Read & learn
Written guides.
Understand Jev, one idea at a time. Walkthroughs, recipes, and writeups — our notes first, the original next.
Learn, build, and play with Jev — from deep technical guides to creative experiments.
Read & learn
Understand Jev, one idea at a time. Walkthroughs, recipes, and writeups — our notes first, the original next.
Watch & learn
See an idea take shape. Tutorials, demos, and deep dives, organized by topic and credited to their creators.
Make & explore
See what builders made with Jev. Games, tools, repositories, articles, and more — traced to their sources.

Every category, from games and tools to repositories and writeups, traced to a primary source.
Real-time research powered bySame 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.
388 experiments · showing 241–300
An MCP server that exposes Jev's Noul, Choice, and Score judgments as agent tools.
A Python tool that uses TypeSafe AI to review code diffs.
A provider-agnostic judgment layer that gates a coding workflow from product requirements through release.
jev-rabbit reviews pull requests against project rules written in plain English.
Duncan's router asks Jev which available model best fits a request, then forwards the prompt there.
Choose the best AI model or agent for a task from services you already subscribe to.
skillbox uses Jev to select relevant agent skills directly from the user's query.
Vercel's fx tests Jev as the reviewer that decides whether automatically generated shell commands are safe to run.
Study Jev's decision concepts in Japanese, then test them in a short game about spotting a disguised delivery unit.
Find code that deserves a closer look by asking Jev to rank possible design problems.
Compacts Pi history without generated summaries, keeping selected tool exchanges and optional assistant prose exactly as they appeared.
Keep track of Codex workers with Jev progress checks, then accept their work only when your chosen command passes.
A reference decision layer for Minecraft that turns typed judgments into tool calls behind hard-coded survival reflexes.
Helps an agent find the right tool or skill without loading the whole catalog into its main conversation.
A Pi tool for asking typed questions, with interchangeable Jev and chat-model backends.
Ask Jev to label nytka datasets and keep a record of the questions and model used.
Get a shell completion from your command history that changes as you type, rather than a static prefix match.
Three Jev tools for the DeepSeek Harness on WSL: ask typed questions, check whether evidence supports a claim, or rank candidates.
A Claude Code and Codex plugin that checks each tool call and final answer against the project's own rules with a System One model.
A Neovim intent router that sends your prompt to Jev as one Choice and dispatches to a read, edit, shell or chat handler.
A linter that sends each file an agent touched to Jev and asks one question: is this slop?
A drop-in routing layer that turns named routes into one Jev Choice, with a gate question for whether the request is even in domain.
An agent skill and stdlib CLI that turn Python or JavaScript question builders into one System One payload, with six named decision playbooks.
Packages Jev as five tools — classify, check, score, rank and ask — and installs the same skill into Claude Code, Codex, Pi and OpenCode with one command.
Checks content an agent is about to read for instructions aimed at the agent, and returns a trust verdict plus capability advice rather than a boolean.
A coding agent that thinks with an LLM and reacts with Jev: every tool call, turn and voice transcript is checked in about 400 milliseconds and code decides.
An OpenAI- and Anthropic-compatible gateway where a small System One model picks which larger model should answer each prompt.
An MCP server and agent skill for using System One at design time: decompose a judgment into questions, lint them, calibrate thresholds on labelled rows and rerank.
A local agent harness that puts Jev in front of an ordinary LLM and pays for the LLM only when the work needs prose.
A coding-agent CLI that splits the work: a decision model picks the next tool, scores progress and judges whether the goal is reached, while an LLM only fills in arguments and writes code.
Gates agent tool calls through detectors, Jev judgments, and deterministic policy before allowing, blocking, or requesting approval.
Reads completed Claude Code or Codex sessions and assigns typed judgements to each turn for later analysis.
Put many MCP servers behind two tools while Jev discovers the best enabled tool and the calling agent supplies its schema-bound arguments.
A Rust CLI turns Jev judgments into stable JSON, resumable batches, assertions, and meaningful shell exit codes.
A small CLI ranks local Agent Skills against a request, then returns suggestions without invoking anything automatically.
Add three Claude Code hooks that flag dangerous commands, failed tool calls, and incomplete work with Jev.
Screen fetched pages and files for prompt injection before coding agents load them, blocking content that crosses configured thresholds.
Check each coding-agent edit against a team style guide and send violations back into the session.
Riley Brown put Jev behind an agent’s model router to choose which model handles each task.
ImRobot’s hook-based gate blocks dangerous agent commands until a person approves that single execution.
Milind S added Jev to OpenMausBot to choose both the teammate and model for each task.
Cyril split agent work so Claude Code writes while Jev handles repeated decisions on suitable tasks.
Jetwani Avinash’s Claude Code gate asks Jev whether each message deserves one line in a repository memory file.
Paulius used Jev to launch agents on Clonk’s visual canvas without waiting for a full LLM loop.
Kelbie built a Jev tool that scores every code chunk for relevance to a developer’s current question.
Cortex is a local MCP server where Claude plans tasks and a faster action layer handles clicks across browsers and Mac apps.
Oskar is building an open-source framework that uses agents and Jev to run end-to-end tests across web and mobile.
grok-jev-reflex is an open-source router where Grok plans and acts while Jev handles cheaper yes-or-no decisions between steps.
Ishwar demonstrates instant Jev compaction during a long Claude Code server-redeployment session.
Action Gate asks Jev to score risky agent actions and routes a simulated $50,000 transfer to human review.
jev-studio packages Jev’s three primitives as MCP tools and a CLI with dry-run provenance.
Monid connects Jev and OpenRouter to a catalogue of tools for lead scoring, research, content analysis, and site audits.
Kiyoro used Jev to detect that Opus 5.5’s default effort had changed from high to medium.
Sawyer Hood uses Jev to choose an agent, model, computer and working folder from a single prompt.
Neha Sharma built a real-time demo that uses Jev to route work among AI agents.
erKam built a Jev check that quotes violated project rules back to Claude Code so it can rewrite its response or edit.
Jev chooses a skill, tool, and parameters before a Slack agent acts, which its maker says doubled its speed.
Jev directs a coding agent toward relevant files and flags possible test gaps, while deterministic tests verify the result.
Read browser-agent activity logs every three seconds and average the resulting risk score across the session.
OpenCodex asks Jev to choose a model and reasoning level for each Codex request, using the proxy's configured route whenever Jev is unavailable or returns an invalid answer.
Jev, briefly
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.
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.
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.
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
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.
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.
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.
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.
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.