["official"]},{"id":"typesafe-agent-skills","url":"https://github.com/typesafe-ai/skills","title":"TypeSafe agent skills","content_text":"Agent skills for building with TypeSafe's System One API","date_published":"2026-08-24T00:00:00Z","authors":[{"name":"TypeSafe AI"}],"tags":["official"]},{"id":"typesafe-javascript-sdk","url":"https://github.com/typesafe-ai/typesafe-sdk-js","title":"TypeSafe JavaScript SDK","content_text":"The official TypeScript/JavaScript library for the TypeSafe API","date_published":"2026-09-04T00:00:00Z","authors":[{"name":"TypeSafe AI"}],"tags":["official","choice"]},{"id":"system-one-adapter-python","url":"https://github.com/typesafe-ai/system-one-adapter-python","title":"System One adapter (Python)","content_text":"Drop-in TypeSafeClient replacement backed by LLM APIs","date_published":"2026-08-08T00:00:00Z","authors":[{"name":"TypeSafe AI"}],"tags":["official","choice","score","noul"]},{"id":"typesafe-python-sdk","url":"https://github.com/typesafe-ai/typesafe-sdk-python","title":"TypeSafe Python SDK","content_text":"The official Python library for the TypeSafe API","date_published":"2026-09-04T00:00:00Z","authors":[{"name":"TypeSafe AI"}],"tags":["official","choice"]},{"id":"advocaat","url":"https://github.com/pithings/advocaat","title":"advocaat","content_text":"A small, type-safe client for asking AI questions about your data, powered by TypeSafe Jev.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"pithings"}],"tags":["sdks-clients","choice","score","noul"]},{"id":"jev-dannote","url":"https://github.com/dannote/jev","title":"jev (dannote)","content_text":"TypeSafe Jev for OTP: reply to Jev from a GenServer and pattern match on its answer","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"dannote"}],"tags":["sdks-clients","choice","score","noul"]},{"id":"typesafe-ai-twister915","url":"https://github.com/Twister915/typesafe-ai","title":"typesafe-ai","content_text":"Typed TypeSafe AI clients for Rust, with async and blocking backends and observable retries.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"Twister915"}],"tags":["sdks-clients","choice","score","noul"]},{"id":"typesafe-sdk-go-tangerg","url":"https://github.com/Tangerg/typesafe-sdk-go","title":"typesafe-sdk-go (Tangerg)","content_text":"Go SDK for the TypeSafe AI API \u2014 typed questions in, probability distributions out.","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"Tangerg"}],"tags":["sdks-clients","choice","score","noul"]},{"id":"zod-jev","url":"https://github.com/jomatsu/zod-jev","title":"zod-jev","content_text":"Zod validates the shape. validates the meaning.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"jomatsu"}],"tags":["sdks-clients","choice","score","noul"]},{"id":"super-jev","url":"https://github.com/Kevthetech143/super-jev","title":"super-jev","content_text":"A small, extensible decision-to-action harness for TypeSafe Jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Kevthetech143"}],"tags":["sdks-clients","choice","score","noul"]},{"id":"typesafe-dotnet-sdk","url":"https://github.com/saibimajdi/typesafeai-dotnet-sdk","title":"typesafe-dotnet-sdk","content_text":"Community .NET SDK for the TypeSafe AI System One API \u2014 typed noul, choice, and score questions with structured, confidence-scored answers. Not affiliated with TypeSafe AI.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"saibimajdi"}],"tags":["sdks-clients","choice","score","noul"]},{"id":"jev-dsl","url":"https://github.com/inanna-malick/jev-dsl","title":"jev-dsl","content_text":"Agent-first Haskell DSL for TypeSafe's Jev judgment model: typed packets, inferred types, answers under the same labels","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"inanna-malick"}],"tags":["sdks-clients","choice","score","noul"]},{"id":"typesafe-sdk-joshmn","url":"https://github.com/joshmn/typesafe-sdk","title":"typesafe-sdk (joshmn)","content_text":"Ruby client for typesafe.ai","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"joshmn"}],"tags":["sdks-clients","choice","score","noul"]},{"id":"jev-java","url":"https://github.com/Olti1947/jev-java","title":"jev-java","content_text":"Idiomatic Java SDK for TypeSafe AI Jev System One decision engine","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"Olti1947"}],"tags":["sdks-clients"]},{"id":"jod","url":"https://github.com/mateonunez/jod","title":"jod","content_text":"Semantic schemas over TypeSafe's Jev \u2014 validate the state locally, then project typed answers.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"mateonunez"}],"tags":["sdks-clients","choice","score","noul"]},{"id":"typesafe-ai-rs","url":"https://github.com/gilljon/typesafe-ai-rs","title":"typesafe-ai-rs","content_text":"Independent async and blocking Rust SDK for the TypeSafe AI System One API","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"gilljon"}],"tags":["sdks-clients"]},{"id":"typesafe-sdk","url":"https://github.com/nshkrdotcom/typesafe_sdk","title":"typesafe_sdk","content_text":"An idiomatic, type-safe Elixir port of the official TypeScript AI SDK (ai / ai-sdk) providing unified LLM integrations, streaming text and structured outputs, tool calling, and agentic workflows. Jev is their current fla","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"nshkrdotcom"}],"tags":["sdks-clients"]},{"id":"typesafe-go-cole-gillespie","url":"https://github.com/cole-gillespie/typesafe-go","title":"typesafe-go (cole-gillespie)","content_text":"unofficial go SDK for typesafe AI, with typed answers, retries, and context support","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"cole-gillespie"}],"tags":["sdks-clients"]},{"id":"typesafe-sdk-java","url":"https://github.com/Premo-Cloud/typesafe-sdk-java","title":"typesafe-sdk-java","content_text":"Community Java client for the TypeSafe System One API (unofficial)","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"Premo-Cloud"}],"tags":["sdks-clients"]},{"id":"typesafe-sdk-swift","url":"https://github.com/InsaneArts/typesafe-sdk-swift","title":"typesafe-sdk-swift","content_text":"Swift SDK for TypeSafe AI","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"InsaneArts"}],"tags":["sdks-clients"]},{"id":"typesafeai-net","url":"https://github.com/Hawxy/TypeSafeAI.Net","title":"TypeSafeAI.Net","content_text":".NET SDK for the TypeSafe AI platform","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Hawxy"}],"tags":["sdks-clients"]},{"id":"zio-typesafe-ai","url":"https://github.com/jamesward/zio-typesafe-ai","title":"zio-typesafe-ai","content_text":"zio-typesafe-ai \u2014 a sdks clients project built on Jev.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"jamesward"}],"tags":["sdks-clients"]},{"id":"jev-go-gaurav-gosain","url":"https://github.com/Gaurav-Gosain/jev-go","title":"jev-go (Gaurav-Gosain)","content_text":"Go client for TypeSafe's System One API and its model Jev: typed judgments and calibrated probabilities instead of generated text","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"Gaurav-Gosain"}],"tags":["sdks-clients"]},{"id":"jev-go-guillemus","url":"https://github.com/guillemus/jev-go","title":"jev-go (guillemus)","content_text":"Unofficial Go SDK for TypeSafe AI's Jev API","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"guillemus"}],"tags":["sdks-clients"]},{"id":"jevclient","url":"https://github.com/AboveColin/jevclient","title":"jevclient","content_text":"Async Python client for TypeSafe Jev. Typed questions in, probabilities and choices out, no prose to parse.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"AboveColin"}],"tags":["sdks-clients","choice"]},{"id":"jevgo","url":"https://github.com/fgn/jevgo","title":"jevgo","content_text":"Go client for TypeSafe AI's System One API (Jev), with optional Langfuse instrumentation","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"fgn"}],"tags":["sdks-clients"]},{"id":"typesafe-client","url":"https://github.com/JedimEmO/typesafe-client","title":"typesafe-client","content_text":"Unofficial typed async Rust client for the TypeSafe System One API","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"JedimEmO"}],"tags":["sdks-clients"]},{"id":"typesafe-sdk-rust","url":"https://github.com/codeitlikemiley/typesafe-sdk-rust","title":"typesafe-sdk-rust","content_text":"Rust SDK for the TypeSafe AI API","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"codeitlikemiley"}],"tags":["sdks-clients"]},{"id":"typesafeai-go","url":"https://github.com/chez-shanpu/typesafeai-go","title":"typesafeai-go","content_text":"Go SDK for TypeSafe AI API https://docs.typesafe.ai/api","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"chez-shanpu"}],"tags":["sdks-clients"]},{"id":"decido","url":"https://github.com/yairshy/decido","title":"decido","content_text":"Probabilistic decisions for Python. Use Jev or bring your own provider; crawl with Playwright.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"yairshy"}],"tags":["sdks-clients"]},{"id":"jev","url":"https://github.com/anilsenay/jev","title":"jev","content_text":"Unofficial Go client for TypeSafe's System One API  and its model, Jev.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"anilsenay"}],"tags":["sdks-clients"]},{"id":"kunobi-jev","url":"https://github.com/kunobi-ninja/kunobi-jev","title":"kunobi-jev","content_text":"Rust client for the TypeSafe System One API (Jev)","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"kunobi-ninja"}],"tags":["sdks-clients"]},{"id":"s1-rs","url":"https://github.com/AbdelStark/s1-rs","title":"s1-rs","content_text":"Typed System One layer for Rust (Choice/Score/Noul). ","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"AbdelStark"}],"tags":["sdks-clients","choice","score","noul"]},{"id":"tinyjevclient","url":"https://github.com/tinyhumansai/tinyjevclient","title":"tinyjevclient","content_text":"An integration with jev by typesafe.ai in Rust","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"tinyhumansai"}],"tags":["sdks-clients"]},{"id":"typesafe","url":"https://github.com/mattneel/typesafe","title":"typesafe","content_text":"An idiomatic Elixir client for the TypeSafe AI API","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"mattneel"}],"tags":["sdks-clients"]},{"id":"typesafe-ai-hfiguera","url":"https://github.com/hfiguera/typesafe_ai","title":"typesafe_ai (hfiguera)","content_text":"An Elixir client for TypeSafe AI with typed responses and bounded concurrency","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"hfiguera"}],"tags":["sdks-clients"]},{"id":"typesafe-ai-typesend","url":"https://github.com/typesend/typesafe_ai","title":"typesafe_ai (typesend)","content_text":"Typed Elixir client for TypeSafe AI and its Jev System One model, with offline test stubs, concurrent fan-out, and atom-keyed answers.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"typesend"}],"tags":["sdks-clients"]},{"id":"typesafe-sdk-ex","url":"https://github.com/vinnie357/typesafe_sdk_ex","title":"typesafe_sdk_ex","content_text":"Typesafe AI SDK in Elixir using Req","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"vinnie357"}],"tags":["sdks-clients"]},{"id":"typesafe-go-zhirschtritt","url":"https://github.com/zhirschtritt/typesafe-go","title":"typesafe-go (zhirschtritt)","content_text":"Idiomatic Go SDK for the TypeSafe AI API","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"zhirschtritt"}],"tags":["sdks-clients"]},{"id":"typesafe-rs","url":"https://github.com/AbdelStark/typesafe-rs","title":"typesafe-rs","content_text":"Latency-first Rust SDK for TypeSafe System One. ","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"AbdelStark"}],"tags":["sdks-clients"]},{"id":"typesafe-sdk-binnash","url":"https://github.com/binnash/typesafe-sdk","title":"typesafe-sdk (binnash)","content_text":"PHP & Laravel SDK for TypeSafe AI's JEV Model series","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"binnash"}],"tags":["sdks-clients"]},{"id":"typesafe-sdk-go","url":"https://github.com/valksor/typesafe-sdk-go","title":"typesafe-sdk-go","content_text":"Unofficial Go SDK for the TypeSafe AI System One API \u2014 1:1 parity with the official JS and Python SDKs. Not affiliated with TypeSafe AI.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"valksor"}],"tags":["sdks-clients"]},{"id":"typesafe-sdk-php","url":"https://github.com/valksor/typesafe-sdk-php","title":"typesafe-sdk-php","content_text":"Unofficial PHP SDK for the TypeSafe AI System One API \u2014 1:1 parity with the official JS and Python SDKs. Not affiliated with TypeSafe AI.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"valksor"}],"tags":["sdks-clients"]},{"id":"typesafe-zig","url":"https://github.com/mattneel/typesafe.zig","title":"typesafe.zig","content_text":"An idiomatic Zig client for the TypeSafe AI API","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"mattneel"}],"tags":["sdks-clients"]},{"id":"eve","url":"https://github.com/vercel/eve","title":"eve","content_text":"The Open Framework for Building Agents","date_published":"2026-06-16T00:00:00Z","authors":[{"name":"vercel"}],"tags":["integrations"]},{"id":"ai-cli","url":"https://github.com/vercel-labs/ai-cli","title":"ai-cli","content_text":"Generate anything from your terminal","date_published":"2025-07-28T00:00:00Z","authors":[{"name":"vercel-labs"}],"tags":["integrations","choice","score"]},{"id":"pg-jev","url":"https://github.com/realZachi/pg-jev","title":"pg-jev","content_text":"Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"realZachi"}],"tags":["integrations","choice","score","noul"]},{"id":"jev-shell-history","url":"https://github.com/mrnugget/jev-shell-history","title":"jev-shell-history","content_text":"Fish-style zsh history autosuggestions ranked by Jev (TypeSafe)","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"mrnugget"}],"tags":["integrations","choice","score","noul"]},{"id":"loki","url":"https://github.com/wundercorp/loki","title":"Loki","content_text":"The agent that evolves with you \ud81a\udd0d","date_published":"2026-09-11T00:00:00Z","authors":[{"name":"wundercorp"}],"tags":["integrations","choice","score","noul"]},{"id":"neo4jev","url":"https://github.com/jexp/neo4jev","title":"neo4jev","content_text":"Typesafe.ai System One Model Jev navigating a Neo4j graph by using a classifier over neighbouring relationships","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"jexp"}],"tags":["integrations","choice","noul"]},{"id":"ruby-llm-typesafe","url":"https://github.com/kieranklaassen/ruby_llm-typesafe","title":"ruby_llm-typesafe","content_text":"TypeSafe structured-output provider for RubyLLM 2","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"kieranklaassen"}],"tags":["integrations","choice","score","noul"]},{"id":"ha-jev","url":"https://github.com/AboveColin/HA-Jev","title":"HA-Jev","content_text":"Home Assistant integration that turns natural-language-ish smart-home state into typed Jev decisions about devices.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"AboveColin"}],"tags":["integrations","choice","score","noul"]},{"id":"pg-typesafe","url":"https://github.com/giuliosmall/pg_typesafe","title":"pg_typesafe","content_text":"Pre-alpha PostgreSQL extension for TypeSafe AI (Jev) categorical classification","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"giuliosmall"}],"tags":["integrations","choice","score","noul"]},{"id":"a0-typesafe-ai","url":"https://github.com/3clyp50/a0-typesafe-ai","title":"a0-typesafe-ai","content_text":"TypeSafe AI Jev judgments for Agent Zero, with typed tools and probability cards.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"3clyp50"}],"tags":["integrations","choice","score","noul"]},{"id":"typesafe-jev-workflow","url":"https://github.com/GiesN/typesafe-jev-workflow","title":"typesafe-jev-workflow","content_text":"A small async LangGraph workflow that sends a mocked email to TypeSafe's Jev model,","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"GiesN"}],"tags":["integrations","choice"]},{"id":"typesafe-on-neon","url":"https://github.com/andrelandgraf/safer-with-jev","title":"typesafe-on-neon","content_text":"Neon Function proxy for the Neon AI Gateway with TypeSafe Jev routing.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"andrelandgraf"}],"tags":["integrations"]},{"id":"laravel-typesafe-jev","url":"https://github.com/Butochnikov/laravel-typesafe-jev","title":"laravel-typesafe-jev","content_text":"Unofficial Laravel integration for TypeSafe Jev AI with typed responses, async requests, scoped dependency injection, and testing fakes.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Butochnikov"}],"tags":["integrations"]},{"id":"llama-index-jev","url":"https://github.com/WiktorB2004/llama-index-jev","title":"llama-index-jev","content_text":"LlamaIndex reranker + router powered by TypeSafe Jev \u2014 typed scores/choices, cheaper than LLM-as-judge.","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"WiktorB2004"}],"tags":["integrations","choice","score"]},{"id":"judging-with-typesafe","url":"https://github.com/carlsonchik/judging-with-typesafe","title":"judging-with-typesafe","content_text":"\u0421\u043a\u0438\u043b\u043b \u0434\u043b\u044f \u0430\u0433\u0435\u043d\u0442\u043e\u0432 Letta: \u0441\u0443\u0436\u0434\u0435\u043d\u0438\u044f \u043f\u043e \u043a\u0440\u0438\u0442\u0435\u0440\u0438\u044f\u043c \u0447\u0435\u0440\u0435\u0437 TypeSafe System One (Jev)","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"carlsonchik"}],"tags":["integrations"]},{"id":"pydantic-jev-examples","url":"https://github.com/adtyavrdhn/pydantic-jev-examples","title":"pydantic-jev-examples","content_text":"Pydantic AI capabilities made stronger with Jev: small runnable demos, one file each","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"adtyavrdhn"}],"tags":["integrations"]},{"id":"typesafe-ai-rails","url":"https://github.com/GenieRobot/typesafe-ai-rails","title":"typesafe-ai-rails","content_text":"typesafe-ai-rails \u2014 a integrations project built on Jev.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"GenieRobot"}],"tags":["integrations"]},{"id":"typesafe-assist","url":"https://github.com/JanOstrowka/typesafe-assist","title":"typesafe-assist","content_text":"Home Assistant Assist conversation agent powered by TypeSafe's Jev (System One) model","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"JanOstrowka"}],"tags":["integrations"]},{"id":"agentgateway-jev-guardrail-example","url":"https://github.com/agentgateway/agentgateway/tree/main/examples/llm-guardrail-jev","title":"agentgateway Jev guardrail example","content_text":"The agentgateway project's example wiring Jev as an LLM guardrail: requests and responses screened by typed yes/no and severity questions.","date_published":"2025-03-18T00:00:00Z","authors":[{"name":"agentgateway"}],"tags":["integrations"]},{"id":"jev-on-vercel-ai-gateway","url":"https://vercel.com/ai-gateway/models/jev","title":"Jev on Vercel AI Gateway","content_text":"Explore the Jev AI model by TypeSafe AI on Vercel AI Gateway","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Vercel"}],"tags":["integrations"]},{"id":"jev4mellea","url":"https://github.com/SoundBlaster/Jev4Mellea","title":"Jev4Mellea","content_text":"Jev adapter to Mellea","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"SoundBlaster"}],"tags":["integrations"]},{"id":"n8n-nodes-typesafe-ai","url":"https://github.com/DomMonte/n8n-nodes-typesafe-ai","title":"n8n-nodes-typesafe-ai","content_text":"n8n community node for the TypeSafe AI System One API \u2014 typed yes/no, choice and score questions with calibrated probabilities","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"DomMonte"}],"tags":["integrations","choice","score"]},{"id":"trainlcd-jev-rerank","url":"https://github.com/TrainLCD/Functions/pull/33","title":"TrainLCD Jev rerank","content_text":"A pull request to TrainLCD's Functions workers adding Jev-based reranking.","date_published":"2026-08-04T00:00:00Z","authors":[{"name":"TrainLCD"}],"tags":["integrations"]},{"id":"typesafe-ui","url":"https://github.com/BunsDev/typesafe-ui","title":"typesafe-ui","content_text":"shadcn-style reusable components and blocks for using TypeSafe AI.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"BunsDev"}],"tags":["integrations"]},{"id":"vercel-ai-sdk-provider","url":"https://ai-sdk.dev/providers/ai-sdk-providers/typesafe-ai","title":"Vercel AI SDK provider","content_text":"Use TypeSafe System One models for typed evaluations with the AI SDK.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Vercel"}],"tags":["integrations"]},{"id":"fast-jev-compaction","url":"https://github.com/tamaratran/fast-jev-compaction","title":"fast-jev-compaction","content_text":"Claude Code plugin that replaces the LLM-written compaction summary with Jev-typed decisions about what context to keep.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"tamaratran"}],"tags":["agent-tooling","noul"]},{"id":"foreman","url":"https://github.com/thruwire/foreman","title":"foreman","content_text":"Software factory foreman based on TypeSafe's Jev model","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"thruwire"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"jev-review-devagrawal09","url":"https://github.com/devagrawal09/jev-review","title":"jev-review (devagrawal09)","content_text":"A staged code-review workflow and local dashboard built with TypeSafe Jev.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"devagrawal09"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"pi-jev-y0usaf","url":"https://github.com/y0usaf/pi-jev","title":"pi-jev (y0usaf)","content_text":"TypeSafe Jev as a decision layer for the Pi coding agent: a measured tool-call gate plus jev_ask for typed, calibrated answers","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"y0usaf"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"jev-router-gargpratyush","url":"https://github.com/gargpratyush/jev-router","title":"jev-router (gargpratyush)","content_text":"Route to the cheapest model in claude code for your task using jev-router","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"gargpratyush"}],"tags":["agent-tooling","choice","score"]},{"id":"jev-review-niazmorshed2007","url":"https://github.com/NiazMorshed2007/jev-review","title":"jev-review (NiazMorshed2007)","content_text":"Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"NiazMorshed2007"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"building-with-jev-skill","url":"https://github.com/dbreunig/building-with-jev-skill","title":"building-with-jev-skill","content_text":"A skill for writing and improving programs that call Jev, TypeSafe's System One model","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"dbreunig"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"jev-mcp-jkudish","url":"https://github.com/jkudish/jev-mcp","title":"jev-mcp (jkudish)","content_text":"Fast, cheap, typed judgments from TypeSafe's Jev model, as MCP tools.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"jkudish"}],"tags":["agent-tooling","choice","score"]},{"id":"typesafe-mcp","url":"https://github.com/itsmostafa/typesafe-mcp","title":"typesafe-mcp","content_text":"mcp connector to give your AI agent direct access to typesafe ai's jev model","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"itsmostafa"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"pi-warden","url":"https://github.com/DevMortimer/pi-warden","title":"pi-warden","content_text":"Guardrails for Pi built on pi-typesafe that steer the agent instead of interrupting you: Jev judges irreversible and off-task tool calls, detects stuck loops, checks unverified done claims, flags slop","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"DevMortimer"}],"tags":["agent-tooling","score"]},{"id":"jev-search","url":"https://github.com/superagents-lab/jev-search","title":"jev-search","content_text":"Search the web with TypeSafe's Jev: source selection, query understanding and relevance ranking. Built with Search1API.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"superagents-lab"}],"tags":["agent-tooling","choice","score"]},{"id":"skillranker","url":"https://github.com/Dicklesworthstone/skillranker","title":"skillranker","content_text":"Rust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks, structured JSON, abstention, and local feedback. Requires a TypeSafe API key.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Dicklesworthstone"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"jev-codex-router","url":"https://github.com/0xNatoshi/jev-codex-router","title":"jev-codex-router","content_text":"Per-turn model & reasoning routing for Codex, driven by Jev (TypeSafe System One): picks the model, thinking depth and speed mode for every turn.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"0xNatoshi"}],"tags":["agent-tooling"]},{"id":"ask-jev-skill","url":"https://github.com/shantanugoel/ask-jev-skill","title":"ask-jev-skill","content_text":"Skill for Hermes, and other agents, to ask typesafe's jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"shantanugoel"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"hono-jev-router","url":"https://github.com/yusukebe/hono-jev-router","title":"hono-jev-router","content_text":"Route HTTP requests by meaning. A semantic router for Hono powered by Jev.","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"yusukebe"}],"tags":["agent-tooling","noul"]},{"id":"winnow","url":"https://github.com/GhalebDweikat/winnow","title":"winnow","content_text":"A calibrated context sieve for Claude Code: every tool result is judged by a System One model before it enters context.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"GhalebDweikat"}],"tags":["agent-tooling","score"]},{"id":"jev-axi","url":"https://github.com/shiftynick/jev-axi","title":"jev-axi","content_text":"Agent-ergonomic CLI for TypeSafe's Jev: fast calibrated judgments (pick, rate, check, rank, triage, guard) from the shell","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"shiftynick"}],"tags":["agent-tooling","choice","score"]},{"id":"yoshi","url":"https://github.com/compozy/yoshi","title":"yoshi","content_text":"Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into https://github.com/compozy/compozy","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"compozy"}],"tags":["agent-tooling"]},{"id":"pi-jev-auto-mode","url":"https://github.com/jomatsu/pi-jev-auto-mode","title":"pi-jev-auto-mode","content_text":"Jev (TypeSafe System One) backed auto mode for the Pi coding agent: semantically auto-approves bash, write, and edit tool calls and fails closed when a decision cannot be made.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"jomatsu"}],"tags":["agent-tooling"]},{"id":"jev-mcp-blakestone-x","url":"https://github.com/blakestone-x/jev-mcp","title":"jev-mcp (blakestone-x)","content_text":"MCP server for TypeSafe Jev: typed classify, score, check, match and screen for any agent, with confidence on every answer","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"blakestone-x"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"jevlint","url":"https://github.com/huntedman/JevLint","title":"JevLint","content_text":"Configurable semantic linting powered by Jev, with file-level NOUL judgments and a magic-strings plugin.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"huntedman"}],"tags":["agent-tooling","noul"]},{"id":"jev-code","url":"https://github.com/devagrawal09/jev-code","title":"jev-code","content_text":"Bounded TypeSafe Jev workflows for coding agents.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"devagrawal09"}],"tags":["agent-tooling","choice"]},{"id":"pi-jev-theooliveira","url":"https://github.com/TheoOliveira/pi-jev","title":"pi-jev (TheoOliveira)","content_text":"Semantic tool routing and typed System One decisions for the Pi coding agent using TypeSafe Jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TheoOliveira"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"pi-jev-router","url":"https://github.com/mejiasd3v/pi-jev-router","title":"pi-jev-router","content_text":"Automatic model routing for Pi using TypeSafe's Jev through Vercel AI Gateway","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"mejiasd3v"}],"tags":["agent-tooling","choice"]},{"id":"snifftest","url":"https://github.com/DanRWilloughby/snifftest","title":"snifftest","content_text":"A prose linter that sniffs out AI writing tells. Zero dependencies, countable rules plus one judgment model.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"DanRWilloughby"}],"tags":["agent-tooling","score"]},{"id":"typesafe-skill-router","url":"https://github.com/DECRUX9812/typesafe-skill-router","title":"typesafe-skill-router","content_text":"TypeSafe (Jev) skill routing for Hermes Agent: names the one skill worth loading, before the model call. Opt-in, stdlib only, ~$0.001 per routed turn.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"DECRUX9812"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"jev-agent-skill-router","url":"https://github.com/GodsBoy/jev-agent-skill-router","title":"jev-agent-skill-router","content_text":"Typed, confidence-aware agent skill routing with TypeSafe Jev.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"GodsBoy"}],"tags":["agent-tooling","choice","noul"]},{"id":"jev-mcp-arunav25","url":"https://github.com/arunav25/jev-mcp","title":"jev-mcp (arunav25)","content_text":"Connect JEV to MCP clients and compare its judgments against general-purpose LLMs using shared datasets and measurable accuracy.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"arunav25"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"jevrouter","url":"https://github.com/BillionsBobby/JevRouter","title":"JevRouter","content_text":"A lightweight Jev-powered router for models, tools, and subagents","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"BillionsBobby"}],"tags":["agent-tooling","choice"]},{"id":"jevwire","url":"https://github.com/Brainwires/jevwire","title":"jevwire","content_text":"Jev decision layer for agents: MCP server, embeddable DecisionModel library, and an escalate-only Claude Code plugin (TypeSafe AI's Jev)","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Brainwires"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"clean-code-review","url":"https://github.com/frostney/clean-code-review","title":"clean-code-review","content_text":"Every code file in a pull request, judged against Uncle Bob's Clean Code by TypeSafe's Jev, then reviewed by Luna. Built on eve and Next.js.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"frostney"}],"tags":["agent-tooling"]},{"id":"diffjury","url":"https://github.com/raihankhan-rk/diffjury","title":"diffjury","content_text":"DiffJury \u2014 TypeSafe Jev PR risk router + code review coach","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"raihankhan-rk"}],"tags":["agent-tooling"]},{"id":"hermes-jev","url":"https://github.com/keeltrace/hermes-jev","title":"hermes-jev","content_text":"Typed System One decisions, ranking, verification, and an opt-in Hermes tool gate using TypeSafe Jev.","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"keeltrace"}],"tags":["agent-tooling"]},{"id":"hermes-jev-approvals","url":"https://github.com/anpicasso/hermes-jev-approvals","title":"hermes-jev-approvals","content_text":"PoC: TypeSafe Jev as the reviewer for Hermes Agent smart command approvals. 8.7x faster, 4.4x fewer prompts, measured on 153 real commands. Approvals only.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"anpicasso"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"jev-borislemeec","url":"https://github.com/BorisLeMeec/jev","title":"jev (BorisLeMeec)","content_text":"A claude code plugin for jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"BorisLeMeec"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"jevex","url":"https://github.com/jvsteiner/jevex","title":"jevex","content_text":"jevex \u2014 a agent tooling project built on Jev.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"jvsteiner"}],"tags":["agent-tooling"]},{"id":"pi-quiet-ask","url":"https://github.com/HyunjunJeon/pi-quiet-ask","title":"pi-quiet-ask","content_text":"TypeSafe Jev as the pi coding agent's quiet decision layer","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"HyunjunJeon"}],"tags":["agent-tooling"]},{"id":"riff","url":"https://github.com/scale-venture-partners/riff","title":"riff","content_text":"A small, fast prose linter: ruff-style rule codes for writing, backed by TypeSafe's Jev model","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"scale-venture-partners"}],"tags":["agent-tooling","choice","noul"]},{"id":"slidepilot","url":"https://github.com/harshil1712/slidepilot","title":"slidepilot","content_text":"Voice-driven semantic auto-advance for Slidev, powered by Cloudflare Agents and TypeSafe AI Jev","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"harshil1712"}],"tags":["agent-tooling"]},{"id":"typesafe-cli-geilt","url":"https://github.com/geilt/typesafe-cli","title":"typesafe-cli (geilt)","content_text":"CLI and agent skill for TypeSafe System One (Jev): typed Choice, Score, and Noul judgments.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"geilt"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"ailerix","url":"https://github.com/tylerjharden/ailerix","title":"ailerix","content_text":"Type-safe model router. Jev (System One) banks each request to a typed catalog route.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"tylerjharden"}],"tags":["agent-tooling"]},{"id":"bicameral","url":"https://github.com/AbdelStark/bicameral","title":"bicameral","content_text":"Hybrid coding harness: System 2 writes, System 1 (Jev) runs reflexes.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"AbdelStark"}],"tags":["agent-tooling"]},{"id":"fast-dev-compaction","url":"https://github.com/leonaaardob/fast-dev-compaction","title":"fast-dev-compaction","content_text":"Codex plugin: verbatim Jev-guided context restoration around session compaction. Port of tamaratran/fast-jev-compaction to Codex lifecycle hooks.","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"leonaaardob"}],"tags":["agent-tooling"]},{"id":"jcm-router","url":"https://github.com/adarshmishra07/jcm-router","title":"jcm-router","content_text":"Local proxy that picks the Claude model and effort per message using TypeSafe Jev. Routes subagents, leaves your cached main chat alone.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"adarshmishra07"}],"tags":["agent-tooling"]},{"id":"jev-guard","url":"https://github.com/leepokai/jev-guard","title":"jev-guard","content_text":"Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injection in results, checks skills and plugins. Claude Code, Codex, Copilot, Gemini, Cu","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"leepokai"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"jev-judgment","url":"https://github.com/HyunjunJeon/jev-judgment","title":"jev-judgment","content_text":"Agent Skill: send closed coding-agent judgments to TypeSafe Jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"HyunjunJeon"}],"tags":["agent-tooling"]},{"id":"jev-mcp-rashedint32","url":"https://github.com/rashedInt32/jev-mcp","title":"jev-mcp (rashedInt32)","content_text":"MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"rashedInt32"}],"tags":["agent-tooling","score"]},{"id":"jev-shield","url":"https://github.com/caiovicentino/jev-shield","title":"jev-shield","content_text":"Semantic MCP firewall powered by Jev \u2014 screens every tool call, tool result, and tool description with calibrated System One verification. 94% block recall, 0 false positives, ~$0.00002/check.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"caiovicentino"}],"tags":["agent-tooling"]},{"id":"jev-skill-gate","url":"https://github.com/ShivamPansuriya/jev-skill-gate","title":"jev-skill-gate","content_text":"Cut Claude Code's skill manifest by ~75% with TypeSafe Jev. Scores every installed skill for relevance and hides the rest via skillOverrides \u2014 12,750 \u2192 3,185 tokens on a 217-skill install, for $0.0009 a session.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"ShivamPansuriya"}],"tags":["agent-tooling","score"]},{"id":"jev-system-architect","url":"https://github.com/samtay32/jev-system-architect","title":"jev-system-architect","content_text":"System-architecture skill for TypeSafe AI Jev/System One \u2014 find fuzzy semantic judgment and turn it into small Choice/Score/Noul primitives.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"samtay32"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"jev-workbench","url":"https://github.com/molis-ai/jev-workbench","title":"jev-workbench","content_text":"Build versioned judgment functions on TypeSafe's Jev once, then call the same published version from your backend over HTTP and from coding agents over MCP. The vendor key stays on your machine.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"molis-ai"}],"tags":["agent-tooling"]},{"id":"jgrep","url":"https://github.com/keltokhy/jgrep","title":"jgrep","content_text":"grep, but the pattern is a description. Filters lines by meaning with TypeSafe's Jev decision model: ~200 ms and a thousandth of a cent per line.","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"keltokhy"}],"tags":["agent-tooling","choice","score"]},{"id":"omp-jev-compaction","url":"https://github.com/jerryfane/omp-jev-compaction","title":"omp-jev-compaction","content_text":"Verbatim Jev-scored context reduction for omp, over TypeSafe or OpenRouter","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"jerryfane"}],"tags":["agent-tooling"]},{"id":"pi-fast-jev-compaction","url":"https://github.com/joelhooks/pi-fast-jev-compaction","title":"pi-fast-jev-compaction","content_text":"Pi extension: verbatim context compaction with TypeSafe Jev decisions","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"joelhooks"}],"tags":["agent-tooling","noul"]},{"id":"pi-heed","url":"https://github.com/Nyarlathoteppppp/pi-heed","title":"pi-heed","content_text":"Runtime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by TypeSafe Jev.","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"Nyarlathoteppppp"}],"tags":["agent-tooling"]},{"id":"skill-router","url":"https://github.com/lomeshdutta/skill-router","title":"skill-router","content_text":"Tell Claude Code which installed skill a session needs, using Jev (TypeSafe AI) for the decision and skills.sh for discovery.","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"lomeshdutta"}],"tags":["agent-tooling"]},{"id":"tiershift","url":"https://github.com/iamvatsalpatel/tiershift","title":"tiershift","content_text":"Shift every LLM call to the cheapest model that can handle it. Routing decided by TypeSafe Jev in ~180 ms. No training data. Policy in plain YAML. TypeScript and Python.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"iamvatsalpatel"}],"tags":["agent-tooling"]},{"id":"todo-jev","url":"https://github.com/maker-KK/todo-jev","title":"todo-jev","content_text":"\u26a1 Ultra-fast, low-cost intelligent task classifier and 3-tier routing engine powered by TypeSafe Jev (System One)","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"maker-KK"}],"tags":["agent-tooling"]},{"id":"typesafe-migration-guard","url":"https://github.com/opaielsheikh/typesafe-migration-guard","title":"typesafe-migration-guard","content_text":"Automated database migration safety reviewer powered by TypeSafe AI (Jev System One model)","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"opaielsheikh"}],"tags":["agent-tooling"]},{"id":"typesafe-mod","url":"https://github.com/BeLazy167/typesafe-mod","title":"typesafe-mod","content_text":"Claude Code mod that routes decisions to TypeSafe's Jev model: ranks installed skills per prompt, and answers the agent's own this-or-that questions when confident.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"BeLazy167"}],"tags":["agent-tooling"]},{"id":"antigravity-mcp-semantic-search-with-typesafeai","url":"https://github.com/greenyamao/Antigravity-mcp-semantic-search-with-TypeSafeAi","title":"Antigravity-mcp-semantic-search-with-TypeSafeAi","content_text":"Fast semantic code search & diff sanity auditor for AI coding assistants (Antigravity, Cursor, Claude Code) powered by TypeSafe System One.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"greenyamao"}],"tags":["agent-tooling"]},{"id":"ask-jev","url":"https://github.com/omni-/ask-jev","title":"ask-jev","content_text":"Utilizing Jev, the RLCD-type model provided by TypeSafe AI, to independently and cheaply judge agentic coding sessions.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"omni-"}],"tags":["agent-tooling"]},{"id":"is-malicious","url":"https://github.com/luantak/is-malicious","title":"is-malicious","content_text":"A codebase scanner that helps you not run malicous code","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"luantak"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"jev-cli-nasrallah-al","url":"https://github.com/Nasrallah-AL/jev-cli","title":"jev-cli (Nasrallah-AL)","content_text":"Command-line tool for TypeSafe's Jev AI model","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"Nasrallah-AL"}],"tags":["agent-tooling"]},{"id":"jev-mcp-burnigtm","url":"https://github.com/burnigtm/jev-mcp","title":"jev-mcp (burnigtm)","content_text":"MCP server that puts TypeSafe Jev on the coding loop in Cursor, Codex, and any MCP client","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"burnigtm"}],"tags":["agent-tooling"]},{"id":"jev-predict-skill","url":"https://github.com/DanielKillenberger/jev-predict-skill","title":"jev-predict-skill","content_text":"Predict another skill's next closed decision with TypeSafe Jev \u2014 without running that skill.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"DanielKillenberger"}],"tags":["agent-tooling"]},{"id":"jev-router-prismhq","url":"https://github.com/prismhq/jev-router","title":"jev-router (prismhq)","content_text":"Open-source LLM router that uses TypeSafe's Jev to pick a model, on top of LiteLLM","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"prismhq"}],"tags":["agent-tooling"]},{"id":"jev-skillful","url":"https://github.com/bestagentkits/jev-skillful","title":"jev-skillful","content_text":"Per-prompt capability router for coding agents: resolves installed skills, MCP servers, agents and commands against your prompt via TypeSafe Jev, and measures whether the injection actually helps.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"bestagentkits"}],"tags":["agent-tooling"]},{"id":"limpet","url":"https://github.com/noplan-inc/limpet","title":"limpet","content_text":"A Stop hook that stops your coding agent from stopping too early. Plain-language rules, judged by jev.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"noplan-inc"}],"tags":["agent-tooling"]},{"id":"omp-typesafe","url":"https://github.com/siddicky/omp-typesafe","title":"omp-typesafe","content_text":"TypeSafe AI (Jev) adversarial reviewer and typesafe_ask tool for the omp coding agent","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"siddicky"}],"tags":["agent-tooling"]},{"id":"agent-gate-loop","url":"https://github.com/Ripwords/agent-gate-loop","title":"agent-gate-loop","content_text":"Reusable GitHub Action: agent fix loop gated by checks, an AI reviewer, and TypeSafe Jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Ripwords"}],"tags":["agent-tooling"]},{"id":"agent-handoff-gate","url":"https://github.com/zsoXi/agent-handoff-gate","title":"agent-handoff-gate","content_text":"An experimental protocol for evidence-aware agent handoffs, bounded worker continuation, and TypeSafe/Jev-assisted review, with reproducible evaluation.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"zsoXi"}],"tags":["agent-tooling"]},{"id":"check-risk","url":"https://github.com/moezubair/check-risk","title":"check-risk","content_text":"A CLI and GitHub Action that assesses code-change risk using deterministic rules and TypeSafe Jev, recommending checks and reviewers before merge.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"moezubair"}],"tags":["agent-tooling"]},{"id":"frost","url":"https://github.com/marcus/frost","title":"frost","content_text":"A flexible and configurable CLI model router using TypeSafe Jev.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"marcus"}],"tags":["agent-tooling"]},{"id":"hermes-jev-router","url":"https://github.com/ussyverse/hermes-jev-router","title":"hermes-jev-router","content_text":"Experimental Hermes plugin: Jev-assisted model routing plans with budget and capability constraints. API access pending.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"ussyverse"}],"tags":["agent-tooling","choice"]},{"id":"jev-builder-loop","url":"https://github.com/rainbowpuffpuff/jev-builder-loop","title":"jev-builder-loop","content_text":"Grok skill: Jev as a judgment sensor in a builder-agent loop (priors \u00d7 probabilities \u2192 next act)","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"rainbowpuffpuff"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"jev-review-thiago-ss","url":"https://github.com/thiago-ss/jev-review","title":"jev-review (thiago-ss)","content_text":"Autonomous Jev pull-request review with typed decisions, calibrated approval gates, and trusted-owner escalation","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"thiago-ss"}],"tags":["agent-tooling"]},{"id":"jev-triage","url":"https://github.com/cephalization/jev-triage","title":"jev-triage","content_text":"Uses typeful jev, zero sync to pull and sync large repositories for issue triage","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"cephalization"}],"tags":["agent-tooling"]},{"id":"omp-jevens-classifier","url":"https://github.com/STRML/omp-jevens-classifier","title":"omp-jevens-classifier","content_text":"Jev-powered model-judged permission gate for OMP (TypeSafe System One)","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"STRML"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"pi-agent-foreman","url":"https://github.com/alexshpunt/pi-agent-foreman","title":"pi-agent-foreman","content_text":"Send Pi agents back to work when they stop before the job is done.","date_published":"2026-09-13T00:00:00Z","authors":[{"name":"alexshpunt"}],"tags":["agent-tooling"]},{"id":"pi-jev-code","url":"https://github.com/KamilPostrozny/pi-jev-code","title":"pi-jev-code","content_text":"Single-agent Pi coding coprocessor with Jev semantic gates, baseline-to-current diff review, and append-only observability telemetry.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"KamilPostrozny"}],"tags":["agent-tooling","choice"]},{"id":"pi-typesafe","url":"https://github.com/twilwa/pi-typesafe","title":"pi-typesafe","content_text":"Pi coding-agent extension built on the TypeSafe AI System One API (Jev)","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"twilwa"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"pi-typesafe-jev","url":"https://github.com/legacybridge-tech/pi-typesafe-jev","title":"pi-typesafe-jev","content_text":"A pi extension that exposes TypeSafe (Jev, System One) judgments as five pi tools, so a model can make narrow semantic judgments while your code and your users keep control of thresholds, weights, and actions.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"legacybridge-tech"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"switchboard","url":"https://github.com/aniruddh-krovvidi/switchboard","title":"switchboard","content_text":"Guardrail + model router for LLM gateways on TypeSafe's Jev (System One model), with an independent accuracy/calibration/latency evaluation. Stdlib Python.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"aniruddh-krovvidi"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"typesafe-demo-mcp","url":"https://github.com/bestagentkits/typesafe-demo-mcp","title":"typesafe-demo-mcp","content_text":"MCP server exposing TypeSafe System One judgments (noul, choice, score) as agent tools","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"bestagentkits"}],"tags":["agent-tooling","choice","score","noul"]},{"id":"typesafeai-review","url":"https://github.com/rbalch/typesafeai-review","title":"typesafeai-review","content_text":"Using Typesafe.AI to generate diff reviews.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"rbalch"}],"tags":["agent-tooling","score"]},{"id":"zcode-jev","url":"https://github.com/Zahrannnn/zcode-jev","title":"zcode-jev","content_text":"Typed judgment layer for coding agents \u2014 gates from PRD to ship. Jev-ready, provider-agnostic.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"Zahrannnn"}],"tags":["agent-tooling","noul"]},{"id":"jev-ultrafast","url":"https://github.com/browser-use/jev-ultrafast","title":"Jev Ultrafast","content_text":"Browser Use's ultrafast agent: Jev chooses the next browser operation and target element over a fresh element table each step, in one call \u2014 a small LLM only writes text when typing is required.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"browser-use"}],"tags":["browser-computer-use","choice"]},{"id":"typesafe-computer-use","url":"https://github.com/awlevin/typesafe-computer-use","title":"typesafe-computer-use","content_text":"Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"awlevin"}],"tags":["browser-computer-use","choice","score","noul"]},{"id":"mobile-jev","url":"https://github.com/droidrun/mobile-jev","title":"mobile-jev","content_text":"\u2014 Jev opens Uber, enters a route from San Francisco Airport to the Golden Gate Bridge, and reaches payment selection. The recorded task timer shows about 21 seconds for 9 actions. A completed booking is not demonstrated.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"droidrun"}],"tags":["browser-computer-use"]},{"id":"jev-browser","url":"https://github.com/jkudish/jev-browser","title":"jev-browser","content_text":"Browser use using Typesafe's Jev model","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"jkudish"}],"tags":["browser-computer-use","choice","score","noul"]},{"id":"unclutter","url":"https://github.com/kitze/unclutter","title":"unclutter","content_text":"WXT browser extension: Jev-powered page clutter removal with reusable template rules.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"kitze"}],"tags":["browser-computer-use","choice"]},{"id":"typesafe-adblock","url":"https://github.com/realZachi/typesafe-adblock","title":"typesafe-adblock","content_text":"\ud83e\uddf9 Fun project: a Chrome extension that asks a tiny AI decision model (TypeSafe Jev) \"is this DOM element an ad?\" and pops it off the page. BYOK, no backend, not a real ad blocker.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"realZachi"}],"tags":["browser-computer-use","noul"]},{"id":"jev-browser-use","url":"https://github.com/wy-coliney/jev-browser-use","title":"jev-browser-use","content_text":"5\u201310x faster browser operations: Jev clicks, Codex thinks and verifies. Built at EZCollegeApp.","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"wy-coliney"}],"tags":["browser-computer-use"]},{"id":"jev-voice-browser","url":"https://github.com/moritzkremb/jev-voice-browser","title":"jev-voice-browser","content_text":"Control a real browser by voice. Jev (TypeSafe System One) decides intent + target in ~300 ms per spoken word; Playwright acts \u2014 often before you finish the sentence.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"moritzkremb"}],"tags":["browser-computer-use","choice","score","noul"]},{"id":"vibecheck","url":"https://github.com/RafalWilinski/vibecheck","title":"vibecheck","content_text":"Chrome extension: vibe-check your X posts with TypeSafe's Jev before you hit Post","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"RafalWilinski"}],"tags":["browser-computer-use","choice","score","noul"]},{"id":"jev-browser-ying-kai-liao","url":"https://github.com/Ying-Kai-Liao/jev-browser","title":"jev-browser (Ying-Kai-Liao)","content_text":"Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"Ying-Kai-Liao"}],"tags":["browser-computer-use","choice","score","noul"]},{"id":"xtags","url":"https://github.com/manifoldor/xtags","title":"xtags","content_text":"\u5728 X \u7684\u65f6\u95f4\u7ebf\u4e0a\uff0c\u7ed9\u6bcf\u6761\u5e16\u5b50\u6807\u51fa\u5b83\u60f3\u8ba9\u4f60\u5e72\u4ec0\u4e48\u3002\u5224\u65ad\u6765\u81ea Jev\uff0c\u4e00\u4e2a\u53ea\u8fd4\u56de\u6982\u7387\u3001\u4e0d\u751f\u6210\u6587\u672c\u7684\u6a21\u578b\u3002","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"manifoldor"}],"tags":["browser-computer-use","choice","noul"]},{"id":"jev-browser-vinilana","url":"https://github.com/vinilana/jev-browser","title":"jev-browser (vinilana)","content_text":"A hybrid browser usage harness in TypeScript: an OpenRouter LLM turns goals into verifiable subgoals, Jev chooses each action and DOM field, OpenRouter generates text whenever a field needs filling, and Playwright execut","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"vinilana"}],"tags":["browser-computer-use","choice"]},{"id":"live-jev","url":"https://github.com/vinilana/live-jev","title":"live-jev","content_text":"2D autonomous car simulation in the browser, driven by TypeSafe's Jev decision model","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"vinilana"}],"tags":["browser-computer-use","choice","score","noul"]},{"id":"askjev","url":"https://github.com/ranjan2829/AskJev","title":"AskJev","content_text":"AskJev \u2014 Jev autopilot for any website + guard on irreversible clicks (TypeSafe System One, not Claude)","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"ranjan2829"}],"tags":["browser-computer-use","choice","score","noul"]},{"id":"computer-use","url":"https://github.com/paulsmith/computer-use-jev","title":"computer_use","content_text":"macOS computer use driven by Jev (TypeSafe System One) as the decision maker","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"paulsmith"}],"tags":["browser-computer-use","choice"]},{"id":"jev-browser-tontoko","url":"https://github.com/tontoko/jev-browser","title":"jev-browser (tontoko)","content_text":"One grounded Jev/Playwright core: typed SDK, persistent CLI, and MCP server with native browser operations and deterministic assertions.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"tontoko"}],"tags":["browser-computer-use","choice"]},{"id":"jev-ego","url":"https://github.com/romaluev/jev-ego","title":"jev-ego","content_text":"Fast browser agent for ego lite. One TypeSafe request per step; an agent or Jev picks the move.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"romaluev"}],"tags":["browser-computer-use","choice"]},{"id":"jev-frontend-qa","url":"https://github.com/Nainish-Rai/jev-frontend-qa","title":"jev-frontend-qa","content_text":"Evidence-driven frontend QA built on Jev Ultrafast and Browser Harness, with a synthetic todo demo.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Nainish-Rai"}],"tags":["browser-computer-use","choice","score"]},{"id":"jev-shield-vmendes90","url":"https://github.com/vmendes90/jev-shield","title":"jev-shield (vmendes90)","content_text":"Privacy-first Chrome extension that semantically blocks native ads, sponsored feed cards, and video ads using TypeSafe Jev","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"vmendes90"}],"tags":["browser-computer-use","score","noul"]},{"id":"almond-fastloop","url":"https://github.com/eriestra/almond-fastloop","title":"almond-fastloop","content_text":"Almond-fastloop: Almond's browser computer-use rig (Chrome DevTools + TypeSafe Jev), and the Browser Use Olympics benchmark it is measured on.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"eriestra"}],"tags":["browser-computer-use","choice"]},{"id":"barrunto","url":"https://github.com/elpumberto/barrunto","title":"barrunto","content_text":"A Chrome extension that brings TypeSafe's Jev to X.com to analyze posts as you browse","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"elpumberto"}],"tags":["browser-computer-use"]},{"id":"jev-browse","url":"https://github.com/kyrylosyzonenko/jev-browse","title":"jev-browse","content_text":"jev-browse drives a real browser with making every decision and performing every action. You give it a goal, such as open the Hacker News FAQ. Jev picks each click, chooses which of your texts to type into which box, and","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"kyrylosyzonenko"}],"tags":["browser-computer-use"]},{"id":"otto","url":"https://github.com/NobleSpartan6/otto","title":"otto","content_text":"Open-source native computer use for macOS and Windows: TypeSafe Jev, local OCR, and selective planning.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"NobleSpartan6"}],"tags":["browser-computer-use","score"]},{"id":"psearch","url":"https://github.com/komikat/psearch","title":"psearch","content_text":"Parallel web search for terminals and agents, with local Chromium and Jev-guided exploration.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"komikat"}],"tags":["browser-computer-use","score"]},{"id":"browser-use-olympics","url":"https://github.com/eriestra/browser-use-olympics","title":"browser-use-olympics","content_text":"Browser Use Olympics by Almond: one prompt, five events, one clock. Plus fast loop, a ~200-line browser computer-use agent (Chrome DevTools + TypeSafe Jev).","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"eriestra"}],"tags":["browser-computer-use","choice"]},{"id":"jev-browser-kesavanking","url":"https://github.com/KesavanKing/jev-browser","title":"jev-browser (KesavanKing)","content_text":"Local browser automation UI that uses TypeSafe Jev to choose bounded page actions and a text model only for field values.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"KesavanKing"}],"tags":["browser-computer-use"]},{"id":"jev-browser-mahmoudadelbghany","url":"https://github.com/MahmoudAdelbghany/jev-browser","title":"jev-browser (MahmoudAdelbghany)","content_text":"Jev-powered browser MCP for LLM agents \u2014 ~300ms decisions, no LLM tokens in the loop. Benchmark vs Playwright MCP included.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"MahmoudAdelbghany"}],"tags":["browser-computer-use","choice","score","noul"]},{"id":"jev-mobile","url":"https://github.com/Friedjof/jev-mobile","title":"jev-mobile","content_text":"Fast structured Android control loops with TypeSafe Jev and Mobile MCP","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Friedjof"}],"tags":["browser-computer-use","choice"]},{"id":"jev-playwright-mcp","url":"https://github.com/krw82/jev-playwright-mcp","title":"jev-playwright-mcp","content_text":"Jev-augmented Playwright MCP proxy \u2014 page-state triage, prompt-injection shielding, goal-based snapshot pruning, risky-action gating. Drop-in wrapper around @playwright/mcp for any coding agent.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"krw82"}],"tags":["browser-computer-use"]},{"id":"jevtest","url":"https://github.com/CorieW/JevTest","title":"JevTest","content_text":"Bounded exploratory browser testing with Jev, deterministic assertions, and replayable evidence.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"CorieW"}],"tags":["browser-computer-use"]},{"id":"sift","url":"https://github.com/tylergibbs1/sift","title":"sift","content_text":"Chrome extension that re-ranks Google results with TypeSafe Jev and folds away sales pages and SEO filler.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"tylergibbs1"}],"tags":["browser-computer-use","score","noul"]},{"id":"sloppy-jevs-extension","url":"https://github.com/neddes/sloppy-jevs-extension","title":"sloppy-jevs-extension","content_text":"Open-source Chrome extension that filters AI-generated prose and ads with Jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"neddes"}],"tags":["browser-computer-use","choice","score","noul"]},{"id":"turbo","url":"https://github.com/sightmap/jev-turbo","title":"turbo","content_text":"Jev-powered semantic browser use","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"sightmap"}],"tags":["browser-computer-use"]},{"id":"jev-trader","url":"https://github.com/jarrodwatts/jev-trader","title":"jev-trader","content_text":"Trading bot that asks Jev for a decision on every Monad block \u2014 sub-second Choice calls fit block time.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"jarrodwatts"}],"tags":["applications"]},{"id":"notra","url":"https://github.com/usenotra/notra","title":"notra","content_text":"Turn Your Work Into Content","date_published":"2025-12-13T00:00:00Z","authors":[{"name":"usenotra"}],"tags":["applications"]},{"id":"jevmeter","url":"https://github.com/ChetasLua/jevmeter","title":"jevmeter","content_text":"Put a live Jev (TypeSafe) meter on any video: every sentence scored, rendered as a 16:9 edit","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"ChetasLua"}],"tags":["applications","score","noul"]},{"id":"jev-moderation-bot","url":"https://github.com/brainstormity/Jev-Moderation-Bot","title":"Jev-Moderation-Bot","content_text":"A Discord moderation bot built with Python and TypeSafe AI (Jev System One). It filters spam and scam links in real time, escalates offenses automatically, and lets moderators profile members based on their message histo","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"brainstormity"}],"tags":["applications","score"]},{"id":"commit-miner","url":"https://github.com/devanshbatham/commit-miner","title":"commit-miner","content_text":"Classify Git commit diffs and messages with Jev. Bug fixes, security fixes/CWEs, and change types.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"devanshbatham"}],"tags":["applications"]},{"id":"blink","url":"https://github.com/ellipsis-dev/blink","title":"blink","content_text":"Codebase search powered by Jev from @typesafe-ai","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"ellipsis-dev"}],"tags":["applications","choice","score"]},{"id":"jev-trades","url":"https://github.com/zadescoxp/Jev-Trades","title":"Jev-Trades","content_text":"Trading bot with the all new TypeSafe AI's first system one model named as Jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"zadescoxp"}],"tags":["applications"]},{"id":"jevlogs","url":"https://github.com/reachjalil/jevlogs","title":"jevlogs","content_text":"Open-source Jev log triage for OpenTelemetry. Score the signal before expensive LLM analysis.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"reachjalil"}],"tags":["applications","choice","score"]},{"id":"ai-elo-ranker","url":"https://github.com/opaielsheikh/ai-elo-ranker","title":"ai-elo-ranker","content_text":"High-speed recursive AI Elo tournament engine powered by Jev and Swiss matchmaking","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"opaielsheikh"}],"tags":["applications","score"]},{"id":"semdecide","url":"https://github.com/sharziki/semdecide","title":"semdecide","content_text":"Typed semantic decisions for Unix pipelines and CI, powered by TypeSafe AI Jev.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"sharziki"}],"tags":["applications","score"]},{"id":"refgarden","url":"https://github.com/AlbionaHoti/refgarden","title":"refgarden","content_text":"A spatial reference explorer for creators. Local Jev query choices, metadata highlights and source-linked collections.","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"AlbionaHoti"}],"tags":["applications","choice"]},{"id":"typesafe-cli-y0usaf","url":"https://github.com/y0usaf/typesafe-cli","title":"typesafe-cli (y0usaf)","content_text":"Ask Jev typed questions from the shell: noul, choice, and score answers as numbers, not prose","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"y0usaf"}],"tags":["applications","choice","score","noul"]},{"id":"jev-grug","url":"https://github.com/mkotlikov/jev-grug","title":"jev-grug","content_text":"Helping JEV speak <3","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"mkotlikov"}],"tags":["applications","choice","noul"]},{"id":"jev-trade","url":"https://github.com/aowang-ai/jev-trade","title":"jev-trade","content_text":"Live Jev trader on Hyperliquid","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"aowang-ai"}],"tags":["applications"]},{"id":"every","url":"https://github.com/sufianetaouil/every","title":"every","content_text":"Ask a yes/no question of every function in a codebase. Ranked answers in seconds, for cents. Grep whose pattern is a question, powered by TypeSafe Jev.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"sufianetaouil"}],"tags":["applications","score"]},{"id":"jev-cli-tumf","url":"https://github.com/tumf/jev-cli","title":"jev-cli (tumf)","content_text":"Small dependency-free CLI for TypeSafe Jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"tumf"}],"tags":["applications","choice","score","noul"]},{"id":"jev-tree","url":"https://github.com/reachjalil/jev-tree","title":"jev-tree","content_text":"Recursive Jev choice over a taxonomy. Select from more than 255 options without breaking TypeSafe Jev's choice cap.","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"reachjalil"}],"tags":["applications","choice"]},{"id":"jevibe-check","url":"https://github.com/sriganesh/jevibe-check","title":"jevibe-check","content_text":"A live tone labeler for Bluesky posts and drafts, using TypeSafe's Jev API.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"sriganesh"}],"tags":["applications"]},{"id":"jevocks","url":"https://github.com/unicodeveloper/jevocks","title":"jevocks","content_text":"Everyday Stocks Status with Jev","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"unicodeveloper"}],"tags":["applications","choice","score"]},{"id":"jevsql","url":"https://github.com/EugeneBoondock/jevsql","title":"jevsql","content_text":"SQL with natural-language predicates, powered by TypeSafe's Jev. Filter, rank, classify and score rows by meaning \u2014 batched, cached and cost-guarded.","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"EugeneBoondock"}],"tags":["applications","choice","score","noul"]},{"id":"smart-switch","url":"https://github.com/reycn/smart-switch","title":"smart-switch","content_text":"Reimagined window switcher for macOS using frontier artificial intelligence. Predicted by TypeSafe's Jev model","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"reycn"}],"tags":["applications","choice"]},{"id":"btc-jev-signal","url":"https://github.com/WebGrga/btc-jev-signal","title":"btc-jev-signal","content_text":"Experimental multi-horizon BTC signal generator using TypeSafe Jev probabilities and Binance market data.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"WebGrga"}],"tags":["applications","score"]},{"id":"commentcop","url":"https://github.com/ntedvs/commentcop","title":"commentcop","content_text":"Put your code comments on trial. Powered by Jev.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"ntedvs"}],"tags":["applications","score"]},{"id":"jackalope","url":"https://github.com/Jackalope-Dev/jackalope","title":"Jackalope","content_text":"A desktop workspace for coding agents, parallel Git worktrees, and code review.","date_published":"2026-09-06T00:00:00Z","authors":[{"name":"Jackalope-Dev"}],"tags":["applications"]},{"id":"jev-cli","url":"https://github.com/jtsang4/jev-cli","title":"jev-cli","content_text":"CLI for TypeSafe AI's Jev evaluation model \u2014 typed questions in, structured JSON answers out","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"jtsang4"}],"tags":["applications","choice","score"]},{"id":"jev-rerank","url":"https://github.com/hev/reranker","title":"jev-rerank","content_text":"Use Jev (TypeSafe's System One model) as a calibrated reranker: one call, up to 30 documents, a probability per document. Apache-2.0.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"hev"}],"tags":["applications","choice","score","noul"]},{"id":"qualm","url":"https://github.com/qddegtya/qualm","title":"qualm","content_text":"Typed decisions from a System One model. An uncertain answer is a different type from a confident one \u2014 and the compiler makes you handle it.","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"qddegtya"}],"tags":["applications","choice","score"]},{"id":"typesafe-jev","url":"https://github.com/gtaras7/typesafe-jev","title":"typesafe-jev","content_text":"Screen a folder of CVs with the TypeSafe Jev decision model: typed judgments, an editable policy, free re-scoring.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"gtaras7"}],"tags":["applications","score"]},{"id":"citation-verifier","url":"https://github.com/MarissaFamularo/citation-verifier","title":"citation-verifier","content_text":"Check whether each cited paper supports the sentence citing it. Claude proves the quote, TypeSafe's Jev scores it, a human decides.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"MarissaFamularo"}],"tags":["applications","score"]},{"id":"dmx-to","url":"https://dmx.to","title":"dmx.to","content_text":"An X client whose timeline is filtered by Jev smart rules: state in, keep-or-hide decisions out.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Kitze"}],"tags":["applications"]},{"id":"draftpulse","url":"https://github.com/pekth/draftpulse","title":"draftpulse","content_text":"Experimental: live X draft viral scorer powered by TypeSafe Jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"pekth"}],"tags":["applications","score"]},{"id":"emoji-jev","url":"https://github.com/colinmcdermott/emoji-jev","title":"emoji-jev","content_text":"Emoji autocomplete at the speed of typing. TypeSafe AI Jev on a Whop-hosted TanStack Start app.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"colinmcdermott"}],"tags":["applications","choice","score"]},{"id":"jev-classifier","url":"https://jevclassifier.vercel.app","title":"Jev Classifier","content_text":"Classify","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Unattributed"}],"tags":["applications"]},{"id":"jev-audio-beeper","url":"https://github.com/santos-sanz/jev-audio-beeper","title":"jev-audio-beeper","content_text":"Low-latency audio censorship POC using Jev typed decisions and ffmpeg.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"santos-sanz"}],"tags":["applications","choice","score"]},{"id":"jev-document-classification","url":"https://github.com/Charlyhno-eng/jev-document-classification","title":"jev-document-classification","content_text":"JEV Document Classification enables the rapid and cost-effective classification of text-based documents using AI, leveraging TypeSafe's \"System One\" model.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Charlyhno-eng"}],"tags":["applications"]},{"id":"jev-resume-analyzer","url":"https://github.com/awun8191/jev-resume-analyzer","title":"jev-resume-analyzer","content_text":"CV diagnostics and job alignment with TypeSafe Jev, React and FastAPI","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"awun8191"}],"tags":["applications","score"]},{"id":"jevegis","url":"https://github.com/0xArx/jevegis","title":"jevegis","content_text":"Guardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"0xArx"}],"tags":["applications"]},{"id":"jevticktrouter","url":"https://github.com/GhrezaKh74/JevTicktRouter","title":"JevTicktRouter","content_text":"A .NET 10 and React 19 application for fast, structured AI-powered ticket triage using TypeSafe Jev.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"GhrezaKh74"}],"tags":["applications","choice","score","noul"]},{"id":"mimicry","url":"https://github.com/jxucoder/mimicry","title":"mimicry","content_text":"Rewrite AI drafts in your own voice with a bounded TypeSafe feedback loop.","date_published":"2026-09-13T00:00:00Z","authors":[{"name":"jxucoder"}],"tags":["applications","score","noul"]},{"id":"pkg-gate","url":"https://github.com/hemanth/pkg-gate","title":"pkg-gate","content_text":"Pre-install security gate for npm lifecycle scripts using TypeSafe System One.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"hemanth"}],"tags":["applications","choice","score"]},{"id":"s1s","url":"https://github.com/cpaczek/s1s","title":"s1s","content_text":"System One Search: navigate and trace code with TypeSafe judgments and repository evidence","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"cpaczek"}],"tags":["applications","score"]},{"id":"scam-shield","url":"https://github.com/ShupingR/scam-shield","title":"scam-shield","content_text":"Scam text message filter powered by TypeSafe's Jev model","date_published":"2026-09-13T00:00:00Z","authors":[{"name":"ShupingR"}],"tags":["applications","choice","score","noul"]},{"id":"transcript-scorecard","url":"https://github.com/brandonbryant12/transcript-scorecard","title":"transcript-scorecard","content_text":"ACME live support-call scoring demo with TypeSafe AI, Effect, SQLite, React, Vite, and Turborepo","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"brandonbryant12"}],"tags":["applications","score"]},{"id":"typesafe-comment","url":"https://github.com/Hexdigest123/typesafe-comment","title":"typesafe-comment","content_text":"Small Python package that uses typesafe.ai to evaluate code comments on certain heuristics","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Hexdigest123"}],"tags":["applications"]},{"id":"typesafe-triage-guard","url":"https://github.com/shivam2003-dev/typesafe-triage-guard","title":"typesafe-triage-guard","content_text":"Three composable judgment pipelines on TypeSafe's Jev: support-ticket triage, observability alert triage, and a deploy-risk gate.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"shivam2003-dev"}],"tags":["applications","choice","score","noul"]},{"id":"typesafe-mario","url":"https://github.com/fhshaik/typesafe-mario","title":"typesafe-mario","content_text":"Plays NES Super Mario Bros. from structured emulator state \u2014 Jev reads the level state and picks the next move, no pixels involved.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"fhshaik"}],"tags":["demos-bots","choice","score","noul"]},{"id":"jev-drone","url":"https://github.com/RomanSlack/jev-drone","title":"jev-drone","content_text":"MuJoCo drone-control study: Jev makes per-tick flight decisions from physics state instead of a policy network.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"RomanSlack"}],"tags":["demos-bots","choice","score","noul"]},{"id":"typesafe-snake","url":"https://github.com/sorrycc/typesafe-snake","title":"typesafe-snake","content_text":"Snake auto-played by TypeSafe's Jev model: one System One choice per tick, legal moves and facts generated in code","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"sorrycc"}],"tags":["demos-bots","choice"]},{"id":"tsai-sc","url":"https://github.com/phyous/tsai-sc","title":"tsai-sc","content_text":"TypeSafe Jev controls original StarCraft shareware through keyboard and mouse with recorded action probabilities.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"phyous"}],"tags":["demos-bots","choice"]},{"id":"mario-jev","url":"https://github.com/shantanugoel/mario-jev","title":"mario-jev","content_text":"A uv-managed Python prototype that plays NES Super Mario Bros. (level 1-1 by default).","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"shantanugoel"}],"tags":["demos-bots","choice","noul"]},{"id":"jev-driving-lab","url":"https://github.com/kavehmz/typesafe-playground","title":"Jev Driving Lab","content_text":"Interactive experiments with TypeSafe Jev, from support routing to 3D driving simulations with real AI decisions and visible sensor inputs.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"kavehmz"}],"tags":["demos-bots"]},{"id":"onevonejev","url":"https://github.com/emrickgarrett/OneVOneJev","title":"OneVOneJev","content_text":"1v1 Jev quickscope arena \u2014 Three.js + TypeSafe System One","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"emrickgarrett"}],"tags":["demos-bots","choice","noul"]},{"id":"heist-one","url":"https://github.com/AbdelStark/heist-one","title":"heist-one","content_text":"Observable browser stealth game: Jev makes typed guard judgments while deterministic code owns the world.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"AbdelStark"}],"tags":["demos-bots","choice","score","noul"]},{"id":"jev-askable-arm","url":"https://github.com/TarunTomar122/jev-askable-arm","title":"jev-askable-arm","content_text":"Zero-shot English goals on a sim Franka. Jev chains hardcoded primitives.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TarunTomar122"}],"tags":["demos-bots"]},{"id":"jev-doom-agent","url":"https://github.com/lukaske/jev-doom-agent","title":"jev-doom-agent","content_text":"A browser-native Doom agent experiment with structured spatial state, composable AI controls, live decision telemetry, and a Chocolate Doom WebAssembly runtime.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"lukaske"}],"tags":["demos-bots","choice"]},{"id":"jev-gomoku-xiechengyuan","url":"https://github.com/XieChengYuan/jev-gomoku","title":"jev-gomoku (XieChengYuan)","content_text":"\u5f08\u77ac\uff1a\u53cc Jev \u4e94\u5b50\u68cb\u4e5d\u5bab\u683c\u8f93\u5165\u5b9e\u9a8c\u53f0\uff0c\u9010\u624b\u67e5\u770b\u6a21\u578b\u51b3\u7b56\uff0c\u652f\u6301\u771f\u5b9e\u5bf9\u5c40\u56de\u653e\u4e0e\u5b9e\u65f6\u5bf9\u6218\u3002","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"XieChengYuan"}],"tags":["demos-bots","choice","score","noul"]},{"id":"rubikjev","url":"https://github.com/0xtrou/rubikjev","title":"rubikjev","content_text":"Challenge the Jev's intelligence in Rubik Cube puzzles","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"0xtrou"}],"tags":["demos-bots","choice","score"]},{"id":"tsai-civ2","url":"https://github.com/phyous/tsai-civ2","title":"tsai-civ2","content_text":"TypeSafe Jev plays original Civilization II in a browser, with live action probabilities. Experimental full-game harness.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"phyous"}],"tags":["demos-bots","choice"]},{"id":"agent-jev-tetris","url":"https://github.com/Yasserbhb/Agent-JEV-Tetris","title":"Agent-JEV-Tetris","content_text":"using the new model JEV to play the game tetris ","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Yasserbhb"}],"tags":["demos-bots","choice"]},{"id":"beatjev","url":"https://github.com/lambertsj/beatjev","title":"beatjev","content_text":"try to beat jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"lambertsj"}],"tags":["demos-bots","noul"]},{"id":"casse-brique-typesafe","url":"https://github.com/Para-FR/casse-brique-typesafe","title":"casse-brique-typesafe","content_text":"A Next.js brick breaker whose paddle is controlled in real time by TypeSafe AI's Jev model. Built with Claude Code.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Para-FR"}],"tags":["demos-bots","choice","score"]},{"id":"chess-jev","url":"https://chess-jev.loomens.com","title":"chess-jev","content_text":"Browser chess where Jev picks moves from structured board state \u2014 'one model, two instincts' lets you play either side.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"loomens"}],"tags":["demos-bots"]},{"id":"cyber-breach-jev","url":"https://github.com/rchovatiya88/cyber-breach-jev","title":"cyber-breach-jev","content_text":"Cyber-Breach: The Jev Protocol - A tactical cyberpunk arena combat game powered by TypeSafe AI Jev System One decision model","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"rchovatiya88"}],"tags":["demos-bots","choice","score","noul"]},{"id":"game-plan","url":"https://game-plan.adriaansendennis.workers.dev/play","title":"Game Plan","content_text":"Connect two seemingly unrelated things using the fewest possible steps.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Adriaan Senden-Dennis"}],"tags":["demos-bots"]},{"id":"hollow-creek","url":"https://hollow-creek-sigma.vercel.app","title":"Hollow Creek","content_text":"Hollow Creek","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Unattributed"}],"tags":["demos-bots"]},{"id":"hundred","url":"https://github.com/jammaru/jev-lab","title":"hundred","content_text":"100 AI NPCs live in a tiny town. Jev chooses the next action; the world writes the story.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"jammaru"}],"tags":["demos-bots","choice"]},{"id":"jev-arcade","url":"https://jev-arcade.vercel.app/duel","title":"Jev Arcade","content_text":"Two playable games against a live Jev AI. An industrial arena duel and a neon survival challenge.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Unattributed"}],"tags":["demos-bots"]},{"id":"jev-board-games","url":"https://jevboardgames.everpaper.app/","title":"Jev board games","content_text":"Tic-tac-toe and Connect Four against Jev. The model picks the move, the code keeps the rules.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"everpaper"}],"tags":["demos-bots"]},{"id":"jev-pac-man","url":"https://jev-pacman.ephraimduncan.com","title":"Jev Pac-Man","content_text":"TypeSafe's Jev model steers a Pac-Man recreation from structured game state.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Ephraim Duncan"}],"tags":["demos-bots"]},{"id":"jev-tetris","url":"https://jev-omega.vercel.app","title":"Jev Tetris","content_text":"Playable Tetris where Jev picks rotation and column from holes, stack height and board state.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Unattributed"}],"tags":["demos-bots"]},{"id":"jev-bfs","url":"https://github.com/komikat/jev-bfs","title":"jev-bfs","content_text":"Wikipedia link races with direct Jev ranking and a live terminal display.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"komikat"}],"tags":["demos-bots","score"]},{"id":"jev-games","url":"https://github.com/shantanugoel/jev-games","title":"jev-games","content_text":"Visual Jev lab for multiple games and emulator platforms","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"shantanugoel"}],"tags":["demos-bots"]},{"id":"jev-gomoku","url":"https://github.com/mizchi/jev-gomoku","title":"jev-gomoku","content_text":"TypeSafe AI \u306e System One \u30e2\u30c7\u30eb Jev \u3092 MoonBit \u304b\u3089\u89e6\u308b\u305f\u3081\u306e\u30d7\u30ec\u30a4\u30b0\u30e9\u30a6\u30f3\u30c9\u3002","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"mizchi"}],"tags":["demos-bots","choice","score","noul"]},{"id":"jev-play-ping-pong","url":"https://github.com/Icohen007/jev-play-ping-pong","title":"jev-play-ping-pong","content_text":"Jev plays browser table tennis in real time: structured telemetry, typed decisions, ordinary Chrome inputs, and auditable evidence.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Icohen007"}],"tags":["demos-bots","choice","score"]},{"id":"jev-snake","url":"https://github.com/iammusham/jev-snake","title":"jev-snake","content_text":"An experimental Snake environment where the game engine owns deterministic rules and TypeSafe AI's Jev makes the movement decision from structured state on every tick.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"iammusham"}],"tags":["demos-bots","choice","score"]},{"id":"jev-t-rex-runner","url":"https://github.com/joshlarsen/jev-t-rex-runner","title":"jev-t-rex-runner","content_text":"Chrome dino game played by Typesafe AI Jev model","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"joshlarsen"}],"tags":["demos-bots","score"]},{"id":"jev-tetris-machinelearning-nerd","url":"https://github.com/MachineLearning-Nerd/jev-tetris","title":"jev-tetris","content_text":"Jev picks rotation and column from holes, stack height and board state \u2014 a live playable Tetris driven by typed choices.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"MachineLearning-Nerd"}],"tags":["demos-bots","choice","score"]},{"id":"jev-mods","url":"https://github.com/Hardel-DW/jev.mods","title":"jev.mods","content_text":"Il doit finir le jeu peut importe de quel mani\u00e9res.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Hardel-DW"}],"tags":["demos-bots"]},{"id":"jev2048","url":"https://github.com/KyleKreuter/jev2048","title":"jev2048","content_text":"Let Jev (TypeSafeAI) solve 2048","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"KyleKreuter"}],"tags":["demos-bots","choice","score"]},{"id":"last-exit","url":"https://github.com/0x963D/last-exit","title":"last-exit","content_text":"A cyberpunk border encounter powered by TypeSafe Jev. Bluff the guard. Inspect the receipts.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"0x963D"}],"tags":["demos-bots"]},{"id":"pdoom-protocol","url":"https://github.com/onionminionops-beep/pdoom-protocol","title":"pdoom-protocol","content_text":"USER + JEV: P(DOOM) PROTOCOL \u2014 co-op platform shooter where TypeSafe Jev plays alongside you","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"onionminionops-beep"}],"tags":["demos-bots"]},{"id":"pong-jev","url":"https://github.com/safzanpirani/pong-jev","title":"pong-jev","content_text":"TypeSafe's Jev plays Atari Pong. One typed Choice question per frame, no coordinates sent to the model.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"safzanpirani"}],"tags":["demos-bots","choice","score"]},{"id":"ps2-ai-agent","url":"https://github.com/opaielsheikh/ps2-ai-agent","title":"ps2-ai-agent","content_text":"Autonomous PlayStation 2 AI Agent with real-time visual telemetry HUD powered by TypeSafe Jev System One","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"opaielsheikh"}],"tags":["demos-bots"]},{"id":"river-oaks","url":"https://github.com/BunsDev/river-oaks","title":"river-oaks","content_text":"NPCs of River Oaks Houston, Texas using Jev to power NPCs","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"BunsDev"}],"tags":["demos-bots"]},{"id":"river-run-typesafe","url":"https://github.com/ashaazami/river-run-typesafe","title":"river-run-typesafe","content_text":"River shooter game in Python, inspired by Atari's River Raid, played by a TypeSafe AI pilot","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"ashaazami"}],"tags":["demos-bots","score"]},{"id":"roverlab","url":"https://github.com/juancamiloqhz/roverlab","title":"roverlab","content_text":"A 3D planetary rover sandbox for experimenting with autonomous decisions using TypeSafe AI.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"juancamiloqhz"}],"tags":["demos-bots","choice","score"]},{"id":"shady-town","url":"https://github.com/tpaulshippy/shady-town","title":"shady-town","content_text":"Shady Town: social-deduction party game for the living room TV, moderated by TypeSafe Jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"tpaulshippy"}],"tags":["demos-bots"]},{"id":"siege","url":"https://github.com/vnmoorthy/siege","title":"siege","content_text":"SIEGE: 200 people vs one agent. A typed action gate (TypeSafe System One) that learns from every breach, evaluated by W&B Weave, hardened by a defender loop. Built at CoreWeave Hacks: Agent Loops 2026.","date_published":"2026-09-13T00:00:00Z","authors":[{"name":"vnmoorthy"}],"tags":["demos-bots","choice","score"]},{"id":"snake-jev","url":"https://github.com/siroccomask/snake-jev","title":"snake-jev","content_text":"Snake controlled by parallel Jev assessments, with one API call per game tick.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"siroccomask"}],"tags":["demos-bots","choice"]},{"id":"terrarium","url":"https://github.com/TheGali/terrarium","title":"terrarium","content_text":"A sandbox where a TypeSafe System One model presses the controls of a small creature. Code runs the world.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TheGali"}],"tags":["demos-bots","choice","score","noul"]},{"id":"typesafe-3d-chess","url":"https://github.com/malDuffin/typesafe-3d-chess","title":"typesafe-3d-chess","content_text":"3D chess powered by TypeSafe AI (Jev). AI vs AI by default, or play either side. Multiple difficulty levels.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"malDuffin"}],"tags":["demos-bots"]},{"id":"typesafe-chess","url":"https://github.com/TholeG/typesafe-chess","title":"typesafe-chess","content_text":"Chess where both players are TypeSafe's Jev model: every move is a typed Choice decision","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TholeG"}],"tags":["demos-bots","choice","score","noul"]},{"id":"typesafe-minecraft-demo","url":"https://github.com/ellistev/typesafe-minecraft-demo","title":"typesafe-minecraft-demo","content_text":"A Minecraft Java player controlled by TypeSafe AI, with live decisions, Canadian flag building, and a side-by-side dashboard.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"ellistev"}],"tags":["demos-bots","choice"]},{"id":"killmyidea","url":"https://github.com/monteduro/killmyidea","title":"killmyidea","content_text":"Describe your startup idea. Jev decides: kill it, fix it or ship it.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"monteduro"}],"tags":["demos-bots","score"]},{"id":"jev-me","url":"https://github.com/jon-devlapaz/jev-me","title":"jev-me","content_text":"Grill-me with Jev optional each turn","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"jon-devlapaz"}],"tags":["demos-bots","choice"]},{"id":"typesafe-ai-playground-bunsdev","url":"https://github.com/BunsDev/typesafe-ai-playground","title":"typesafe-ai-playground (BunsDev)","content_text":"Community TypeSafe AI playground: 110 use cases, games, dilemmas and model challenges, with editable prompts, A/B comparisons and a mobile-friendly UI.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"BunsDev"}],"tags":["demos-bots","choice","score","noul"]},{"id":"jev-autopilot","url":"https://github.com/arielweinberger/jev-autopilot","title":"jev-autopilot","content_text":"This demo uses Jev from TypeSafe AI to autonomously fly a drone in a random city from point A to point B, avoiding obstacles along the way. A trip costs $0.01.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"arielweinberger"}],"tags":["demos-bots","choice"]},{"id":"jev-system-one","url":"https://github.com/haseeb-heaven/jev-system-one","title":"jev-system-one","content_text":"A polished OpenAI + TypeSafe Jev terminal interface for answers with transparent decision reports","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"haseeb-heaven"}],"tags":["demos-bots","choice","score","noul"]},{"id":"should-ai-kill-us-all","url":"https://github.com/hellogumbo/should-ai-kill-us-all","title":"Should AI Kill Us All?","content_text":"A live verdict page that asks Jev every ten minutes whether AI should kill us all, fed by the day's odd news.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"hellogumbo"}],"tags":["demos-bots","choice","score","noul"]},{"id":"typesafe-ai-playground","url":"https://github.com/nickthompson480/typesafe-ai-playground","title":"typesafe-ai-playground","content_text":"Community TypeSafe AI playground: 110 use cases, games, dilemmas and model challenges, with editable prompts, A/B comparisons and a mobile-friendly UI.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"nickthompson480"}],"tags":["demos-bots","choice","score","noul"]},{"id":"clarity-judge","url":"https://github.com/BunsDev/clarity-judge","title":"clarity-judge","content_text":"Multi-axis writing quality checker powered by TypeSafe AI's Jev model. Separate named checks, each with its own verdict and confidence.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"BunsDev"}],"tags":["demos-bots","choice","score","noul"]},{"id":"got-jev","url":"https://github.com/phureewat29/got-jev","title":"got-jev","content_text":"Jev (TypeSafe AI) PoC through Game of Thrones","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"phureewat29"}],"tags":["demos-bots","score"]},{"id":"gpt-vs-jev","url":"https://github.com/TanayPadar/gpt-vs-jev","title":"gpt-vs-jev","content_text":"Compare GPT generated language with JEV structured Noul decisions on the same input.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TanayPadar"}],"tags":["demos-bots","noul"]},{"id":"guard-jev","url":"https://github.com/NorbertBodziony/guard-jev","title":"guard-jev","content_text":"Text moderation demo: one TypeSafe systemOne call screens 7 Noul hazards + 1 severity Score in parallel. Verdict computed in code via policy thresholds.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"NorbertBodziony"}],"tags":["demos-bots","score","noul"]},{"id":"harden-jev-decides","url":"https://github.com/tylerjharden/harden-jev-decides","title":"harden-jev-decides","content_text":"JEV picks which stream idea becomes the live MVP. TypeSafe System One decision board.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"tylerjharden"}],"tags":["demos-bots","choice"]},{"id":"instinct","url":"https://github.com/joevidev/ui-generator-instinct-jev","title":"Instinct","content_text":"Describe it. Jev decides. A demo of \u2014 TypeSafe's \"System One\" model \u2014 as a UI generator. You describe a case in free text; Jev never generates a line of code or copy back. It only ever answers typed questions (Choice, No","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"joevidev"}],"tags":["demos-bots","choice","score","noul"]},{"id":"jev-playground-little-planet-labs","url":"https://github.com/Little-Planet-Labs/jev-playground","title":"jev-playground (Little-Planet-Labs)","content_text":"A small Next.js app for experimenting with TypeSafe AI's Jev model (System One)","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Little-Planet-Labs"}],"tags":["demos-bots","choice","score","noul"]},{"id":"toolgate","url":"https://github.com/ndolinschi/toolgate","title":"toolgate","content_text":"Agent tool/MCP call gate \u2014 allow / ask_human / deny via TypeSafe Jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"ndolinschi"}],"tags":["demos-bots","score"]},{"id":"typesafe-ai-playground-markjaquith","url":"https://github.com/markjaquith/typesafe-ai-playground","title":"typesafe-ai-playground (markjaquith)","content_text":"A playground for experiments around Jev, TypeSafe's System One model.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"markjaquith"}],"tags":["demos-bots","choice","score","noul"]},{"id":"typesafe-arena","url":"https://github.com/DeepBlueDynamics/typesafe-arena","title":"typesafe-arena","content_text":"A playground for TypeSafeAI's Jev Model","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"DeepBlueDynamics"}],"tags":["demos-bots","choice","score","noul"]},{"id":"cartshield","url":"https://github.com/ndolinschi/cartshield","title":"cartshield","content_text":"CartShield \u2014 SMB checkout fraud disposition via TypeSafe Jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"ndolinschi"}],"tags":["demos-bots"]},{"id":"crowdcheck","url":"https://crowdcheck-ai.vercel.app/","title":"Crowdcheck","content_text":"Test your post on 10,000 AI readers before the real internet sees it.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Unattributed"}],"tags":["demos-bots"]},{"id":"extremely-specific-council","url":"https://github.com/cbetz/extremely-specific-council","title":"extremely-specific-council","content_text":"Twelve members. Zero qualifications. A playful TypeSafe AI council with animated votes, inspectable decisions, and shareable verdicts.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"cbetz"}],"tags":["demos-bots","choice","score","noul"]},{"id":"harnessjudge","url":"https://github.com/ndolinschi/harnessjudge","title":"harnessjudge","content_text":"Judge agent steps \u2014 ok / retry / escalate / stop via TypeSafe Jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"ndolinschi"}],"tags":["demos-bots"]},{"id":"hiresignal","url":"https://github.com/ndolinschi/hiresignal","title":"hiresignal","content_text":"HireSignal \u2014 resume first-pass fit+interview via TypeSafe Jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"ndolinschi"}],"tags":["demos-bots"]},{"id":"human-compiler","url":"https://github.com/asfarsadewa/human-compiler","title":"human-compiler","content_text":"A compiler for human language. Paste text, get diagnostics. Measured by TypeSafe Jev.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"asfarsadewa"}],"tags":["demos-bots","choice","score","noul"]},{"id":"jev-gamecast","url":"https://github.com/narulaskaran/jev-data-questions","title":"Jev Gamecast","content_text":"Bring a dataset. Ask a question. See Jev classify every row.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"narulaskaran"}],"tags":["demos-bots","choice","score","noul"]},{"id":"jev-mood-demo","url":"https://jev-demo.vercel.app","title":"Jev mood demo","content_text":"A 3D robot companion driven by TypeSafe's Jev model: typed decisions, confidence gating, no text generation.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Unattributed"}],"tags":["demos-bots"]},{"id":"jev-room","url":"https://jev-room.moe136231.chatgpt.site","title":"Jev Room","content_text":"An interactive room that responds to your words. Explore presets or connect Jev to see real AI decisions.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"moe136231"}],"tags":["demos-bots"]},{"id":"jev-ad-preflight","url":"https://github.com/cardotrejos/jev-ad-preflight","title":"jev-ad-preflight","content_text":"Typesafe/Jev public X demo","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"cardotrejos"}],"tags":["demos-bots"]},{"id":"jev-board-lab","url":"https://github.com/WebGrga/jev-board-lab","title":"jev-board-lab","content_text":"Interactive explorer and Jev question workspace for Jev Board datasets.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"WebGrga"}],"tags":["demos-bots","choice","score","noul"]},{"id":"jev-bun1","url":"https://github.com/heiwa4126/jev-bun1","title":"jev-bun1","content_text":"TypeSafe \u306e Jev \u3092 TypeScript SDK \u3067\u4f7f\u3063\u3066\u307f\u308b\u6700\u521d\u306e 1 \u6b69","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"heiwa4126"}],"tags":["demos-bots","noul"]},{"id":"jev-demos","url":"https://github.com/Bud-ro/jev-demos","title":"jev-demos","content_text":"Demos to test the effectiveness of TypeSafe's \"Jev\" System One Model","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Bud-ro"}],"tags":["demos-bots"]},{"id":"jev-dev","url":"https://github.com/n-yokomachi/jev-dev","title":"jev-dev","content_text":"\u540c\u3058\u767a\u8a00\u3092 jev \u3068 LLM \u306e\u4e21\u65b9\u306b\u5224\u5b9a\u3055\u305b\u3001\u611f\u60c5\u306e\u5909\u52d5\u5024\u306e\u30ba\u30ec\u3068\u5fdc\u7b54\u901f\u5ea6\u30921\u753b\u9762\u3067\u898b\u6bd4\u3079\u308b\u30c7\u30e2\uff08affectus + Vercel AI Gateway\uff09","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"n-yokomachi"}],"tags":["demos-bots"]},{"id":"jev-paper-judge","url":"https://github.com/JacobLinCool/jev-paper-judge","title":"jev-paper-judge","content_text":"Feedback on your paper in seconds.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"JacobLinCool"}],"tags":["demos-bots","choice","score"]},{"id":"jev-playground-wustep","url":"https://github.com/wustep/jev-playground","title":"jev-playground (wustep)","content_text":"Can a System One model steer music? Jev picks the plan (enums only); code renders sheet, audio and MIDI.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"wustep"}],"tags":["demos-bots","choice","score","noul"]},{"id":"jev-should-i-apply","url":"https://github.com/cardotrejos/jev-should-i-apply","title":"jev-should-i-apply","content_text":"Typesafe/Jev public X demo","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"cardotrejos"}],"tags":["demos-bots"]},{"id":"jev-user-jury","url":"https://github.com/cardotrejos/jev-user-jury","title":"jev-user-jury","content_text":"Typesafe/Jev public X demo","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"cardotrejos"}],"tags":["demos-bots"]},{"id":"jevplay","url":"https://github.com/ndolinschi/jevplay","title":"jevplay","content_text":"TypeSafe Jev playground \u2014 custom Choice/Score/Noul builder with live distributions","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"ndolinschi"}],"tags":["demos-bots","choice","score","noul"]},{"id":"job-risk-analyzer","url":"https://github.com/WeSecureYou/Jev-test","title":"Job Risk Analyzer","content_text":"A TypeScript/Node.js CLI and REST API that uses TypeSafe AI's Jev System One model to evaluate an occupation's exposure to AI-driven layoffs, likely future trajectory, need for human accountability, and overall resilienc","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"WeSecureYou"}],"tags":["demos-bots","choice","score","noul"]},{"id":"lanebreak","url":"https://github.com/ndolinschi/lanebreak","title":"lanebreak","content_text":"LaneBreak \u2014 support ticket priority+routing via TypeSafe Jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"ndolinschi"}],"tags":["demos-bots"]},{"id":"mcpmatch","url":"https://github.com/ndolinschi/mcpmatch","title":"mcpmatch","content_text":"Match user goals to MCP catalog (two-stage) via TypeSafe Jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"ndolinschi"}],"tags":["demos-bots"]},{"id":"probably","url":"https://github.com/JordiParraCrespo/typesafe-ai-trading-showcase","title":"Probably","content_text":"Live BTC, ETH, and XRP prices with a shared TypeSafe buy/wait demonstration. No trades are placed. Not financial advice.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"JordiParraCrespo"}],"tags":["demos-bots"]},{"id":"pulselane","url":"https://github.com/ndolinschi/pulselane","title":"pulselane","content_text":"PulseLane \u2014 clinic triage decisions via TypeSafe Jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"ndolinschi"}],"tags":["demos-bots"]},{"id":"search-function-test","url":"https://github.com/Shifros/Search-Function-Test","title":"Search-Function-Test","content_text":"A test project based on Jev AI, the goal is to build a search function for a blog/article website that has 100s of articles to search from, So the user can actually use the search as chat to question anything and find re","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Shifros"}],"tags":["demos-bots"]},{"id":"spendbrake","url":"https://github.com/ndolinschi/spendbrake","title":"spendbrake","content_text":"Agent budget brake \u2014 continue / downgrade_model / stop via TypeSafe Jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"ndolinschi"}],"tags":["demos-bots"]},{"id":"swarmrouter","url":"https://github.com/ndolinschi/swarmrouter","title":"swarmrouter","content_text":"Route tasks to research/code/browser/support/writer agents via TypeSafe Jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"ndolinschi"}],"tags":["demos-bots"]},{"id":"trustgate","url":"https://github.com/ndolinschi/trustgate","title":"trustgate","content_text":"TrustGate \u2014 indie media T&S gate via TypeSafe Jev","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"ndolinschi"}],"tags":["demos-bots"]},{"id":"typesafe-typewriter","url":"https://typesafe-demo.val.run/","title":"TypeSafe Typewriter","content_text":"16 typed judgments about your text, asked in one call and re-run on every keystroke.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Steve Krouse"}],"tags":["demos-bots"]},{"id":"typesafe-image-diffusion","url":"https://github.com/Wizhill05/typesafe-image-diffusion","title":"typesafe-image-diffusion","content_text":"Diffusion-style pixel art out of a general classifier (TypeSafe Jev): 256 parallel pixel questions + refinement passes","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Wizhill05"}],"tags":["demos-bots","choice","score"]},{"id":"yes-no","url":"https://yesno.coderai.dev","title":"Yes / No","content_text":"Test Jev, the System One model from TypeSafe AI, for free. Ask any question and get one clear answer \u2014 Yes, No or Maybe \u2014 grounded in live web search when it needs current facts. No sign-up.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Coder AI"}],"tags":["demos-bots"]},{"id":"semif","url":"https://github.com/TheoLeeCJ/SemIf","title":"SemIf","content_text":"Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"TheoLeeCJ"}],"tags":["benchmarks-research","choice","score"]},{"id":"jevlike","url":"https://github.com/vinnylarouge/jevlike","title":"jevlike","content_text":"Train a small model that chooses among a changing list of text options.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"vinnylarouge"}],"tags":["benchmarks-research","choice","score"]},{"id":"jev-visual","url":"https://github.com/hr98w/jev-visual","title":"jev-visual","content_text":"An educational Jev-like visual inference experiment on Apple Silicon: shared context, direct candidate scoring, and local visual demos.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"hr98w"}],"tags":["benchmarks-research","choice","score"]},{"id":"decider","url":"https://github.com/Mapika/decider","title":"decider","content_text":"One-pass typed decisions with calibrated probabilities (System One style model), fine-tuned from Qwen3.5-2B","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"Mapika"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"jev-eval-agent","url":"https://github.com/vinilana/jev-eval-agent","title":"jev-eval-agent","content_text":"A personal-assistant agent built with (Vercel), with 100 mocked tools,","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"vinilana"}],"tags":["benchmarks-research","choice","noul"]},{"id":"reflex","url":"https://github.com/kshetrajna12/reflex","title":"reflex","content_text":"A small open decision model: state + typed questions -> calibrated probabilities. A Jev / System One re-creation on Qwen3.5.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"kshetrajna12"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"typesafe-ai-benchmark","url":"https://github.com/iammrduncan/typesafe-ai-benchmark","title":"typesafe-ai-benchmark","content_text":"This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"iammrduncan"}],"tags":["benchmarks-research","choice","noul"]},{"id":"open-jev-daseinlabs","url":"https://github.com/daseinlabs/open-jev","title":"open-jev (daseinlabs)","content_text":"Disclaimer: This project was inspired by . It is an independent reimplementation and is not affiliated with or endorsed by the original author.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"daseinlabs"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"jevmlx","url":"https://github.com/bnsd55/jevmlx","title":"jevmlx","content_text":"Jev-style parallel constrained decisions for any MLX model on Apple Silicon. Typed, schema-valid JSON in one forward pass.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"bnsd55"}],"tags":["benchmarks-research","choice","score"]},{"id":"mini-jev","url":"https://github.com/r-ms/mini-jev","title":"mini-jev","content_text":"mini-Jev: what a Jev-style typed-decision interface looks like on a frozen Qwen3-4B \u2014 read the option letter's logits instead of generating JSON. Preregistered experiment, results, teaching bench.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"r-ms"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"openjev","url":"https://github.com/razorback16/openjev","title":"openjev","content_text":"Open, Jev-compatible System One decision server on DiffusionGemma","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"razorback16"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"jev-on-a-laptop","url":"https://github.com/rorshopping/jev-on-a-laptop","title":"jev-on-a-laptop","content_text":"Unofficial study: Jev-style parallel typed decisions on stock 1.5B-8B models on an Apple Silicon laptop. Benchmarks, research notes, and a Hugging Face Space demo.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"rorshopping"}],"tags":["benchmarks-research","choice"]},{"id":"open-jev-joshuasp","url":"https://github.com/JoshuaSP/open-jev","title":"open-jev (JoshuaSP)","content_text":"Typed JSON inference with DiffusionGemma, with Every and Jev benchmark results","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"JoshuaSP"}],"tags":["benchmarks-research","score"]},{"id":"jevbetter","url":"https://github.com/olanotolu/jevbetter","title":"jevbetter","content_text":"A stronger one-pass scorer over a variable list of text options. Hashed n-gram encoder, rival-aware attention, gated head, temperature scaling \u2014 with a head-to-head benchmark vs the jevlike starter design.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"olanotolu"}],"tags":["benchmarks-research","score"]},{"id":"typear","url":"https://github.com/zmtomorrow/TypeAR","title":"TypeAR","content_text":"Type-Safe Decoding for Autoregressive LLMs","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"zmtomorrow"}],"tags":["benchmarks-research","choice","score"]},{"id":"jev-benchmarks","url":"https://github.com/AbdelStark/jev-benchmarks","title":"jev-benchmarks","content_text":"Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"AbdelStark"}],"tags":["benchmarks-research","choice","score"]},{"id":"jev-column-race","url":"https://github.com/goodrahstar/jev-column-race","title":"jev-column-race","content_text":"Jev vs Gemini 3.8 Flash: labelling 1,000 app reviews, 4.1\u00d7 faster and 7\u00d7 cheaper","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"goodrahstar"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"openvons","url":"https://github.com/genai-craft/openvons","title":"openvons","content_text":"openvons (open-Jev): \u6709\u9650\u9078\u629e\u80a2\u306b\u78ba\u7387\u3067\u7b54\u3048\u308b\u5224\u65ad\u5c64 \u2014 \u30c6\u30ad\u30b9\u30c8 / \u753b\u50cf / \u65e5\u672c\u8a9e\u97f3\u58f0\u30b3\u30de\u30f3\u30c9","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"genai-craft"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"jev-apps","url":"https://github.com/JackZeng/Jev_apps","title":"Jev_apps","content_text":"\u770b\u770b Jev \u80fd\u505a\u4ec0\u4e48\uff1a\u7528\u4e2d\u82f1\u6587\u8bb2\u6e05\u70ed\u95e8\u5e94\u7528\u3001\u5de5\u4f5c\u539f\u7406\u548c\u5404\u81ea\u4f18\u7f3a\u70b9\u3002Explore Jev apps with plain-language examples, explanations, and comparisons.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"JackZeng"}],"tags":["benchmarks-research"]},{"id":"jevfire","url":"https://github.com/kikoncuo/jevfire","title":"jevfire","content_text":"JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"kikoncuo"}],"tags":["benchmarks-research","choice","score"]},{"id":"legalforecastbench","url":"https://github.com/johnhughes3/LegalForecastBench","title":"LegalForecastBench","content_text":"LegalForecast-MTD benchmark alpha and official evaluation workflows","date_published":"2026-05-18T00:00:00Z","authors":[{"name":"johnhughes3"}],"tags":["benchmarks-research","score"]},{"id":"openjev-zhihz","url":"https://github.com/zhihz/openjev","title":"openjev (zhihz)","content_text":"Local bilingual probability decisions from context, questions, and candidate answers. Independent research preview inspired by TypeSafe Jev.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"zhihz"}],"tags":["benchmarks-research","choice","score"]},{"id":"jev-korean-benchmark","url":"https://github.com/mahlernim/jev-korean-benchmark","title":"jev-korean-benchmark","content_text":"Reproducible early-access evaluation of Jev on Korean understanding and medical text, with runtime and cost evidence","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"mahlernim"}],"tags":["benchmarks-research","choice","score"]},{"id":"jev-lm","url":"https://github.com/y0usaf/jev-lm","title":"jev-lm","content_text":"A word-level language model whose output layer is Jev: n-gram drafter, Noul chunk verification, bits-per-token eval","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"y0usaf"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"system-one-open","url":"https://github.com/mithalouni/system-one-open","title":"system-one-open","content_text":"Open replica of TypeSafe's Jev: typed calibrated decisions in one forward pass, on Gemma 4 E2B / Gemma 3 270M (Modal)","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"mithalouni"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"typesafe-local","url":"https://github.com/aabolfazl/typesafe-local","title":"typesafe-local","content_text":"Inspired by TypeSafe Ai, Ask a local LLM typed questions, get calibrated probabilities instead of text. Structured output without generation or parsing. MLX / Apple Silicon.","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"aabolfazl"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"daf-jev","url":"https://github.com/docxology/daf-jev","title":"daf-jev","content_text":"daf-jev: composable Python toolkit for TypeSafe's Jev (System One) decision API \u2014 question builders, confidence gates, evaluator, calibration, CLI, MCP server, agent skill","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"docxology"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"jev-behavior-study","url":"https://github.com/RINNECODER/jev-behavior-study","title":"jev-behavior-study","content_text":"Independent Jev 1.13.0 behavior study: report, controlled prompt experiments, raw results, and offline verification.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"RINNECODER"}],"tags":["benchmarks-research","choice","score"]},{"id":"jev-chat","url":"https://github.com/adhyaay-karnwal/jev-chat","title":"jev-chat","content_text":"A chatbot from typed Jev decisions: hierarchical speculative decoding over System One probabilities.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"adhyaay-karnwal"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"jev-search-rerank-eval","url":"https://github.com/zhuyansen/jev-search-rerank-eval","title":"jev-search-rerank-eval","content_text":"Does a TypeSafe Jev rerank beat embedding search? Graded relevance eval (9,831 pairs, 164 zh/en queries) over the Agent Skills Hub catalog, with the judge-circularity bias measured.","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"zhuyansen"}],"tags":["benchmarks-research","choice","score"]},{"id":"litjev","url":"https://github.com/zhengxuyu/litjev","title":"LitJev","content_text":"Turn any off-the-shelf LLM into a Jev -like decision layer","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"zhengxuyu"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"system-one","url":"https://github.com/sgoedecke/system-one","title":"system-one","content_text":"Batched single-token choice inference for open language models, compatible with TypeSafe","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"sgoedecke"}],"tags":["benchmarks-research","choice"]},{"id":"verdict-open-jev","url":"https://github.com/Heman10x-NGU/Verdict-open-jev","title":"Verdict-open-jev","content_text":"Non-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit, and in-browser WebGPU playground","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Heman10x-NGU"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"calibre","url":"https://github.com/FirasSX914/Janus","title":"calibre","content_text":"Measure when to use Jev and other models on your data, then route accordingly.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"FirasSX914"}],"tags":["benchmarks-research"]},{"id":"jev-stock","url":"https://github.com/sosopop/jev_stock","title":"jev_stock","content_text":"An experimental JEV-powered framework for forecasting short-term stock price direction from structured market data.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"sosopop"}],"tags":["benchmarks-research","choice","score"]},{"id":"jev-benchmark","url":"https://github.com/wondertwins/jev-benchmark","title":"jev-benchmark","content_text":"Benchmarks and a playground for TypeSafe's Jev (System One) model: chess, and who-is-the-player-talking-to for speech-to-text game NPCs","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"wondertwins"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"jev-for-engineers","url":"https://github.com/Foadsf/jev-for-engineers","title":"jev-for-engineers","content_text":"Eight minimal working examples of TypeSafe's Jev (a System One model) applied to mechanical and electrical engineering: CAD/CAE/CAM routing, FEM result triage, DFM screening, BOM alignment, hallucination-proof extraction","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"Foadsf"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"jev-gate","url":"https://github.com/MongLong0214/jev-gate","title":"jev-gate","content_text":"Not every coding task needs your best model. Experimental Jev-powered model routing for Claude Code \u2014 V3 prototype runs today, V4 routes at the task boundary.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"MongLong0214"}],"tags":["benchmarks-research","choice","score"]},{"id":"jev-harness","url":"https://github.com/AntonioCoppe/jev-harness","title":"jev-harness","content_text":"Decision harness for TypeSafe Jev \u2014 confidence gates, shadow mode, recipes, and evals. Claude CLI 48.9s \u2192 Jev 1.3s on the same row-filter job.","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"AntonioCoppe"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"jevcal","url":"https://github.com/abhixhek/jevcal","title":"jevcal","content_text":"Stop guessing confidence thresholds: calibrate, threshold, and drift-check typed decision models (TypeSafe Jev) against an LLM teacher.","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"abhixhek"}],"tags":["benchmarks-research","choice","noul"]},{"id":"jevgpt","url":"https://github.com/Bewinxed/jevgpt","title":"jevgpt","content_text":"A chatbot built on a model that cannot generate text (TypeSafe AI's Jev, driven autoregressively)","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Bewinxed"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"open-alternative-jev","url":"https://github.com/ikermoel/open-alternative-jev","title":"open-alternative-jev","content_text":"Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with honest benchmarks","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"ikermoel"}],"tags":["benchmarks-research","choice"]},{"id":"trade-jev","url":"https://github.com/justinhe16/trade-jev","title":"trade-jev","content_text":"Backtest Jev (TypeSafe) as a BUY/SELL/HOLD trader on NQ L10 order-book data","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"justinhe16"}],"tags":["benchmarks-research"]},{"id":"decisionbridge","url":"https://github.com/grishahq/decisionbridge","title":"decisionbridge","content_text":"A Jev-inspired decision interface for existing LLMs. Explicit choices, scores, calibration, and review thresholds.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"grishahq"}],"tags":["benchmarks-research","choice","score"]},{"id":"jev-agent-failure-benchmark","url":"https://github.com/TokenTrim/jev-agent-failure-benchmark","title":"jev-agent-failure-benchmark","content_text":"Benchmarking Jev (Typesafe.ai) against a strong LLM on the Who&When Pro agent-failure-attribution benchmark (text subset).","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TokenTrim"}],"tags":["benchmarks-research","choice"]},{"id":"jev-curate","url":"https://github.com/AkashPriyadarshii/jev-curate","title":"jev-curate","content_text":"High-throughput synthetic & pretraining dataset sifter powered by TypeSafe AI Jev (api.typesafe.ai). Stream, filter, and score Parquet & JSONL datasets at 1,500+ rows/sec using System One typed decisions (Choice, Score, ","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"AkashPriyadarshii"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"jev-exploration","url":"https://github.com/SamuelSacco/jev-exploration","title":"jev-exploration","content_text":"Jev (TypeSafe) exploratory thread: claim audit, live demos, and runnable code","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"SamuelSacco"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"jev-freeform","url":"https://github.com/kesku/jev-freeform","title":"jev-freeform","content_text":"An observable raw-character chat experiment powered entirely by TypeSafe Jev Choice","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"kesku"}],"tags":["benchmarks-research","choice"]},{"id":"jev-little-airways","url":"https://github.com/lbotinelly/jev-little-airways","title":"jev-little-airways","content_text":"A show-and-tell capability study for Jev, TypeSafe's System One decision model.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"lbotinelly"}],"tags":["benchmarks-research"]},{"id":"jev-rerank-bench","url":"https://github.com/anessbelbati/jev-rerank-bench","title":"jev-rerank-bench","content_text":"Can a decision model beat dedicated rerankers? TypeSafe Jev vs Cohere Rerank 4 vs ZeroEntropy zerank-2 vs a chat-model baseline: 14 datasets, every raw API response, bootstrap ranges on every gap.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"anessbelbati"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"jev-research-eval","url":"https://github.com/jgridifier/jev-research-eval","title":"jev-research-eval","content_text":"Reproducible Jev Ultrafast research-browser eval harness + field note (QC\u2019d cases, suite runner, report generator). Not investment advice.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"jgridifier"}],"tags":["benchmarks-research"]},{"id":"jev-sec-bench","url":"https://github.com/Gaurav-Gosain/jev-sec-bench","title":"jev-sec-bench","content_text":"Blind security benchmarks for Jev, TypeSafe's System One model: prompt injection and vulnerable code detection, built on jev-go","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"Gaurav-Gosain"}],"tags":["benchmarks-research","score"]},{"id":"jev-synergy-screening","url":"https://github.com/PistachioAIHQ/jev-synergy-screening","title":"jev-synergy-screening","content_text":"Jev (TypeSafe System One) \u00d7 ASReview SYNERGY abstract screening demo \u2014 Choice/Noul vs gold labels","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"PistachioAIHQ"}],"tags":["benchmarks-research","choice","noul"]},{"id":"jevify","url":"https://github.com/altryne/jevify","title":"jevify","content_text":"An agent skill to discover TypeSafe Jev opportunities, design typed questions, and learn from recent community experiments.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"altryne"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"kyotsu-ai-bench","url":"https://github.com/shibadogcap/kyotsu-ai-bench","title":"kyotsu-ai-bench","content_text":"AI benchmark on Japan's 2026 Common Test: Jev vs luna-none vs luna-low (static dashboard)","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"shibadogcap"}],"tags":["benchmarks-research"]},{"id":"mcts-agent","url":"https://github.com/lhemerly/mcts-agent","title":"mcts-agent","content_text":"Discriminative Monte Carlo Tree Search using TypeSafe Jev System One Primitives and Gemini","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"lhemerly"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"padflow-jev-evals","url":"https://github.com/zsavage8/padflow-jev-evals","title":"padflow-jev-evals","content_text":"Typed-decision benchmark from PadFlow (land development SaaS): schemas, anonymized labeled rows, and a runner for confidence-calibrated models like TypeSafe Jev.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"zsavage8"}],"tags":["benchmarks-research","score"]},{"id":"qwen-rlcd","url":"https://github.com/shamazharikh/qwen-rlcd","title":"qwen-rlcd","content_text":"Jev-style calibrated decision model (Choice/Score/Noul) on Qwen3.5-0.8B","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"shamazharikh"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"risc-jev","url":"https://github.com/i2cjak/RISC-jeV","title":"RISC-jeV","content_text":"Jev wired up as a RISC-V CPU \u2014 an extreme experiment in how far state-in/decision-out can go.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"i2cjak"}],"tags":["benchmarks-research"]},{"id":"financialpredictionjev","url":"https://github.com/thodoh1/FinancialPredictionJev","title":"FinancialPredictionJev","content_text":"Using Jev to test how well it predicts financial markets(just like most llms as of september 2026, it doesnt do that good)","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"thodoh1"}],"tags":["benchmarks-research"]},{"id":"jev-alpha-bench","url":"https://github.com/Gaurav-Gosain/jev-alpha-bench","title":"jev-alpha-bench","content_text":"Does Jev predict stock returns from news? It reads the news well; there is no tradeable alpha. Three arms separate reading from recall.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"Gaurav-Gosain"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"jev-anotacao-sentencas","url":"https://github.com/lab-dados/jev-anotacao-sentencas","title":"jev-anotacao-sentencas","content_text":"Jev (TypeSafe) vs. Gemini 3.8 Flash vs. GPT-5.6 Luna na anota\u00e7\u00e3o estruturada de senten\u00e7as do TJSP: qualidade, tempo e custo","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"lab-dados"}],"tags":["benchmarks-research"]},{"id":"jev-as-a-judge","url":"https://github.com/danielgshea/jev-as-a-judge","title":"jev-as-a-judge","content_text":"Using Jev as an evaluator.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"danielgshea"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"jev-deferred-crispification","url":"https://github.com/dnakhoa/jev-deferred-crispification","title":"jev-deferred-crispification","content_text":"Position paper: the Hidden-Markov and fuzzy primitives missing from TypeSafe AI's Jev and System-One decision models. Two lemmas, one principle (Deferred Crispification), one architecture (BSF-S1).","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"dnakhoa"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"jev-finance-benchmark","url":"https://github.com/hifizz/jev-finance-benchmark","title":"jev-finance-benchmark","content_text":"typesafe.ai model jev finance benchmark","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"hifizz"}],"tags":["benchmarks-research"]},{"id":"jev-headline-bench","url":"https://github.com/Gaurav-Gosain/jev-headline-bench","title":"jev-headline-bench","content_text":"Can Jev pick the winner of a real headline A/B test? 64.5% across 10,984 Upworthy randomized experiments, 74.7% when the difference was decisive.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"Gaurav-Gosain"}],"tags":["benchmarks-research","score"]},{"id":"jev-jp-address","url":"https://github.com/smasato/jev-jp-address","title":"jev-jp-address","content_text":"Jev (TypeSafe) \u6027\u80fd\u8a55\u4fa1\u30d7\u30ed\u30b8\u30a7\u30af\u30c8 \u2014 \u65e5\u672c\u90f5\u4fbf KEN_ALL \u3092\u30de\u30b9\u30bf\u306b\u3001AI SDK \u7d4c\u7531\u306e Jev \u304c\u4f4f\u6240\u306e\u3042\u3044\u307e\u3044\u4e00\u81f4\u306b\u3069\u3053\u307e\u3067\u4f7f\u3048\u308b\u304b\u3092\u691c\u8a3c","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"smasato"}],"tags":["benchmarks-research","choice"]},{"id":"jev-lab","url":"https://github.com/Menny1337/jev-lab","title":"jev-lab","content_text":"TypeScript experiments, evaluations, and latency benchmarks for TypeSafe's Jev model","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"Menny1337"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"jev-phishing-bench","url":"https://github.com/anisselbd/jev-phishing-bench","title":"jev-phishing-bench","content_text":"Jev (TypeSafe) vs Claude Haiku 4.5 on 2 000 phishing emails: accuracy, calibration, latency, cost. Reproducible benchmark.","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"anisselbd"}],"tags":["benchmarks-research","choice","noul"]},{"id":"jev-pick-and-place-study","url":"https://github.com/tryaksh/jev-pick-and-place-study","title":"jev-pick-and-place-study","content_text":"A small reproducible MuJoCo pilot comparing Jev, Claude Haiku, and reactive rules for pick-and-place.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"tryaksh"}],"tags":["benchmarks-research"]},{"id":"jev-playground-hegargarcia","url":"https://github.com/hegargarcia/jev-playground","title":"jev-playground (hegargarcia)","content_text":"A playground for benchmarking TypeSafe AI\u2019s Jev against other evaluation models in games with explicit states, legal actions, and measurable outcomes.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"hegargarcia"}],"tags":["benchmarks-research","choice","score"]},{"id":"jev-report","url":"https://github.com/HackSing/jev-report","title":"jev-report","content_text":"\u53d1\u660e RLHF \u7684\u4eba\uff0c\u8fd9\u6b21\u505a\u4e86\u4e2a\u4e0d\u4f1a\u8bf4\u8bdd\u7684\u6a21\u578b\uff1aJev \u72ec\u7acb\u7814\u7a76\u62a5\u544a\u300252 \u9875 PDF + 50 \u6761\u4e2d\u6587\u5b9e\u6d4b\u590d\u73b0\u5305 + 143 \u6761\u53ef\u56de\u6eaf\u6570\u636e\u8868","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"HackSing"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"jev-routing-experiment","url":"https://github.com/TokenTrim/jev-routing-experiment","title":"jev-routing-experiment","content_text":"Benchmarking TypeSafe's Jev decision model as a cost-efficient LLM router on RouterArena","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"TokenTrim"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"jev-secret-detection","url":"https://github.com/teyhouse/jev-secret-detection","title":"jev-secret-detection","content_text":"Measures how well TypeSafe's RLCD-Jev model spots real secret credentials in file snippets","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"teyhouse"}],"tags":["benchmarks-research","score","noul"]},{"id":"jev-shadcn-lint-eval","url":"https://github.com/blas0/jev-shadcn-lint-eval","title":"jev-shadcn-lint-eval","content_text":"A small second eval for shadcn-ui/lint that uses TypeSafe's Jev to judge the linter's own output.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"blas0"}],"tags":["benchmarks-research","score"]},{"id":"jev-spam-eval","url":"https://github.com/bitnovus/jev-spam-eval","title":"jev-spam-eval","content_text":"Zero-shot spam filtering with TypeSafe Jev Noul questions, compared with TF-IDF baselines","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"bitnovus"}],"tags":["benchmarks-research","choice","noul"]},{"id":"jev-trace-classifier","url":"https://github.com/sypherin/jev-trace-classifier","title":"jev-trace-classifier","content_text":"Application of TypeSafe Jev (noul judgment primitive) on the collusion.wiki corpus: agent vs human page authorship, head-to-head vs local Qwen3.8-Flash-Next","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"sypherin"}],"tags":["benchmarks-research","score","noul"]},{"id":"misereru-slide-jev","url":"https://github.com/myokoym/misereru-slide-jev","title":"misereru-slide-jev","content_text":"TypeSafe AI \u306e Jev / System One Models \u3092\u7d99\u7d9a\u7684\u306b\u8abf\u67fb\u3057\u3001Markdown\u30b9\u30e9\u30a4\u30c9\u3068\u3057\u3066\u6574\u7406\u3059\u308brepository\u3067\u3059\u3002","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"myokoym"}],"tags":["benchmarks-research"]},{"id":"openjev-experiments","url":"https://github.com/zefir1990/openjev-experiments","title":"openjev-experiments","content_text":"Openjev experiments","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"zefir1990"}],"tags":["benchmarks-research","choice"]},{"id":"parallel-constrained-decoding-qwen2-5-1b-rlcd","url":"https://huggingface.co/spaces/drinkmoonshine/parallel-constrained-decoding","title":"Parallel Constrained Decoding (Qwen2.5-1B-RLCD)","content_text":"Enter a text document and a JSON schema that describes the information you want to extract. The app runs a fast parallel constrained decoding method and a standard generation method, showing the ge...","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"drinkmoonshine"}],"tags":["benchmarks-research"]},{"id":"pocketjev","url":"https://github.com/NullPo-jp/PocketJev","title":"PocketJev","content_text":"On-device iPhone visual decision tool using MLX and Qwen3-VL direct option logits.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"NullPo-jp"}],"tags":["benchmarks-research","choice","score"]},{"id":"shade-arena-jev-monitor","url":"https://github.com/nican2018/shade-arena-jev-monitor","title":"shade-arena-jev-monitor","content_text":"Evaluating TypeSafe's Jev as a fast monitor and action gate for agent sabotage in SHADE-Arena, compared with Gemini 2.5 Flash/Pro.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"nican2018"}],"tags":["benchmarks-research","score"]},{"id":"system-one-adapter-rust","url":"https://github.com/codeitlikemiley/system-one-adapter-rust","title":"system-one-adapter-rust","content_text":"Rust port of TypeSafe system-one-adapter (LLM-backed system_one evaluations)","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"codeitlikemiley"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"system-one-gemma","url":"https://github.com/akash-kamat/system-one-gemma","title":"system-one-gemma","content_text":"Open-source Jev-style System One decision model. Gemma 3 270M with a scoring head \u2014 fast, calibrated decisions in a single forward pass. No text generation. Inspired by TypeSafe.ai's Jev.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"akash-kamat"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"thaiexam-jev-charts","url":"https://github.com/vehas/thaiexam-jev-charts","title":"thaiexam-jev-charts","content_text":"Charts: TypeSafe Jev evaluated on Thai standardized exams vs 110 other models","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"vehas"}],"tags":["benchmarks-research","score"]},{"id":"typesafe-chess-eval","url":"https://github.com/AliceRoselia/Typesafe_chess_eval","title":"Typesafe_chess_eval","content_text":"An evaluation of typesafe AI chess. As it turns out, the AI isn't doing really well even though chess is not a particularly open-ended game. Still, it's only a prototype and this probably wasn't optimzied for games.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"AliceRoselia"}],"tags":["benchmarks-research"]},{"id":"typesafe-oracles","url":"https://github.com/trophee-bot/typesafe-oracles","title":"typesafe-oracles","content_text":"Evaluating TypeSafe's System One primitives (Choice/Score/Noul) \u2014 where a typed oracle beats an LLM call","date_published":"2026-09-16T00:00:00Z","authors":[{"name":"trophee-bot"}],"tags":["benchmarks-research","choice","score","noul"]},{"id":"awesome-typesafe","url":"https://github.com/AbdelStark/awesome-typesafe","title":"awesome-typesafe","content_text":"A curated list of official resources and community projects for TypeSafe, System One models, and Jev.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"AbdelStark"}],"tags":["community-lists","choice","score","noul"]},{"id":"awesome-jev-yibie","url":"https://github.com/yibie/awesome-jev","title":"awesome-jev (yibie)","content_text":"A curated list of public projects, integrations, and discussions built on Jev \u2014 TypeSafe AI's System One model for typed decisions.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"yibie"}],"tags":["community-lists","choice","score","noul"]},{"id":"awesome-jev","url":"https://github.com/cobanov/awesome-jev","title":"awesome-jev","content_text":"A curated, source-backed list of projects built with Jev, TypeSafe AI's System One model for typed decisions.","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"cobanov"}],"tags":["community-lists","choice","score","noul"]},{"id":"awesome-jev-anotiawang","url":"https://github.com/AnotiaWang/awesome-jev","title":"awesome-jev (AnotiaWang)","content_text":"A curated list of awesome Jev / TypeSafe System One applications, libraries, and resources.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"AnotiaWang"}],"tags":["community-lists","choice","score","noul"]},{"id":"awesome-jev-fatwang2","url":"https://github.com/fatwang2/awesome-jev","title":"awesome-jev (fatwang2)","content_text":"A source-backed Jev project directory with a reusable Jev-only GitHub review workflow.","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"fatwang2"}],"tags":["community-lists","choice","score","noul"]},{"id":"awesome-jev-projects","url":"https://github.com/logicrw/awesome-jev-projects","title":"awesome-jev-projects","content_text":"Awesome Jev: source-backed open-source ecosystem radar, plain-language project discovery, and automatic GitHub sync","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"logicrw"}],"tags":["community-lists"]},{"id":"awesome-jev-omnijev","url":"https://github.com/OmniJev/awesome-jev","title":"awesome-jev (OmniJev)","content_text":"Papers, open reproductions and independent evaluations behind System One models and Jev.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"OmniJev"}],"tags":["community-lists","choice","score","noul"]},{"id":"ai-that-does-not-talk","url":"https://ziplyne.agency/blog/ai-that-doesnt-talk-typesafe-jev-guide","title":"AI that does not talk","content_text":"TypeSafe's Jev is an AI model that returns typed values instead of prose \u2014 with a confidence score that tells you when it doesn't know. What it does, where it fits, and how to start.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"ZipLyn"}],"tags":["articles-threads"]},{"id":"aiavatarkit-turn-end-gate","url":"https://x.com/uezochan/status/2100608556823388486","title":"AIAvatarKit turn-end gate","content_text":"Jev\u3067\u97f3\u58f0\u5bfe\u8a71\u306e\u30bf\u30fc\u30f3\u30a8\u30f3\u30c9\u5224\u5b9a\u3084\u3063\u3066\u307f\u305f\u3002\u767a\u8a71\u7d42\u4e86\u5f8c0.5\u79d2\u5f8c\u306bJev\u3067\u30bf\u30fc\u30f3\u30a8\u30f3\u30c9\u3057\u305f\u304b\u3069\u3046\u304b\u3092\u5224\u5b9a\u3057\u3066\u3001\u30b9\u30b3\u30a2\u306b\u5fdc\u3058\u3066\u8ffd\u52a0\u30db\u30fc\u30eb\u30c9\u3002","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"\u3046\u3048\u305e\u3046@\u3046\u306a\u6280\u7814\u4ee3\u8868 (@uezochan)"}],"tags":["applications"]},{"id":"ainews-jev-a-system-one-model-that-only-decides","url":"https://www.latent.space/p/ainews-jev-a-system-one-model-that","title":"AINews: Jev, a System One Model that only decides","content_text":"congrats to TypeSafe!","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Latent.Space"}],"tags":["articles-threads"]},{"id":"browser-use-jev","url":"https://x.com/gregpr07/status/2100411066966749359","title":"Browser Use + Jev","content_text":"Breaking: Browser Use + Jev = Ultrafast \u26a1","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Gregor Zunic (@gregpr07)"}],"tags":["articles-threads"]},{"id":"computer-use-built-on-jev","url":"https://x.com/awlevin/status/2100262612428894676","title":"Computer use built on Jev","content_text":"aaron's computer-use agent built on Jev \u2014 maker-reported ~155x cheaper than Opus 5 and ~20x faster than a frontier-LLM driver.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"aaron (@awlevin)"}],"tags":["browser-computer-use"]},{"id":"consolechaosracing-driven-by-jev","url":"https://x.com/Maoku/status/2100611986358927627","title":"ConsoleChaosRacing driven by Jev","content_text":"Typesafe system_one \u2026 Jev \u3061\u3083\u3093","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Maoku (@Maoku)"}],"tags":["demos-bots"]},{"id":"duckdb-jev-classifier","url":"https://x.com/hamiltonulmer/status/2100370557405667768","title":"DuckDB Jev classifier","content_text":"Hamilton Ulmer's DuckDB extension that runs Jev classification as a SQL function \u2014 rows in, typed labels out, inside the query engine.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Hamilton Ulmer (@hamiltonulmer)"}],"tags":["applications"]},{"id":"early-jev-tools-roundup","url":"https://x.com/0xLogicrw/status/2100478725393686556","title":"Early Jev tools roundup","content_text":"Jev \u8fd9\u4e2a waitlist \u8fd8\u662f\u5f88\u7ed9\u529b\u7684\uff0c\u6628\u5929\u7533\u8bf7\uff0c\u4eca\u5929\u5c31\u80fd\u7528\u4e0a\u3002","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"\u601d\u7ef4\u602a\u602a (@0xLogicrw)"}],"tags":["community-lists"]},{"id":"ground-truth-news-framing-extension","url":"https://x.com/jagenaujagenau/status/2100622352333574460","title":"Ground Truth news-framing extension","content_text":"A small browser extension that scores the news article you're reading for framing and loaded language, using Jev to judge the text.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"D (@jagenaujagenau)"}],"tags":["browser-computer-use"]},{"id":"hacker-news-launch-thread","url":"https://news.ycombinator.com/item?id=49717558","title":"Hacker News launch thread","content_text":"Introducing System One Models and Jev | Hacker News","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Hacker News"}],"tags":["articles-threads"]},{"id":"he-says-he-co-invented-chatgpt-his-new-ai-will-not-write-a-w","url":"https://dev.to/gabrielanhaia/he-says-he-co-invented-chatgpt-his-new-ai-jev-wont-write-a-word-e3c","title":"He says he co-invented ChatGPT. His new AI will not write a word","content_text":"Jev answers with typed decisions and probabilities, never text. The TypeScript API, and the catch hiding inside 'zero hallucinations'. Tagged with ai, llm, typescript, machinelearning.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Gabriel Anhaia"}],"tags":["articles-threads"]},{"id":"hide-posts-on-x-with-natural-language","url":"https://x.com/marcelpociot/status/2100520134481735729","title":"Hide posts on X with natural language","content_text":"Marcel Pociot's browser extension that hides or collapses X posts matching a natural-language rule, with Jev deciding post by post.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Marcel Pociot \ud83e\uddea (@marcelpociot)"}],"tags":["browser-computer-use"]},{"id":"hook-panel-a-b-tester","url":"https://x.com/Vybhav/status/2100609472750047263","title":"Hook panel A/B tester","content_text":"Near-real-time A/B testing of TikTok/Instagram hook panels against ~100 rich personas \u2014 Jev plays each persona and rates the hook.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Vybhav Ramachandran (@Vybhav)"}],"tags":["applications"]},{"id":"internal-classifier-field-note","url":"https://x.com/identityTorn/status/2100475121324728615","title":"Internal classifier field note","content_text":"Field notes from pointing Jev at an internal benchmark classifier: what worked, what didn't, and what the confidence scores said.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"iden (@identityTorn)"}],"tags":["articles-threads"]},{"id":"jev-as-an-agent-safety-monitor","url":"https://x.com/isNickMa/status/2100566407524344225","title":"Jev as an agent safety monitor","content_text":"An experiment using Jev as a safety monitor over an AI agent's proposed actions \u2014 flagging risky steps by probability.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"\ud83d\ude0eNick \u5e38\u80dc (@isNickMa)"}],"tags":["benchmarks-research"]},{"id":"jev-gomoku-harness","url":"https://x.com/VacekvVita/status/2100609341145465325","title":"Jev gomoku harness","content_text":"V\u00ed\u0165a Vacek's gomoku harness: local tactics shrink 225 moves to ~40 candidates, then Jev picks the move.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"V\u00ed\u0165a \ud835\udd4f-Vacek (@VacekvVita)"}],"tags":["demos-bots"]},{"id":"jev-in-34-seconds","url":"https://x.com/dwhitedesign/status/2100368024649769384","title":"Jev in 34 seconds","content_text":"Daniel White's 34-second explainer of what Jev is and how the typed-question API works.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Daniel White (@dwhitedesign)"}],"tags":["articles-threads"]},{"id":"jev-in-a-grammarly-style-mac-app","url":"https://x.com/nielsmouthaan/status/2100543809465577665","title":"Jev in a Grammarly-style Mac app","content_text":"Built a Grammarly-like Mac app with Jev.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Niels Mouthaan (@nielsmouthaan)"}],"tags":["applications"]},{"id":"jev-typewriter-launch","url":"https://x.com/stevekrouse/status/2100287368221659289","title":"Jev Typewriter launch","content_text":"typesafe's jev is fun! live demo you can play with: https://t.co/ctnPF0w70r\" / X","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Steve Krouse (@stevekrouse)"}],"tags":["articles-threads"]},{"id":"jev-vs-qwen-on-cerebras","url":"https://x.com/iamMrDuncan/status/2100467548298899918","title":"Jev vs Qwen on Cerebras","content_text":"Built an alternative version of @typesafeai but on @cerebras with Qwen 3.8 27b.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Shannon \ud83e\udd16\u2620\ufe0f (@iamMrDuncan)"}],"tags":["benchmarks-research"]},{"id":"jev-zenn-dev","url":"https://zenn.dev/mizchi/articles/jev-plays-gomoku","title":"jev \u540c\u58eb\u306b\u4e94\u76ee\u4e26\u3079\u3067\u5bfe\u6226\u3055\u305b\u305f","content_text":"jev \u540c\u58eb\u306b\u4e94\u76ee\u4e26\u3079\u3067\u5bfe\u6226\u3055\u305b\u305f","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"mizchi"}],"tags":["articles-threads"]},{"id":"jev-rabbit-pr-review-bot","url":"https://x.com/thekitze/status/2100616530275029139","title":"jev-rabbit PR review bot","content_text":"kitze's PR review bot that uses Jev to make review judgments over pull requests.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"kitze \ud83d\udee0\ufe0f tinkerer.club (@thekitze)"}],"tags":["agent-tooling"]},{"id":"jev-system-one-models-explained","url":"https://www.theneuron.ai/explainer-articles/typesafe-jev-system-one-models-explained/","title":"Jev: System One models explained","content_text":"TypeSafe\u2019s JEV returns structured decisions with confidence scores instead of chatbot replies. Here\u2019s how it works and where it could fit in AI workflows.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"The Neuron"}],"tags":["articles-threads"]},{"id":"jev-the-language-model-that-will-not-talk","url":"https://anthonymaio.substack.com/p/jev-the-language-model-that-wont","title":"Jev: The Language Model That Will Not Talk","content_text":"The interesting claim in Jev isn\u2019t the price, although that promises to be a game-changer.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Anthony Maio"}],"tags":["articles-threads"]},{"id":"kalshi-prediction-market-bot","url":"https://x.com/stablebun/status/2100614911898390589","title":"Kalshi prediction-market bot","content_text":"A small bot that asks Jev for a decision on Kalshi 15-minute and 1-hour BTC, ETH, and SOL markets.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Bunchhieng Soth (@stablebun)"}],"tags":["applications"]},{"id":"launch-thread-by-diogo-almeida","url":"https://x.com/CompleteSkeptic/status/2099925682726002904","title":"Launch thread by Diogo Almeida","content_text":"After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Diogo Almeida (@CompleteSkeptic)"}],"tags":["articles-threads"]},{"id":"mini-vibe-check-jev-judged-everything-i-have-written-in-0-7-","url":"https://every.to/also-true-for-humans/mini-vibe-check-typesafe-s-jev-judged-everything-i-ve-written-in-0-7-seconds","title":"Mini-Vibe Check: Jev judged everything I have written in 0.7 seconds","content_text":"Its new model turns fuzzy questions into probabilities fast and cheaply enough to check an AI agent\u2019s work as it goes","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Mike Taylor (Every)"}],"tags":["articles-threads"]},{"id":"model-router-built-with-jev","url":"https://x.com/ephraimduncan/status/2100454070536351824","title":"Model router built with Jev","content_text":"Built a model router with Jev by @typesafeai.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Duncan (@ephraimduncan)"}],"tags":["agent-tooling"]},{"id":"model-router-cli","url":"https://x.com/nidhisinghattri/status/2100617830890885415","title":"Model router CLI","content_text":"Nidhi Singh's CLI model router \u2014 Jev decides which model handles each prompt.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Nidhi Singh (@nidhisinghattri)"}],"tags":["agent-tooling"]},{"id":"one-judge-call-vs-twelve-dimension-scores","url":"https://agentjournal.dev/blog/llm-judge-vs-feature-extraction/","title":"One judge call vs twelve dimension scores","content_text":"Jev as a feature extractor vs a single judge call, measured on three classification tasks: 34.1M input tokens, $1.43, 25\u00d7 the false positives. When decomposition actually pays.","date_published":"2026-09-18T00:00:00Z","authors":[{"name":"Agent Journal"}],"tags":["articles-threads"]},{"id":"opencode-browser-use-powered-by-jev","url":"https://x.com/thdxr/status/2100288951978164647","title":"OpenCode browser use powered by Jev","content_text":"preview of how fast browser use can be","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"dax (@thdxr)"}],"tags":["browser-computer-use"]},{"id":"skillbox-jev-skill-routing","url":"https://x.com/thekitze/status/2100556122570792999","title":"skillbox + Jev skill routing","content_text":"kitze wired Jev into skillbox so Jev picks the right skill instead of the agent burning turns searching.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"kitze \ud83d\udee0\ufe0f tinkerer.club (@thekitze)"}],"tags":["agent-tooling"]},{"id":"spanish-aepd-corpus-test","url":"https://x.com/juanmacias/status/2100463494629925048","title":"Spanish AEPD corpus test","content_text":"He probado @typesafeai y la verdad es que merece la pena much\u00edsimo. Tiene unos casos de usos muy espec\u00edficos que me han venido super bien.\" / X","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"juanmacias \ud83c\udff3\ufe0f\u200d\ud83c\udf08 (@juanmacias)"}],"tags":["benchmarks-research"]},{"id":"stagehand-jev-browser-use","url":"https://x.com/kylejeong/status/2100622054945095934","title":"Stagehand + Jev browser use","content_text":"Browser/computer use combining Jev decisions with Stagehand \u2014 built for speed.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Kyle Jeong (@kylejeong)"}],"tags":["browser-computer-use"]},{"id":"starcraft-brood-war-wasm-mcp-demo","url":"https://x.com/literallydenis/status/2100622868878868603","title":"StarCraft Brood War WASM MCP demo","content_text":"Jev is impressive, but it still can\u2019t withstand a StarCraft BW Zerg rush","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Denis Shiryaev \ud83d\udc99\ud83d\udc9b (@literallydenis)"}],"tags":["demos-bots"]},{"id":"support-ticket-classifier","url":"https://x.com/ifahimreza/status/2100616988746023102","title":"Support ticket classifier","content_text":"Fahim Reza's tiny support-ticket classifier, ported from a GPT baseline to JEV with promising results.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Fahim Reza (@ifahimreza)"}],"tags":["applications"]},{"id":"tabletop-mmorpg-action-mapper","url":"https://x.com/Jon_iy/status/2100397782322364792","title":"Tabletop MMORPG action mapper","content_text":"Maps natural-language tabletop/MMORPG player actions to game moves using Jev decisions.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"hot shit bangers (@Jon_iy)"}],"tags":["demos-bots"]},{"id":"typed-decisions-not-chat","url":"https://warmersun.com/jev/","title":"Typed decisions, not chat","content_text":"Jev by TypeSafe AI \u2014 a tech primer on typed decisions, speed claims, and an inspectable audit trail. Research appendix attached.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Warmer Sun"}],"tags":["articles-threads"]},{"id":"typesafe-ai-debuts-model-for-machines-that-plays-doom","url":"https://www.theregister.com/ai-and-ml/2026/09/16/typesafe-ai-debuts-model-for-machines-that-plays-doom/5296711","title":"TypeSafe AI debuts model for machines that plays Doom","content_text":"'Jev' doesn't chat. It produces typed probabilistic decisions","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"The Register"}],"tags":["articles-threads"]},{"id":"typesafe-jev-the-first-decision-only-model-class","url":"https://www.developersdigest.tech/blog/typesafe-jev-system-one-models-release-guide-2026","title":"TypeSafe Jev: the first decision-only model class","content_text":"TypeSafe's Jev is the first 'System One' model: no text generation, typed decisions with calibrated probabilities, 70-500ms responses, and $0.042 per million...","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Developers Digest"}],"tags":["articles-threads"]},{"id":"typesafe-jev-zenn-dev","url":"https://zenn.dev/nwn/articles/824026c76116e0","title":"TypeSafe\u306eJev\u3092\u6b63\u3057\u304f\u9a5a\u304f","content_text":"TypeSafe\u306eJev\u3092\u6b63\u3057\u304f\u9a5a\u304f\u3001\u305d\u308c\u3063\u3066LLM\u3067\u3067\u304d\u307e\u305b\u3093\u304b\uff1f","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"nwn"}],"tags":["articles-threads"]},{"id":"vercel-fx-jev-as-a-command-safety-reviewer","url":"https://x.com/rauchg/status/2100307962262872105","title":"Vercel fx: Jev as a command safety reviewer","content_text":"We're seeing extraordinary results from @typesafeai. Default mode in \ud835\ude8f\ud835\udea1 is auto, with a safety reviewer analyzing every command.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Guillermo Rauch (@rauchg)"}],"tags":["agent-tooling"]},{"id":"vizdoom-jev-agent","url":"https://x.com/kmad/status/2100339921714323624","title":"ViZDoom Jev agent","content_text":"Kevin Madura's ViZDoom agent \u2014 Jev plays Doom from game state, the community's hello-world.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Kevin Madura (@kmad)"}],"tags":["demos-bots"]},{"id":"what-is-jev","url":"https://mohammedshehu.com/jev-typesafe-ai/","title":"What is Jev?","content_text":"Learn how TypeSafe AI's Jev model works, how to use it in Python, and how its structured AI decisions could support real-world use cases.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Mohammed Shehu"}],"tags":["articles-threads"]},{"id":"wiki-link-clicker-demo","url":"https://x.com/mark1nhu/status/2100620075090792490","title":"Wiki-link clicker demo","content_text":"@drefrajo @Neriousy @typesafeai @opencode Yes. Each page has some link candidates and then Jev chooses which link to click based on the stated goal.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"Marcos Filho (@mark1nhu)"}],"tags":["demos-bots"]},{"id":"jev-poker-eval","url":"https://backnotprop.com/blog/jev-poker/","title":"Jev is the fish at the poker table","content_text":"An independent eval: Jev plays solved flop spots against TexasSolver \u2014 matches the solver's top action 63% of the time, and shoves 4x pot with the nuts because the state never says 'you're ahead'.","date_published":"2026-09-17T00:00:00Z","authors":[{"name":"backnotprop"}],"tags":["benchmarks-research","choice","noul"]}]}