Read & learn
Written guides.
Understand Jev, one idea at a time. Walkthroughs, recipes, and writeups — our notes first, the original next.
Explore the Jev ecosystem.
Learn, build, and play with Jev — from deep technical guides to creative experiments.
Watch & learn
Video guides.
See an idea take shape. Tutorials, demos, and deep dives, organized by topic and credited to their creators.
Make & explore
Experiments.
See what builders made with Jev. Games, tools, repositories, articles, and more — traced to their sources.
The directory03 / 03 · Experiments
Find something worth exploring.Experiments
Every category, from games and tools to repositories and writeups, traced to a primary source.
Real-time research powered by
Same ideas.
Different paths.
This is the full registry, not just the featured picks. Figures like speed, cost, and stars are maker-reported or captured snapshots, not JevMade measurements.
2140 experiments · showing 61–120
Collects Jev projects, reusable agent skills, and editable decision recipes with an optional validated Python client.
SOURCE SCREENSHOTEXPAND ↗
Coder One uses Jev to steer and check bounded autonomous coding sessions.
SOURCE SCREENSHOTEXPAND ↗
from the source
let mut judge = policy .judge(jev_client, workdir.clone(), &state.issue, recorder.clone()) .with_deep(policy.deep_jev());judge.survey(&mut state).await;
Rizzo Flow serves local Spark models through a Jev-compatible API and visual playground without generating answer text.
SOURCE SCREENSHOTEXPAND ↗
Compare Jev's market probabilities and trading choices in a Polymarket benchmark that never places real-money orders.
SOURCE SCREENSHOTEXPAND ↗
from the source
probability = noul_probability(answers, "probability")action = choice_value(answers, "action")confidence = choice_value(answers, "confidence")
See where a Claude Code session made progress and where it went in circles, with Jev reviewing a redacted trace.
SOURCE SCREENSHOTEXPAND ↗
from the source
key: "progressingEfficiently", label: "Progress", question: "Did the agent make steady, meaningful progress toward the user's task... higher_probability_is_better: true, answer: MetricAnswer::Noul,
Shows intent, risk, and ranked reply suggestions beside supported macOS chats while keeping message sending under user control.
SOURCE SCREENSHOTEXPAND ↗
Browse a bilingual, source-linked index of Jev projects grouped by decision pattern, with dated link and call-site checks.
SOURCE SCREENSHOTEXPAND ↗
A Hermes toolkit for model routing, retrieval triage, memory, skill selection, context trimming and interface decisions.
SOURCE SCREENSHOTEXPAND ↗
Identify IRS forms and schedules from their text with Jev.
SOURCE SCREENSHOTEXPAND ↗
from the source
const q1: Record<string, ChoiceQuestion> = { kind: { type: 'choice', instructions: 'What kind of page is this?', criteria: KIND_C... form: { type: 'choice', instructions: FORM_INSTRUCTIONS, criteria: firstList }, } const r1 = await opts.backend.ask(state, q1)
A Jev-compatible server reads answer-label logits from Qwen3.6-35B-A3B while SGLang reuses shared prompt prefixes.
SOURCE SCREENSHOTEXPAND ↗
An MCP server that lets a coding agent ask Jev whether a claim is supported, a page is worth reading, or its own patch is safe.
SOURCE SCREENSHOTEXPAND ↗
choice
How does the evidence relate to claim `claim0` (`<claim text>`)? · supports / contradicts / says_nothing
Check a company-report hypothesis against quoted paragraphs, keeping support, contradiction and unresolved claims visible.
SOURCE SCREENSHOTEXPAND ↗
Shortlist coding approaches, score them in a loop, and inspect the gates surrounding an LLM implementation run.
SOURCE SCREENSHOTEXPAND ↗
A software-factory foreman built around TypeSafe's Jev model.
SOURCE SCREENSHOTEXPAND ↗
from the source
TYPESAFE_API_KEY=your-key-here
Tunes Jev decision functions from labelled examples by surfacing uncertain cases and proposing revised definitions through GEPA.
SOURCE SCREENSHOTEXPAND ↗
A 151M non-autoregressive decision model pairs typed outputs with benchmark receipts, calibration analysis, and browser-oriented artifacts.
SOURCE SCREENSHOTEXPAND ↗
A Mac menu-bar assistant that uses Jev to choose what to click.
SOURCE SCREENSHOTEXPAND ↗
from the source
nonisolated static let maxChoices = 255 nonisolated static let doneThreshold = 0.70 nonisolated static let absentThreshold = 0.50 nonisolated private static let noneKey = "__none__" endpoint: URL = URL(string: "https://api.typesafe.ai/v1/systemone")!) {
A staged Jev code-review workflow with a local dashboard.
SOURCE SCREENSHOTEXPAND ↗
from the source
Noul risk matrix -> Choice + Score file profiles -> Choice evidence selection -> Choice mechanism classification -> Score severity
TypeSafe agent skills
officialOfficial agent skills for writing software that uses TypeSafe's System One API.
SOURCE SCREENSHOTEXPAND ↗
from the source
claude plugin marketplace add typesafe-ai/skillsclaude plugin install typesafe@typesafe-ai
Point DocJev at a PDF and a list of categories you wrote in plain English, and Jev names the category or marks where each new document starts.
ACTUAL RECORDING12 SEC ↗
noul
Does page number 5 start a new source document, rather than continue page number 4?
Vector Graph RAG can rerank graph relations with Jev and compare the resulting retrieval recall.
SOURCE SCREENSHOTEXPAND ↗
from the source
"reranker_provider": self.rag.settings.reranker_provider,"jev_model": self.rag.settings.jev_model if self.rag.settings.reranker_provider == "jev"..."jev_threshold": self.rag.settings.jev_threshold if self.rag.settings.reranker_provider...
skillbox is a self-hosted, versioned Agent Skills library with MCP access, scoped clients, and optional Jev recommendations.
SOURCE SCREENSHOTEXPAND ↗
AbdelStark curates official references and community work around TypeSafe, Jev, and System One models.
SOURCE SCREENSHOTEXPAND ↗
A macOS automation loop that reads the screen with OCR, asks Jev what to do next, and clicks the chosen target.
SOURCE SCREENSHOTEXPAND ↗
from the source
git clone https://github.com/awlevin/typesafe-computer-usecd typesafe-computer-useuv synccp .env.example .env # fill in the keys
Audits each LLM code-review finding with one credibility question before deterministic CI rules decide whether to fail.
SOURCE SCREENSHOTEXPAND ↗
from the source
"questions": { QUESTION_ID: { "type": "noul", "question": VERIFY_QUESTION, "instructions": VERIFY_INSTRUCTIONS,
Jobseek asks Jev to sort batches of listings by a job seeker's plain-language preferences, showing accepted and rejected matches in separate groups.
SOURCE SCREENSHOTEXPAND ↗
from the source
decision: parseChoiceAnswer(answers[job.key]),
Drive an environment from a finite action menu, with Jev choosing the next step and code executing it.
SOURCE SCREENSHOTEXPAND ↗
Suggests a safe moment to compact an agent session by combining two Jev judgments with context usage.
SOURCE SCREENSHOTEXPAND ↗
Autopilot's /jev command asks typed yes-or-no, choice or score questions about the current coding session.
SOURCE SCREENSHOTEXPAND ↗
from the source
const answer = await askJev(apiKey, question, { context });const presentation = presentJevAnswer(question, answer);setResult(eventKey, { kind: "jev", result: presentation.text,
Port browser-use's Jev-driven browser agent to local Laya on Apple Silicon while retaining an optional hosted Jev mode.
SOURCE SCREENSHOTEXPAND ↗
A browser video editor whose Jev-powered Director turns plain-language requests into structured timeline operations.
SOURCE SCREENSHOTEXPAND ↗
from the source
// Shared shapes for the Director's timeline operations and vault-media placement.// Filled by Jev on the server (POST /director/route), executed in Home.tsx.export type TimelineOperation = | 'delete' // remove clip(s) | 'split' // cut clip(s) at a time
Notra turns material from your work into publishable content.
SOURCE SCREENSHOTEXPAND ↗
Adds typed tool, skill, owner, and quality decisions to agent harnesses without taking over their planning or execution.
SOURCE SCREENSHOTEXPAND ↗
A PostgreSQL extension for asking questions about tables in plain language with Jev.
SOURCE SCREENSHOTEXPAND ↗
yibie's directory groups public Jev projects, integrations, and discussions by practical use case.
SOURCE SCREENSHOTEXPAND ↗
from the source
- [Name](URL) - Industry: one-sentence description of the Jev use case.
Compare Jev with other controllers on simulated Panda pick-and-place, stacking, and obstacle-crossing tasks.
ACTUAL RECORDING12 SEC ↗
Combine cryptocurrency market data with a sample of X posts to produce a buy, sell, hold, or take-profit decision card.
SOURCE SCREENSHOTEXPAND ↗
Provides a visual editor for connecting Jev decision nodes into runnable workflows.
SOURCE SCREENSHOTEXPAND ↗
Jev steers through traffic, junctions, and highway merges by choosing from paths generated inside a 3D driving simulator.
SOURCE SCREENSHOTEXPAND ↗
A Claude Code router that uses Jev to choose the cheapest suitable model for each task.
SOURCE SCREENSHOTEXPAND ↗
from the source
git clone https://github.com/gargpratyush/jev-router.gitcd jev-routernpm installnpm linkecho "JEV_API_KEY=..." > ~/.jev-router.env
See Jev's published chess row alongside language models in a benchmark that separates wins, losses and illegal moves across repeated games.
SOURCE SCREENSHOTEXPAND ↗
Filters oversized Bash output into verbatim chunks before Claude Code or Codex has to read it.
SOURCE SCREENSHOTEXPAND ↗
A mobile automation demo where Jev navigates Uber from route entry to payment selection.
ACTUAL RECORDING12 SEC ↗
from the source
git clone https://github.com/droidrun/mobile-jev.gitcd mobile-jevcorepack enablepnpm install --frozen-lockfilecp .env.example .env.local
A web playground compares parallel and one-shot LLM judgments with a compatible open decision-model backend.
SOURCE SCREENSHOTEXPAND ↗
TypeSafe JavaScript SDK
officialThe official TypeScript and JavaScript SDK for the TypeSafe API.
SOURCE SCREENSHOTEXPAND ↗
choice
What is this ticket about?
Float a translucent panel over WeChat or QQ to see intent, risk, urgency, and Jev-ranked reply candidates.
SOURCE SCREENSHOTEXPAND ↗
Search multilingual text by meaning, with grep-like thresholds and AND, OR and NOT combinations over exact source lines.
SOURCE SCREENSHOTEXPAND ↗
Jevlint checks pieces of code against plain-language rules, with uncertain answers kept separate from passes and failures.
SOURCE SCREENSHOTEXPAND ↗
System One adapter (Python)
officialA Python replacement for TypeSafeClient that runs against general-purpose LLM APIs.
SOURCE SCREENSHOTEXPAND ↗
from the source
from system_one_adapter import SystemOneAdapterClient, Noul, Score, Choiceclient = SystemOneAdapterClient( structured_outputs=True, # use the provider's native structured-output mode llm_answer_mode="probabilities", # or "discrete" normalize_probabilities=True,
A local-first MCP plugin for continuous software-quality reviews by coding agents.
SOURCE SCREENSHOTEXPAND ↗
Medical MCP asks Jev to rank fetched clinical literature against a research question.
SOURCE SCREENSHOTEXPAND ↗
from the source
const applied: PolicyDecision = applyPolicy(judged.scores, row.evidence);const ranked = toRankedHit(row.hit, applied);
cobanov maintains a source-linked catalog of projects built with Jev.
SOURCE SCREENSHOTEXPAND ↗
An Apple Silicon experiment scores visual candidates directly against shared context using a local model.
SOURCE SCREENSHOTEXPAND ↗
from the source
jev-visual examples/photo-request.json --model-path .models/Qwen3.5-0.8B-4bit
Prism shadows deterministic Solana liquidity rules with Jev judgments about strategy, toxic flow, recovery, and market stress.
SOURCE SCREENSHOTEXPAND ↗
fatwang2 pairs a sourced Jev project directory with a reusable GitHub review workflow dedicated to Jev submissions.
SOURCE SCREENSHOTEXPAND ↗
Indexes visible browser controls, lets Jev choose an allowed operation and target, then verifies page evidence with Playwright.
SOURCE SCREENSHOTEXPAND ↗
An MCP server that lets agents navigate a browser with Jev decisions.
SOURCE SCREENSHOTEXPAND ↗
from the source
Install the Jev Browser MCP server for me. The package is @jkudish/jev-browser on npm an...command is `npx -y @jkudish/jev-browser`; register it as an MCP server with your client....TYPESAFE_API_KEY is already set in the server environment; if not, walk me through setti...pasting the key into the chat (I can create one at console.typesafe.ai/settings/keys). W...registered, ask if I'd like to run a first navigation task, and when we do, show me the...
JevK5 trains and serves an open-weight decision model that returns closed-choice probabilities in one forward pass; it is not TypeSafe's Jev.
SOURCE SCREENSHOTEXPAND ↗
An agent skill for writing and improving programs that call Jev.
SOURCE SCREENSHOTEXPAND ↗
from the source
git clone https://github.com/dbreunig/building-with-jev-skillcp -r building-with-jev-skill/skills/jev ~/.claude/skills/jev
Honing puts small open decision models into Red Alert 2 and a bouncing-shell tank game, then feeds what happened back into their training and the code around them.
ACTUAL RECORDING12 SEC ↗
Jev, briefly
A decision model, not a chatbot.
A chat model generates text token by token and hopes you parse it. Jev never generates a word. Your code sends the state of the world plus typed questions; Jev returns every answer in one parallel pass — typed values with calibrated probabilities and a confidence score your code can trust. About 70–500 ms end to end, $0.042 per million input tokens, output free. Trained with what TypeSafe calls Reinforcement Learning for Calibrated Decisions.
choice Pick one of these.
You define the options. Jev returns the chosen option, a probability for every option, and a confidence. The workhorse of routing, agents, and games — the answer space is always legal, so there is nothing to parse and nothing to hallucinate.
score Rate this on a rubric.
You describe ordered levels — say trivial / normal / critical. Jev returns the level, the probability of each, and a confidence. Scores turn fuzzy judgment (“how severe is this log line?”) into a number-free decision your code can branch on.
noul Is this statement true?
You assert a statement; Jev returns the probability that it is true — a noul. Moderation, verification, guardrails, “does this diff actually fix the bug?”: one question, one calibrated probability.
Official material lives at typesafe.ai and docs.typesafe.ai. JevMade is an independent community registry — not affiliated with or endorsed by TypeSafe AI.
Recurring lessons
Patterns that keep showing up.
One decision per tick
Games, drones, trading bots, and browser agents all converge on the same loop: serialize the state, ask one decisive question, act, repeat. Jev’s latency makes the loop feel instant — the model lives inside the control loop, not outside it.
Confidence as a gate
The answer says what; the confidence says whether to act. The most reliable entries threshold on confidence to route edge cases to a slower model or a human — automation with an honest escape hatch.
Shrink the choice space in code
Makers rarely ask Jev to pick from everything. Local tactics prune 225 gomoku moves to ~40; DOM filters turn a page into an element table; code narrows options, Jev judges within them.
Jev judges, LLMs talk
A recurring split: Jev makes every decision cheaply and instantly, and a small LLM is only invoked when a human-facing string must actually be written. Decision and generation are separate budgets.
Made something with Jev?
Send the link — repo, live demo, post, or video — plus a line on what it does and which primitives it uses. Every entry is verified against its primary source before it ships.
Submit your experimentSign in first so we can reply to you. Submissions are reviewed, not published automatically.