
Guidegithub.com
Awesome Jev
The companion list to this site: use cases, projects, SDKs, tools and learning resources, with pricing, limits and a quick start.
Updated Sep 18, 2026
Projects, posts and guides about Jev, the System One model from TypeSafe AI. Each entry links to its source and shows the cost and speed its author reported.

Diogo Almeida
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions AFAICT the shortest path to AI-based economic revolution

Guidegithub.com
The companion list to this site: use cases, projects, SDKs, tools and learning resources, with pricing, limits and a quick start.
Tony Dinh
@tdinh_me
Just trying out Jev, I made a Chrome extension that: - Listens to your YouTube audio (optional) - Detects if it gets to a sponsor segment - Skips it ➡️➡️➡️ - All in real-time while costing ~$0.005 per video Prototype project, BYOK, open-source: github.com/trungdq88/yout…

GitHubAgents and browsers
PickBrowser Use’s browser agent, with Jev choosing each next step.
Browser Use
~2.9k
GitHubAgents and browsers
Computer use on macOS, with one Jev decision per step.
Andrew Levin
~$0.0002Jarrod Watts
@jarrodwatts
I built a trading bot with Jev! Jev decides if it should "buy" or "sell", given the price feed of an asset pair, and executes real trades. It uses Monad to place the orders on Kuru's on-chain order book in every 300ms block. Demo link → jev-trader.vercel.app

GitHubRobotics and devices
A simulated drone that asks Jev for a judgment 2.5 times a second.
Roman Slack
2.5 HzSponsors

GitHubAgents and browsers
A browser you control by voice, from Moritz Kremb’s Jev tutorial.
Moritz Kremb
Vincent Wang-Maścianica
@vinnylarouge
I reverse-engineered a jev-like architecture given its type. You can find the repo here to train your own jevlikes: github.com/vinnylarouge/j…
GitHubResearch and data

Eric Zhang
@ekzhang1
Inspired by @typesafeai , here is a Jev-compatible public API to play with It runs a comparable open model (Qwen3.6-35B-A3B), and just uses SGLang radix cache to preserve the prefill reuse / really fast parallel systemone generation - 64 tasks in <1s. github.com/ekzhang/openje…

GitHubTriage and routing
Routes each Claude Code task to the cheapest model that can do it.
Pratyush Garg
121
GitHubTools and apps
An MCP server with claim checks, screening and ranking built on Jev.
Joey Kudish
70
GitHubTools and apps
An MCP connector that gives your agent direct access to Jev.
Mostafa
62
GitHubResearch and data
A small open decision model: state and typed questions in, probabilities out.
Kshetrajna Raghavan
57
GitHubTools and apps
A browser extension where Jev decides which parts of a page are clutter.
Kitze
74
GitHubContent and growth
A Discord moderation bot with Jev making the calls.
Brainstormity
25
GitHubContent and growth
Moderation with a probability per category and thresholds you set.
Omar Hernandez


GitHubContent and growth
An agent-first SEO and GEO CLI in Rust, with DuckDuckGo and Jev.
Akash Priyadarshi

GitHubTools and apps
A shell CLI for agents: pick, rate, check, rank, triage and guard.
Nicholas Underwood

GitHubTools and apps
A typed judgment CLI: questions in, answers and exit codes out.
model-clis

GitHubTools and apps
A Python toolkit: question builders, confidence gates and calibration.
Daniel Ari Friedman


GitHubTools and apps
110 use cases, games and dilemmas, with editable prompts and A/B tests.
Val Alexander
110
GitHubAgents and browsers
Browser automation where an LLM plans and Jev decides.
Ying-Kai Liao
Sponsors

GitHubAgents and browsers
One Jev and Playwright core behind a typed SDK, a CLI and an MCP server.
Tomohiko Hiraki

GitHubAgents and browsers
Jev picks each action; an LLM plans; every claim cites the page.
Agent Labs

GitHubAgents and browsers
Browser use for coding agents, with Jev deciding each step in ~300 ms.
Brian Kim
~300 ms
GitHubAgents and browsers
Claude thinks, Jev reacts: browser tasks at about 100 ms a decision.
MirkoSonio
~100 ms
GitHubAgents and browsers
A speed layer for computer use: one Jev decision per step.
Hitakshi Arora



GitHubAgents and browsers
A decision layer for agents: MCP server, library and Claude Code plugin.
Brainwires

GitHubAgents and browsers
Checks every side-effecting tool call against what you asked for.
Bowen Xu

GitHubAgents and browsers
Automatic context clearing for Pi, without losing the conversation.
Nour

GitHubAgents and browsers
A context curator for the Pi agent, built on Jev.
Shashank H

GitHubAgents and browsers
A Codex plugin where Jev trims bulky tool results.
Konstantinos Botonakis

GitHubAgents and browsers
Jev selects the developer tools; Codex writes the code.
Mihajlo Micic

GitHubAgents and browsers
An MCP server so coding agents stop spending tokens on small choices.
Ravinder Poonia

GitHubAgents and browsers
An MCP server that puts Jev on the coding loop in Cursor and Codex.
burnigtm

Guidegithub.com
Tamara Tran’s Claude Code plugin: Jev scores every tool call and result in one request, drops or truncates the stale ones, and keeps the rest word for word.

GitHubAgents and browsers
Plain-language MCP tool calls with no LLM at all, only Jev.
abhishekashokvkumar


GitHubTriage and routing
One batched call picks model tier, tools, skill and effort for each turn.
Joaquin Marcoff

GitHubTriage and routing
An agent-native router that picks a model by task complexity.
Raj Dhakad

GitHubTriage and routing
A GitHub Action that reviews and classifies PRs with Jev alone.
wang2



GitHubTools and apps
Fish-style zsh autosuggestions, ranked by Jev instead of by prefix.
Malek Gara-Hellal

GitHubTools and apps
A private Mac voice diary: local transcription, Jev sorting, Notion library.
Abid A Gafoor
Sponsors

GitHubResearch and data
Offline Obsidian search, with an optional Jev rerank you approve first.
jh1373

GitHubResearch and data
An English–Icelandic dictionary with Jev reranking the results.
Jökull Sólberg Auðunsson

GitHubResearch and data
Systematic-review data from trial reports, every answer a verbatim quote.
Ahmad Sofi-Mahmudi

GitHubTrading and markets
A stock terminal: Valyu brings the evidence, Jev gives the status.
Prosper Otemuyiwa


GitHubGames and real time
A penalty shootout against Jev, on Render Workflows and Postgres.
Ojus M Save

GitHubGames and real time
A traffic simulation where Jev controls a whole city.
Siddhant Kuwar

GitHubGames and real time
A fire evacuation simulation with a Jev-style decision for each person.
Meteor Simulation

GitHubGames and real time
Jev can’t write a note, but with the right questions it improvises piano.
Paul

GitHubGames and real time
Jev picks the plan; code renders the sheet music, audio and MIDI.
Stephen Wu

GitHubTools and apps
A small React app where Jev guesses an age band from a name.
C.H Lee

GitHubAgents and browsers
Vercel’s open agent framework, with Jev as its default evaluate model.
Vercel

SkillTools and apps
The official skill for building with Jev, installable with one command.
TypeSafe AI
215

SkillTools and apps
A Rust CLI where Jev ranks agent skills for the next step.
Jeff Emanuel
44
SkillTools and apps
Routes which agent skill runs, with typed Jev decisions and confidence.
Dewaldt Huysamen

SkillTools and apps
An agent skill that sends a coding agent’s closed judgments to Jev.
HyunjunJeon

SkillTools and apps
Split a judgment into Choice, Score and Noul, lint it, then measure it.
Shingo Imota

SkillTools and apps
An agent skill for designing systems around Jev’s judgments.
Basit Mustafa

SkillTriage and routing
Deterministic model routing for coding agents, with a skill for Codex.
Instructa

SkillTools and apps
A skills framework for coding agents, with Jev gates and vetting.
Akash Priyadarshi

SkillTools and apps
A skill for writing and fixing programs that call Jev.
Drew Breunig
86
GitHubTools and apps
Jev picks which of your rules apply, so Claude only sees those.
Elia Alberti
Sponsors
Eugene Cheah - AI builder @ 🇸🇬|🇺🇸
@picocreator
love jev, but upset it - isn't open source? - it lack vision capability? We fixed all of that, introducing SimpleJev.ai A fully open source library which takes any HF model and Jev-ify it, with an API endpoint Now on github, and live in production at @FeatherlessAI
GitHubTools and apps

GitHubAgents and browsers
A mobile agent on a real Android phone, with Jev making each decision.
Droidrun
9 actions in ~21 s
SkillAgents and browsers
A Codex skill: Jev clicks, Codex thinks and checks the result.
coliney
~5–10×
GitHubAgents and browsers
A LinkedIn recruiting agent that browses profiles and saves the evidence.
skeptrune

GitHubAgents and browsers
A judgment layer that checks every Claude Code tool call against your policy.
Clownware
~$0.04/day
GitHubAgents and browsers
A gate on every agent tool call, with Jev as one of its sensors.
somoore

GitHubGames and real time
Pong where the ball moves one step per model decision. Jev against the LLMs.
Ably Labs

GitHubGames and real time
Jev plays real-time Tetris against Claude Haiku or Gemini Flash.
Tony Dinh

GitHubGames and real time
A solo mahjong coach: Jev picks the tile to discard. In Japanese.
smilior




GitHubTriage and routing
GitHub PR labels chosen by Jev, with size measured as scope, not lines.
Jeremy Huang


GitHubTools and apps
Cucumber tests from the .feature file alone. No step definitions.
Michael Poage

GitHubTools and apps
Semantic code search for coding agents, benchmarked on SWE-bench Lite.
Bently
82%

GitHubTools and apps
A context sieve for Claude Code: Jev judges each tool result before it lands.
Ghaleb Dweikat
~17

GitHubTools and apps
Classify first, read selectively: an agent plugin and MCP tool.
Kush Bhuwalka
~16Sponsors

GitHubTools and apps
A Pi extension: Jev picks the file excerpts, a local model writes the code.
Max Lv


GitHubTools and apps
A Rust CLI for Jev, with a linter that checks questions before you pay.
Ariel Frischer

GitHubContent and growth
A prose linter for AI writing tells: regex rules plus Jev for judgment.
Daniel Willoughby
~14
GitHubContent and growth
Writing checked on separate named axes, each with its own verdict.
TypeSafeAI (community)

GitHubContent and growth
A Chrome extension that blurs low-value LinkedIn posts.
sushrutb17

GitHubTriage and routing
The live Bluesky firehose, judged post by post, with a lane for humans.
Leo Mata
~$0.00003
GitHubTriage and routing
A Telegram bot that deletes only the spam Jev is sure about.
Nikita Kolmogorov

GitHubTriage and routing
Input moderation for Mastra agents in one file.
CodeAlive
~0.4 s
GitHubTrading and markets
Fed press conferences scored word by word, Jev against chat models.
SuperTurbo
~150 ms
GitHubResearch and data
Ask a question about every row in SQL, and get a real SQL type back.
Colliber


Guidegithub.com
Rajeeve Kuriakose’s runnable Jev examples, through OpenRouter, so you can start today.

GitHubResearch and data
Where Jev holds up and where it breaks, with real API receipts.
Zaious

GitHubTools and apps
A Chrome extension that files bookmarks by rules you write.
acorn181

GitHubTools and apps
A macOS utility that tells you which listening ports are safe to stop.
Epiphany Dynamics

GitHubTools and apps
An unofficial Laravel package for Jev, with typed responses and test fakes.
Alexey (Butochnikov)

GitHubTools and apps
A tiny Jev-like model on Qwen2.5-0.5B that trains and runs on a MacBook.
Jared Palmer
~160 ms
GitHubTools and apps
Typed, calibrated decisions from any open-weights model, on your own GPU.
ikermoel

GitHubTools and apps
An open 151M decision model on ModernBERT, with a WebGPU playground.
Hemant Kumar
Sponsors

Guidegithub.com
Official resources and community projects for TypeSafe, System One models and Jev.

Guidegithub.com
Public Jev projects, integrations and discussions, sorted by category.


Guidegithub.com
A source-backed project directory, with a GitHub review workflow that uses only Jev.

Guidegithub.com
OmniJev’s list of the papers, open reproductions and independent evaluations behind System One models.

Guidegithub.com
思维怪怪’s source-backed radar of the open-source ecosystem, in English, Chinese, Japanese and Korean.
Code you can read, fork and run. Each repo here calls Jev for a decision: which link to follow, which bucket a ticket goes in, which move to make. The figures on a card are the ones its author published.
109 builds and 10 guides