Read & learn
Written guides.
Understand Jev, one idea at a time. Walkthroughs, recipes, and writeups — our notes first, the original next.
A public registry · independent & community-run
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.
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.
1611 experiments · showing 361–420
OmniJev collects the papers, open reproductions, and independent evaluations behind Jev and System One models.
SOURCE SCREENSHOTEXPAND ↗
Race Jev against Claude, Gemini, or a local model in a real-time Tetris duel with a shared piece sequence.
SOURCE SCREENSHOTEXPAND ↗
Watch Jev walk, fish, cook, fight, trade, and recover through a RuneScape world using about fifty available actions.
ACTUAL RECORDING12 SEC ↗
Watch a classifier awkwardly become a chatbot by choosing each next word from a tiny fixed vocabulary.
SOURCE SCREENSHOTEXPAND ↗
A GitHub Action that approves a pull request only when every configured Jev policy question clears its threshold.
SOURCE SCREENSHOTEXPAND ↗
A joke package that asks Jev whether a number is even, making one network round trip where a remainder would do.
SOURCE SCREENSHOTEXPAND ↗
choice
Is this number even? · true / false
Adds Jev routing to Oh My Pi, with models, prompts and thresholds you can edit in configuration files.
SOURCE SCREENSHOTEXPAND ↗
Offers idiomatic Elixir functions for typed decisions through TypeSafe System One or OpenRouter’s Decisions API.
SOURCE SCREENSHOTEXPAND ↗
Checks changed code against Markdown specifications and reports likely drift in CI or an agent workflow.
SOURCE SCREENSHOTEXPAND ↗
Run the open-weight Laya decision model locally on Apple Silicon through an Apple-focused runtime; it is Jev-compatible but does not use Jev.
SOURCE SCREENSHOTEXPAND ↗
Select a coding model and reasoning effort for Claude Code or Codex, then keep that pair stable through the task.
SOURCE SCREENSHOTEXPAND ↗
Play poker hands toward a target score while BLUFF's optional Jev autopilot studies the table and chooses its next line.
SOURCE SCREENSHOTEXPAND ↗
Edit Jev scenarios beside their typed answers and probabilities in a colorful three-column playground.
SOURCE SCREENSHOTEXPAND ↗
A set of bounded Jev workflows for coding agents.
SOURCE SCREENSHOTEXPAND ↗
from the source
git clone https://github.com/devagrawal09/jev-code.gitcd jev-codenpm cinpm run buildnode dist/cli.js --help # use "node /path/to/jev-code/dist/cli.js" wherever this READM...
A Pi extension that routes tasks to models through Vercel AI Gateway using Jev.
SOURCE SCREENSHOTEXPAND ↗
from the source
{ "jevRouter": { "options": { "openai-codex/gpt-5.6-luna": { "description": "Small fixes, tests, and routine implementation.",
An opt-in Hermes plugin that uses Jev to select one skill before the main model call.
SOURCE SCREENSHOTEXPAND ↗
A command-line filter that uses Jev to match lines by a natural-language description rather than a text pattern.
SOURCE SCREENSHOTEXPAND ↗
from the source
export JEV_GATEWAY_URL=https://gateway.example.com/v1/systemoneexport JEV_GATEWAY_API_KEY=... # or ~/.config/jev/gateway.key and gateway.urljgrep "a stack trace" build.log # picked automatically when it is the only key set
A live Hyperliquid trading application that can use Jev as its decision model.
SOURCE SCREENSHOTEXPAND ↗
from the source
MODEL=jevJEV_PROVIDER=typesafeTYPESAFE_API_KEY=# JEV_MODEL_ID defaults to jev-latest
A bilingual English-Chinese guide explains notable Jev applications, how they work and their trade-offs.
SOURCE SCREENSHOTEXPAND ↗
Compare Jev's mine probabilities with an exact solver on reproducible Minesweeper boards.
SOURCE SCREENSHOTEXPAND ↗
A UI experiment that asks Jev to choose layouts and components for working shadcn screens.
SOURCE SCREENSHOTEXPAND ↗
Pit local Laya against Jev in matched snake races and fighting-game rounds, or assign either model to both sides.
SOURCE SCREENSHOTEXPAND ↗
Collapse LinkedIn bait, promotions, sponsored posts, and blocked topics while keeping an inspectable score line on each post.
SOURCE SCREENSHOTEXPAND ↗
Use Jev as a fast conversational gate before a Discord voice bot’s speech model and server tools respond.
SOURCE SCREENSHOTEXPAND ↗
Connect Aside browser agents to Jev for bounded next-action decisions while Aside observes and executes.
SOURCE SCREENSHOTEXPAND ↗
Moderates tournament copy and in-game snake shouts, while keeping hard blocks and the human review queue firmly in code.
SOURCE SCREENSHOTEXPAND ↗
Turns a Git diff into native runner filters for the tests most likely to be affected.
SOURCE SCREENSHOTEXPAND ↗
A Mac assistant that enters supplier invoices into Frappe Books, with Jev choosing the on-screen actions.
SOURCE SCREENSHOTEXPAND ↗
from the source
URL = os.environ.get("TYPESAFE_URL", "https://api.typesafe.ai/v1/systemone")def choice(instructions: str, criteria: dict[str, str]) -> dict: return {"type": "choice", "instructions": instructions, "criteria": criteria}def ask(state: dict, questions: dict) -> dict: body = {"model": MODEL, "state": state, "questions": questions}
Trains and serves open models behind a Jev-compatible typed-decision API, without calling hosted Jev.
SOURCE SCREENSHOTEXPAND ↗
Adds Jev-backed output pruning, injection screening, and completion gates to DeepSeek Harness.
SOURCE SCREENSHOTEXPAND ↗
Guides coding agents from a possible Jev use case to a bounded design, baseline, fallback, and small validation experiment.
SOURCE SCREENSHOTEXPAND ↗
Combines DeepSeek-written WeChat replies with optional Jev intent checks, quality review, and ranking on Windows and preview macOS builds.
SOURCE SCREENSHOTEXPAND ↗
Turns plain-English browser flows into Playwright runs where Jev selects controls and independent checks preserve evidence for every result.
SOURCE SCREENSHOTEXPAND ↗
Maps 1,000 recent AI papers into 24 topics with Jev, then compares a seeded sample with an LLM judge.
SOURCE SCREENSHOTEXPAND ↗
Chooses which discovered MCP tool Codex should call, then applies deterministic policy before execution.
SOURCE SCREENSHOTEXPAND ↗
Defines reusable “jevels” for operational decisions and records their answers in a terminal interface.
SOURCE SCREENSHOTEXPAND ↗
Tracks Jev ecosystem projects in a ranked hub rather than implementing a decision workflow itself.
SOURCE SCREENSHOTEXPAND ↗
Try three editable forms that show how Jev routes each submission to a recipient.
SOURCE SCREENSHOTEXPAND ↗
Tell wilwid what you don't want to see, and it hides matching posts and videos.
ACTUAL RECORDING12 SEC ↗
An extensible Python harness that turns Jev decisions into actions.
SOURCE SCREENSHOTEXPAND ↗
An unofficial .NET SDK for asking Jev Noul, Choice, and Score questions.
SOURCE SCREENSHOTEXPAND ↗
from the source
using TypeSafeAI;var client = new TypeSafeClient(); // reads TYPESAFE_API_KEYvar result = await client.SystemOneAsync( "My card was charged twice, please fix this ASAP.", [
A Haskell DSL for defining typed Jev question packets and matching answers to their labels.
SOURCE SCREENSHOTEXPAND ↗
from the source
type Routes = "use_witness" ::> Witness :|: "ask_model" ::> Handoff :|: "edges" ::* Edgetype Inspection = Packet ( "next" ::= Choice Routes :& "enough" ::= Noul :& "children" ::= Each Edge Noul
A Python skill router that uses Jev to make typed, confidence-aware selections.
SOURCE SCREENSHOTEXPAND ↗
Connect Jev to an MCP client, then compare its answers with those of general-purpose models.
SOURCE SCREENSHOTEXPAND ↗
noul
Does the sender need a response today rather than this week?
An agent decision toolkit with a Jev MCP server, embeddable library, and Claude Code plugin.
SOURCE SCREENSHOTEXPAND ↗
A Claude Code plugin for using Jev.
SOURCE SCREENSHOTEXPAND ↗
A fast prose linter with Ruff-style rule codes and Jev-backed semantic checks.
SOURCE SCREENSHOTEXPAND ↗
from the source
# riff.tomlselect = ["RIF", "CLR", "JEV"] # omit to use every default-on ruleignore = ["JEV002"] # drop reasoning-leak (noisy on reflective writ...extend-select = ["JEV401"] # turn on a default-off rule (passive voice)jev = true # set false to skip semantic rules
Jev Guard checks coding-agent tool calls and returns an allow, ask, or deny decision based on risk and session context.
SOURCE SCREENSHOTEXPAND ↗
from the source
npm i -g jev-guardjev-guard key "…" # TypeSafe key from console.typesafe.ai, or a vck_…...jev-guard install claude|codex|copilot|gemini|cursor|pi|opencode # writes hooks into t...jev-guard check Bash '{"command":"rm -rf ~/"}'# DENY jev-guard blocked this call (risk 3.0/3, approval p=0.98, confidence 0.99): Bash...
A TypeScript command-line client for TypeSafe's Jev model.
SOURCE SCREENSHOTEXPAND ↗
Spot the sales pitch, call to action or other intent behind an X post with labels chosen by Jev.
SOURCE SCREENSHOTEXPAND ↗
from the source
content.js 读 DOM、提取帖子、渲染标签、缓存 ↓ chrome.runtime.sendMessagebackground.js (service worker) 唯一发请求的地方 ↓ fetchapi.typesafe.ai
A browser-based 2D autonomous-car simulation driven by Jev decisions.
SOURCE SCREENSHOTEXPAND ↗
from the source
npm installcp .env.example .env # TYPESAFE_API_KEY from https://console.typesafe.ai/settings/k... # optional OPENROUTER_API_KEY for the comparison modenpm start # http://localhost:3000
A recursive tournament engine that uses Jev scoring and Swiss matchmaking to rank AI candidates by Elo.
SOURCE SCREENSHOTEXPAND ↗
from the source
TYPESAFE_API_KEY=your_key_hereTYPESAFE_MODEL=jev-latest
A command-line tool for inserting Jev-based semantic decisions into Unix pipelines and CI jobs.
SOURCE SCREENSHOTEXPAND ↗
from the source
TYPESAFE_API_KEY='...'
A Three.js quickscope arena pits the player against a Jev-controlled opponent.
SOURCE SCREENSHOTEXPAND ↗
jevfire batches many Jev-style decisions over one shared context on CUDA language models.
SOURCE SCREENSHOTEXPAND ↗
from the source
git clone https://github.com/kikoncuo/jevfire.gitcd jevfirepython -m venv .venvsource .venv/bin/activatepython -m pip install -e '.[dev]'
LegalForecastBench provides an alpha benchmark and evaluation workflow for LegalForecast-MTD.
SOURCE SCREENSHOTEXPAND ↗
A word-level language model that drafts with n-grams and asks Jev to check chunks of the result.
SOURCE SCREENSHOTEXPAND ↗
from the source
jev-lm probe "the little dog was" --top 5jev-lm verify "the capital of france is" "paris" "london"jev-lm gen "the little dog" --words 18 --tracejev-lm gen "she went to the door" --draft --tracejev-lm eval --file data/heldout_en.txt --positions 60
typesafe-local asks a local MLX model typed questions and returns calibrated probabilities without generating or parsing prose.
SOURCE SCREENSHOTEXPAND ↗
from the source
{ "model": "mlx-community/Qwen3-1.7B-bf16", "answers": { "refund_requested": {"type": "noul", "noul": 1.0, "raw_mass": 1.0}, "department": {"type": "choice", "choice": "billing",
Verdict is a 151M-parameter ModernBERT decision engine with calibrated uncertainty and no autoregressive generation.
SOURCE SCREENSHOTEXPAND ↗
Turn live Japanese speech into variety-show captions, manga effects, colored lenses, and sound cues.
SOURCE SCREENSHOTEXPAND ↗
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 experiment → hello@JevMade.com