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.
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.
311 experiments · showing 181–240
An MCP server for semantic code search and diff checks in Antigravity, Cursor, and Claude Code.
SOURCE SCREENSHOTEXPAND ↗
A PowerShell tool that asks Jev to review coding-agent conversations and answer focused questions about them.
SOURCE SCREENSHOTEXPAND ↗
from the source
:jev Audit the current conversation:jev ask Did the tests pass? A typed yes/no judgment plus evidence sufficiency:jev --details Include evidence window and omission counts:jev help Local help
An MCP server that brings Jev judgments into Cursor, Codex, and other MCP clients.
SOURCE SCREENSHOTEXPAND ↗
noul
Is this urgent?
An agent skill that uses Jev to predict another skill's next closed decision without running it.
SOURCE SCREENSHOTEXPAND ↗
A capability router that matches each coding prompt with installed skills, MCP servers, agents, and commands.
SOURCE SCREENSHOTEXPAND ↗
A stop hook that keeps coding agents working until plain-language completion rules are satisfied.
SOURCE SCREENSHOTEXPAND ↗
from the source
claude plugin marketplace add noplan-inc/limpetclaude plugin install limpet@limpet --config typesafe_api_key=... --config block=0.8
Ask Jev to review code or answer a question from inside Oh My Pi.
SOURCE SCREENSHOTEXPAND ↗
from the source
src/index.ts factory: triggers, typesafe_ask, /adversary, /typesafesrc/reviewer.ts batteries, severity derivation, emission guard, delivery routingsrc/evidence.ts git probes via pi.exec, missed-callsite grepsrc/branch.ts session-branch scanner (camelCase roles)src/client.ts @typesafe-ai/sdk wrapper, usage tracking
Sort through repository issues with help from Jev, while Zero keeps the repository data in sync.
SOURCE SCREENSHOTEXPAND ↗
from the source
git clone https://github.com/cephalization/jev-triagecd jev-triagecp .env.example .env # set TYPESAFE_API_KEY, and GITHUB_TOKEN if you want pull reque...vp installvp run dev # postgres (docker) + migrations + api + zero-cache + web
Inspect and operate an SO-101 robot workbench where Jev can choose bounded joint movements.
SOURCE SCREENSHOTEXPAND ↗
Lets agents gather audit context while Jev assigns severity, confidence and routing judgments for code-owned policy.
SOURCE SCREENSHOTEXPAND ↗
Remove stale read-only Pi tool exchanges while preserving every retained piece of evidence byte for byte.
SOURCE SCREENSHOTEXPAND ↗
Filter ripgrep passages for a Codex task without losing the ability to reveal hidden results or nearby code.
SOURCE SCREENSHOTEXPAND ↗
Find files and line ranges relevant to a coding task with a searchable map of your source code.
SOURCE SCREENSHOTEXPAND ↗
from the source
questions['q' + k] = noul( `To carry out the task in \`task\`${where}, a developer must read or modify this code...);const question = choice( `A developer must carry out the task described in \`task\`${projectClause(project)}. W...
Lets a Flutter integration test state its goal, then chooses registered UI actions until that goal is met or attempts run out.
SOURCE SCREENSHOTEXPAND ↗
from the source
'goal_reached': { 'type': 'noul', 'instructions': 'Is the goal already achieved according to the current screen? Judge only visible...
Applies a YAML policy to Claude Code tool calls, using Jev scores to allow, deny, or review each action.
SOURCE SCREENSHOTEXPAND ↗
Ranks Clay people-search results with Jev probabilities for role fit and current operating-founder status.
SOURCE SCREENSHOTEXPAND ↗
Composes Unix-style tools that seed, expand, judge, verify, and report code defects while preserving evidence chains.
SOURCE SCREENSHOTEXPAND ↗
Routes each agent turn’s effort, tools, skill, and model tier from one bounded Jev request behind a hard deadline.
SOURCE SCREENSHOTEXPAND ↗
Turns an agent skill into project-specific Oxlint checks, using AST rules for structure and Jev for contextual judgement.
SOURCE SCREENSHOTEXPAND ↗
Adds a zero-dependency CLI and coding-agent skill for batching narrow yes/no, choice, and score judgements.
SOURCE SCREENSHOTEXPAND ↗
A command-line referee judges supplied evidence with Jev, compares choices in both option orders and keeps local decision receipts.
SOURCE SCREENSHOTEXPAND ↗
Let a coding agent fix a GitHub issue, with tests and AI reviewers checking its work before it proceeds.
SOURCE SCREENSHOTEXPAND ↗
An experiment in checking an agent's work before handing it to another agent, with Jev helping review the evidence.
SOURCE SCREENSHOTEXPAND ↗
A CLI and GitHub Action that combines deterministic rules with Jev to assess the risk of code changes.
SOURCE SCREENSHOTEXPAND ↗
from the source
- uses: moezubair/check-risk@v0.1 with: base: ${{ github.event.pull_request.base.sha }} head: ${{ github.event.pull_request.head.sha }} typesafe-api-key: ${{ secrets.TYPESAFE_API_KEY }}
A configurable Go CLI that uses Jev to route prompts between models.
SOURCE SCREENSHOTEXPAND ↗
An experimental Hermes plugin for planning model routes within budget and capability constraints.
SOURCE SCREENSHOTEXPAND ↗
from the source
hermes plugins install ussyverse/hermes-jev-router --no-enable# Review code, then enable explicitly:hermes plugins enable jev-router
A Grok skill that combines Jev probabilities with prior beliefs to choose the next action in a builder-agent loop.
SOURCE SCREENSHOTEXPAND ↗
from the source
git clone https://github.com/rainbowpuffpuff/jev-builder-loop.gitmkdir -p ~/.grok/skillsln -sfn "$(pwd)/jev-builder-loop" ~/.grok/skills/jev-builder-loop
An automated pull-request reviewer with Jev-based approval thresholds and escalation to trusted owners.
SOURCE SCREENSHOTEXPAND ↗
from the source
export TYPESAFE_API_KEY='...'export GITHUB_TOKEN='...'.venv/bin/python -m jev_review github --repo OWNER/REPO --pr 123 --config examples/githu....venv/bin/python -m jev_review poll --repo OWNER/REPO --config examples/github-config.js...
A Jev-powered permission gate for the omp coding agent.
SOURCE SCREENSHOTEXPAND ↗
A Pi extension that sends agents back to work when Jev determines they stopped before completing the task.
SOURCE SCREENSHOTEXPAND ↗
from the source
{ "typesafe": { "type": "api_key", "key": "..." }}
A Pi coding coprocessor that uses Jev gates to review changes from the initial baseline and record an append-only activity trail.
SOURCE SCREENSHOTEXPAND ↗
Ask Jev to choose, score or answer yes-or-no questions without leaving a Pi coding session.
SOURCE SCREENSHOTEXPAND ↗
from the source
sidecar=/absolute/path/to/pi-typesafemkdir jev-playgroundcd jev-playgroundgit initpi -e "$sidecar/src/extension.ts"
A Pi extension that exposes five tools for narrow Jev judgments while leaving thresholds and actions in application code.
SOURCE SCREENSHOTEXPAND ↗
noul
Does `ticket_message` request a refund?
A standard-library Python gateway that checks prompts for risk and routes safe requests to a suitable model.
SOURCE SCREENSHOTEXPAND ↗
from the source
client ─► POST /v1/chat/completions │ ├─ 1 Jev call, 4 questions in parallel (questions.py) │ injection? harmful? pii? (Noul each) tier: small | large | uncle... ├─ policy.py (pure code) risk ≥ 0.80 → 403 block · 0.40–0.80 → allow + fla...
An MCP server that exposes Jev's Noul, Choice, and Score judgments as agent tools.
SOURCE SCREENSHOTEXPAND ↗
A Python tool that uses TypeSafe AI to review code diffs.
SOURCE SCREENSHOTEXPAND ↗
A provider-agnostic judgment layer that gates a coding workflow from product requirements through release.
SOURCE SCREENSHOTEXPAND ↗
jev-rabbit reviews pull requests against project rules written in plain English.
SOURCE SCREENSHOTEXPAND ↗
from the source
“i'm cooking jev-rabbit 🐰
a PR review bot that uses Jev with a set of rules you write...
Duncan's router asks Jev which available model best fits a request, then forwards the prompt there.
SOURCE SCREENSHOTEXPAND ↗
from the source
“Built a model router with Jev by @typesafeai.
Jev decides what model fits your reques...
Choose the best AI model or agent for a task from services you already subscribe to.
SOURCE SCREENSHOTEXPAND ↗
from the source
“i used jev from typesafeai to build a model router cli
you give in a task and current...
skillbox uses Jev to select relevant agent skills directly from the user's query.
SOURCE SCREENSHOTEXPAND ↗
from the source
“i added Jev to skillbox so instead of my dumb agents doing 30 turns on finding the righ...
Vercel's fx tests Jev as the reviewer that decides whether automatically generated shell commands are safe to run.
SOURCE SCREENSHOTEXPAND ↗
from the source
“We're seeing extraordinary results from @typesafeai. Default mode in 𝚏𝚡 is auto, with a...
Study Jev's decision concepts in Japanese, then test them in a short game about spotting a disguised delivery unit.
SOURCE SCREENSHOTEXPAND ↗
Find code that deserves a closer look by asking Jev to rank possible design problems.
SOURCE SCREENSHOTEXPAND ↗
Compacts Pi history without generated summaries, keeping selected tool exchanges and optional assistant prose exactly as they appeared.
SOURCE SCREENSHOTEXPAND ↗
Keep track of Codex workers with Jev progress checks, then accept their work only when your chosen command passes.
SOURCE SCREENSHOTEXPAND ↗
A reference decision layer for Minecraft that turns typed judgments into tool calls behind hard-coded survival reflexes.
SOURCE SCREENSHOTEXPAND ↗
from the source
export const API = { baseUrl: 'https://api.typesafe.ai', evaluatePath: '/v1/systemone', modelsPath: '/v1/models', apiKeyEnv: 'TYPESAFE_API_KEY',
Helps an agent find the right tool or skill without loading the whole catalog into its main conversation.
SOURCE SCREENSHOTEXPAND ↗
A Pi tool for asking typed questions, with interchangeable Jev and chat-model backends.
SOURCE SCREENSHOTEXPAND ↗
Ask Jev to label nytka datasets and keep a record of the questions and model used.
SOURCE SCREENSHOTEXPAND ↗
Get a shell completion from your command history that changes as you type, rather than a static prefix match.
ACTUAL RECORDING12 SEC ↗
Three Jev tools for the DeepSeek Harness on WSL: ask typed questions, check whether evidence supports a claim, or rank candidates.
SOURCE SCREENSHOTEXPAND ↗
from the source
return await client.systemOne({ state: args.state, questions })
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.
SOURCE SCREENSHOTEXPAND ↗
from the source
const res = await fetch(`${baseUrl.replace(/\/$/, "")}/v1/systemone`, {
A Neovim intent router that sends your prompt to Jev as one Choice and dispatches to a read, edit, shell or chat handler.
SOURCE SCREENSHOTEXPAND ↗
from the source
M.defaults = {endpoint = \"https://openrouter.ai/api/alpha/decisions\",model = \"typesafe/jev-1.13\",
A linter that sends each file an agent touched to Jev and asks one question: is this slop?
SOURCE SCREENSHOTEXPAND ↗
from the source
result = client.system_one( (client = TypeSafeClient(model="jev-latest") at line 85)
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.
SOURCE SCREENSHOTEXPAND ↗
from the source
* Falls back to `POST {baseURL}/v1/systemone
An agent skill and stdlib CLI that turn Python or JavaScript question builders into one System One payload, with six named decision playbooks.
SOURCE SCREENSHOTEXPAND ↗
from the source
req = urllib.request.Request(args.endpoint, data=req_data, headers=headers, method=
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.
SOURCE SCREENSHOTEXPAND ↗
from the source
const url =
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.
SOURCE SCREENSHOTEXPAND ↗
from the source
this.baseUrl = opts.baseUrl ?? 'https://api.typesafe.ai/v1/systemone';
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.
SOURCE SCREENSHOTEXPAND ↗
from the source
export const TYPESAFE_BASE_URL = process.env.TYPESAFE_BASE_URL ??
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.