Skip to content
JevDirectory.orgTraffic count unavailable. View site traffic

Jev directory

Jev for Realtime control

225 curated Jev resources. Drive realtime, robotic, and simulation loops with per-step decisions.

By format

225
  • Docs5
  • Repos & sites177
  • Videos7
  • Posts6
  • Articles17
  • Playgrounds13

Updated

All 225 Jev AI model resources for Realtime control

Search the full list, or filter by category, format, and tag.

LessWrong: testing Jev as a trusted monitor for AI control
A LessWrong pilot testing Jev as a trusted monitor in the ControlArena APPS backdoor setting: one yes/no question reaches AUROC 0.976 and catches 90% of backdoors at a 2% false-positive rate for about $0.04 per thousand submissions.
Jev Guides & ArticlesArticle#community#press#security
Community
Connect AI Company v2 (RL Decider Teacher)
A PPO-trained reinforcement-learning decision brain for the CONNECT TYCOON company simulator from CONNECT AI LAB: it runs staffing, inventory, marketing, refund and security judgments and answers in the JEV request format with probabilities.
Jev Models & Reimplementations#community#open-models#reinforcement-learning
Community
Robo-Jev 2B
Steerix's robo-jev v0.7 merges a robotics LoRA into Qwen3.5-2B as a 2B System 1 that answers physical-judgment questions from a robot's scene; the card reports 0.81 physical judgment against TypeSafe Jev's 0.28.
Jev Models & Reimplementations#community#open-models#robotics
Community
decider-2b-vision
Mapika's vision decider: decider-2b v5 text weights transplanted into the Qwen3.5-2B vision-language model, tuned so an image plus a lettered question returns a calibrated probability at one answer slot with no generation. Breakout from pixels scores 41, above its teacher's 22.
Jev Models & Reimplementations#community#open-models#local
Community
JEVWeb
xiq's JEV-format view of OpenJev-Data: every browser step re-expressed as state, questions and gold across eight configs covering Mind2Web, NNetNav, WebChain, two teacher runs and on-policy GLM, plus a frozen 2,346-step bench and 153 live tasks. Licences are mixed and per-row terms apply.
Jev Benchmarks & EvaluationsDocs#community#evaluation#browser-agent
Community
Open-Jev Typed Decision Datasets (11-47)
Twelve frozen, mostly synthetic typed-decision configs from the independent Open-Jev project, published as redistributable parquet splits with manifests, raw records and reconstruction instructions; the card states these are not official TypeSafe training data.
Jev Benchmarks & EvaluationsDocs#community#evaluation#calibration
Community
6G-JEV (RANIntent v1)
RANIntent v1: an O-RAN intent-interpretation benchmark from UTS with 16 telemetry conditions, where an interpreter returns one A1 policy with 9 fields; 300 test and 60 dev cases per condition.
Jev Benchmarks & EvaluationsDocs#community#evaluation#telecom
Community
Yao Agents
8.1kGitHub stars
Self-hosted agent workspace platform from YaoApp that keeps all your agents and workspaces in one place across desktop, mobile, browser, or API, with Jev available inside it as TypeSafe AI's System One model for typed decisions with confidence.
Jev Agents & MCP#community#github#agents
Communityyaoapp/yaoGo
dsh-sieve
110GitHub stars
A context-engineering plugin for DeepSeek Harness that filters tool output, prunes older context and discloses skills progressively, cutting replay payloads by 36.28% in characters, and relies on Jev or Laya as its judge model.
Jev Integrations & Adapters#community#github#typescript
CommunitySev7eEn7/dsh-sieveTypeScript
NPCTalk
123GitHub stars
Makes NPCs in games talk back: skills, a self-hosted Fish Audio voice server and tools that let a coding agent wire up in-character dialogue, with TypeSafe Jev picking each NPC action and a full GTA V example.
Jev Agents & MCP#community#github#python
Communitychristos-antono/NPCTalkPython
JevAny
105GitHub stars
Open infrastructure from the SimpleJev project for training, evaluating and deploying System 1 decision models across language and multimodal backbones: one API takes a state, question and candidate options and returns a choice with probabilities.
Jev Repos & SDKs#community#github#python
CommunitySimpleJev/JevAnyPython
DriveJev
94GitHub stars
An open-source System I decision model for autonomous driving: DriveJev scores every offered driving behaviour with a probability instead of generating text, and the demo clips show it holding, yielding, and proceeding in the JevPilot simulator.
Jev Models & Reimplementations#community#github#autonomous-driving
Communitybenmagnifico/drivejevJavaScript
Multi-UAV JEV
54GitHub stars
A MuJoCo city simulation where one, two or four camera-observed drones pursue a target: each role asks Jev role-specific typed questions while deterministic mission navigation, safety guards and motor control run independently at 50 Hz.
Jev Demos & Experiments#community#github#python
CommunityYongLD/Multi-UAV-JEVPython
open-annie
41GitHub stars
An open-source browser 3D character split between two models: GPT-Live-1 talks with you over WebRTC while Jev reads the live transcript and picks Annie's face, gestures and body language in about 120 ms, with code gates on every answer.
Jev Demos & Experiments#community#github#python
Communityrehan-remade/open-anniePython
partway
32GitHub stars
Voice control for macOS from tostechbr that acts partway through your sentence: it asks Jev about every word and gets typed decisions back in about 200 ms, so Notes can open before you finish saying the command. It needs a Jev API key and Apple Silicon.
Jev Tools & CLIs#community#github#macos
Communitytostechbr/partwaySwift
Flick
27GitHub stars
A local stdio MCP server from bgivenb that runs whole browser and macOS goals for your agent: your agent supplies the goal, exact values, and completion conditions, and Flick loops observe, decide, and act with TypeSafe Jev. TypeScript core with Playwright and Swift drivers.
Jev Agents & MCP#community#github#mcp
Communitybgivenb/flick-computer-useTypeScript
Jev Cookbook
24GitHub stars
A community curriculum of Jupyter notebook recipes that teach typed decisions with Jev, TypeSafe's System One model. Each recipe takes one bounded Choice, Noul or Score decision over text or image state, spanning first classification through closed-loop control.
Jev Cookbooks#community#github#python
Communityjev-engineering/cookbookJupyter Notebook
Jev Phone
11GitHub stars
A Jev-powered multimodal mobile automation SDK: a standalone Python tap SDK for Android, iOS and HarmonyOS where you hand over a tap target and the SDK locates and executes it on the current screen, with millisecond-level local processing.
Jev Repos & SDKs#community#github#mobile
Communitydongxinsuperman/jev-phonePython
jevman
7GitHub stars
Pac-Man where the characters are driven by System One decision models: TypeSafe's jev (typesafe/jev-1.13.0, the default) and others Opper serves, with the model's odds drawn on the board and a leaderboard benchmark.
Jev Demos & Experiments#community#github#typescript
Communityjoch/jevmanTypeScript
River Oaks District
6GitHub stars
An inhabited science-fantasy take on Houston's River Oaks District with mapped streets, boutiques and residents: NPCs powered by Jev per the repository description. Play as Jevica in third person, fly her bubble, and use Camera mode to compose and share photos.
Jev Demos & Experiments#community#github#javascript
Communitybunsdev/river-oaksJavaScript
Veyra
6GitHub stars
An autonomous, provider-neutral trading service in Rust: LLM and Jev structured judgements pass a deterministic risk gate before any MetaTrader 4 order, with durable risk logic and reconciliation in Postgres and a web console for operators. Licence listed as NOASSERTION.
Jev Tools & CLIs#community#github#rust
Communityiamngoni/veyraRust
tinycomputer
6GitHub stars
A Rust harness for desktop and browser automation where every choice about what to press comes from Jev: the decision model answers small closed questions about the screen while plain Rust reads the screen as named buttons and fields, acts, verifies and enforces the safety rules. It stops before money moves.
Jev Agents & MCP#community#github#rust
Communitytinyhumansai/tinycomputerRust
Heliotrope
5GitHub stars
A carbon-aware load scheduler that shifts deferrable electricity loads (EV charging, water heating, laundry, cooling) into the cleanest grid hours without missing a deadline. Jev classifies loads and ranks which matters first; OR-Tools CP-SAT keeps deadlines and physics hard while carbon is the objective.
Jev Tools & CLIs#community#github#python
Communitystellariex/heliotropePython
andy-harness
5GitHub stars
A plugin-based agent harness (FastAPI + Vue 3) bundling a chat GUI, multi-provider model access, an MCP client and marketplace, skills, workflow studio, sandboxed execution and a Tauri desktop shell. It integrates TypeSafe AI's Jev for structured Choice, Score and Noul decisions.
Jev Agents & MCP#community#github#agents
Communityandyqiuqiubo/andy-harnessTypeScript
JEV Orchestrator
5GitHub stars
A Claude Code plugin that sends every Agent spawn through JEV (TypeSafe), which picks the model (haiku, sonnet, opus), the effort and the tool profile of each subagent. It fails open to sonnet at medium effort, accepts a TypeSafe or OpenRouter key, and ships plan and run skills.
Jev Agents & MCP#community#github#claude-code
Communityhiyoku/jev-orcTypeScript
jevcraft
5GitHub stars
A mineflayer-based Minecraft bot whose decisions are made entirely by TypeSafe's Jev System One model: code lists the legal actions and Jev picks one in about 0.2 seconds for roughly 1.7 cents per bot-hour. Fifteen of 40 fresh worlds reached the Nether; none has beaten the game.
Jev Demos & Experiments#community#github#minecraft
Communitymrubens/jevcraftJavaScript
jev-box-tracking
5GitHub stars
A Python library and CLI that tracks objects in real time by combining TypeSafe Jev Box questions with sparse optical flow and a Kalman filter. Jev supplies absolute positions, flow updates velocity every frame, and a history buffer rewinds the filter to the frame each answer describes.
Jev Repos & SDKs#community#github#python
CommunityBenCaunt/jev-box-trackingPython
JEV AgentNetwork
4GitHub stars
An event-driven multi-agent network where JEV observes live state and assigns pending work to available agents. Its AgentRouter reference implementation routes on every completion event instead of waiting for a round to end, while general-purpose agents with OpenAI Responses API tools execute work concurrently.
Jev Agents & MCP#community#github#agents
CommunityKelly-Leeee/AgentNetwork-jevPython
GenClass
4GitHub stars
A 32M-parameter typed-decision model plus a Chrome extension that runs entirely on-device with WebGPU/WASM and Moonshine speech recognition. Its local server speaks POST /v1/systemone, so existing Jev clients work by changing the base URL; a benchmark table claims zero option-order flips.
Jev Tools & CLIs#community#github#chrome-extension
CommunityMeharPro/GenClassPython
brojev
4GitHub stars
A fast browser agent plugin for Claude Code written in Go: it drives Chrome through its own raw DevTools Protocol engine with no Playwright, and TypeSafe's Jev, reached through OpenRouter, picks each operation and target in a single request.
Jev Agents & MCP#community#github#browser
Communitybarockok/brojevGo
pi-mast-steer
4GitHub stars
A Pi extension that watches a coding agent's transcript for five common failure modes, including loops, drift and broken requirements, and nudges the agent when it sees one. TypeSafe's Jev, a classifier model, judges the transcript rather than an LLM.
Jev Agents & MCP#community#github#pi
Communitydbreunig/pi-mast-steerTypeScript
Jev plays Factorio
4GitHub stars
A Python experiment that lets TypeSafe's Jev play Factorio from screenshots alone: each tick the vision model looks at the screen, decides, and presses keys or moves the mouse, aiming to craft 10 automation science packs from a fresh freeplay game.
Jev Demos & Experiments#community#github#factorio
Communitykgaspard/jev-factorioPython
jev-shorts-editor
4GitHub stars
A skill that turns a talking-head video into a finished 1080x1920 vertical short with one command: it cuts retakes and dead air, reframes the speaker and adds animated captions, graphic cards, zooms, transitions and sound effects. Every edit decision is a Jev call.
Jev Agents & MCP#community#github#video
Communitymisbahsy/jev-shorts-editorTypeScript
mario-decisions-agent
4GitHub stars
A Super Mario Bros agent whose only brain is a remote vision model on the other side of an API: screenshots in, button out, and no memory peeking. It runs on the OpenAI Decisions API by default and supports TypeSafe's Jev (jev-preview) as an alternative.
Jev Demos & Experiments#community#github#mario
Communityparjanyaacoder/mario-decisions-agentPython
Jev Agent Control
3GitHub stars
An OpenCode V2 server plugin that uses Jev to route requests between the Plan, Build and your own primary agents, and hand off unfinished work at completed execution boundaries while following each target agent's configured model.
Jev Integrations & Adapters#community#github#typescript
Communitykrzysztof-cieslak/jev-agent-controlTypeScript
Jev Factorio Agent
4GitHub stars
An experimental Factorio agent in which Jev chooses goals and actions as typed questions while deterministic code owns the game rules and actuation; an offline mock loop runs with no API key and no game copy, with live and hierarchical modes documented.
Jev Agents & MCP#community#github#python
Communitycompletedottech/jev-factorio-agentPython
jev-effort
3GitHub stars
A Claude Code mod that sends each prompt to Jev through OpenRouter and turns the returned 0-3 score into a reasoning effort level, from low to xhigh. Shadow mode is on by default, so it only logs what it would set until you turn it off.
Jev Integrations & Adapters#community#github#claude-code
Communitygebeer/jev-effortTypeScript
jev-ios-bridge
3GitHub stars
A bridge and Claude Code plugin that runs scripts of taps, typing and swipes on iOS simulators or Android devices and has Jev judge each checkpoint's screen text, returning passed, failed or inconclusive with screenshots and a log. Saved scripts rerun from the terminal with no Claude in the loop.
Jev Integrations & Adapters#community#github#ios
Communityhugues-vnsgn/jev-ios-bridgeTypeScript
dsh-set-model
3GitHub stars
A DeepSeek Harness plugin that lets the agent switch model presets and thinking depth on its own, either with the set_model and switch_preset tools or through Jev, which reads each turn's instruction and picks a tier. Jev auto-switching is a separate switch, off by default.
Jev Integrations & Adapters#community#github#deepseek
Communityjohn-walks-slow/dsh-set-modelTypeScript
Intelliwright
3GitHub stars
A Playwright-based end-to-end test runner for web apps where Jev powers plain-English assertions, actions by description, goal-driven runs and failure triage. Its API mirrors Playwright Test, with test, expect, fixtures and page objects, and every Jev feature is optional.
Jev Tools & CLIs#community#github#testing
Communityneeraj719714/intelliwrightTypeScript
jev-max
3GitHub stars
A Jev browser agent that breaks the three walls of shadow DOM, iframes and canvas: a piercing snapshot, vision-grounded fallback clicks, uploads, drag-and-drop and multi-tab, all driven by one Jev request per cycle. It ships as a Python library and an MCP server.
Jev Agents & MCP#community#github#browser
Communitysaloni-garg/jev-maxPython
Jev on SMAC
3GitHub stars
A four-step experiment asking whether Jev, a fast model that picks among named options, can act as the policy in StarCraft multi-agent micro (SMAC), comparing every step against baselines that had the same information but no Jev.
Jev Benchmarks & Evaluations#community#github#benchmark
Communitywang90063/jev-on-smacPython
reflex-cu
2GitHub stars
An open-source computer-use MCP server for Claude Code, Codex and other agents that reads the accessibility tree instead of screenshotting every step, using Jev as a fast judge and, experimentally, as image input to spot icons and game objects.
Jev Agents & MCP#community#github#mcp
Community8itlab/reflex-cuPython
systemone-gridworld
2GitHub stars
A deterministic gridworld that benchmarks System One decision backends, typed calibrated decisions over a declared option set with one forward pass and no decoding, in a sequential loop, with a scripted oracle scoring agreement without labels.
Jev Benchmarks & Evaluations#community#github#benchmark
Communitylovelacemadeline/systemone-gridworldPython
jeva
1GitHub stars
A self-trainable 2B browser-agent decision model that speaks TypeSafe's /v1/systemone protocol, so an existing jev-ultrafast agent is repointed with a one-line base-URL change. Runs as a 1.6 GB Q4_K_M GGUF under llama.cpp at about 236 ms per decision.
Jev Models & Reimplementations#community#github#python
Communitychemany/jevaPython
systemone-drone
1GitHub stars
A browser playground where N drones fly on one shared 16x11 grid, each controlled by a System One decision model through OpenRouter. Mock mode runs with no key, and every rule number is editable in the panel without code changes.
Jev Demos & Experiments#community#github#javascript
Communitywnoronha/systemone-droneJavaScript
Nudge for Omarchy
0GitHub stars
An Omarchy launcher where you describe what you need and JEV routes it to a reviewed safe operation, settings panel or keyboard shortcut from a live command catalogue. Clear matches run; Preview only shows the plan.
Jev Tools & CLIs#community#github#python
CommunityCozidian/omarchy-jevPython
AmberFlow
0GitHub stars
A frozen-plan browser automation middleware for TypeScript and Node 22.6+: an LLM plans once, local rules and decision models execute step by step, and after one demonstrated run it can repeat the plan offline.
Jev Integrations & Adapters#community#github#automation
CommunityJohnly1986/AmberFlowTypeScript

Start here with the Jev AI model

Featured entries for realtime control.

Cua
30kGitHub stars
The Cua computer-use platform documents a jev-use recipe where TypeSafe Jev picks bounded action IDs and Cua Driver executes clicks and fills in the browser.
Jev Demos & Experiments#community#browser#computer-use
Communitytrycua/cuaRust

Jev AI model articles

Original guides that go deeper on Jev realtime control.

All Jev articles
Voice and real-time decisions: turn detection and intent
Voice agents need decisions in milliseconds. How turn detection, intent, and escalation work in real time, and where a fast decision layer fits.
Jev Practices & Patterns#voice#realtime#agents
Read article
Robotics and industrial control: perception-to-action gates
Perception-to-action gates are safety-critical decisions. How robotics projects use decision models and where deterministic control still wins.
Jev Demos & Experiments#robotics#control#safety
Read article
OpenRouter and multi-provider routing for decision models
One key, many providers: how decision models fit OpenRouter's routing, what the response shapes look like, and where fallbacks belong.
Jev Integrations & Adapters#integrations#openrouter#routing
Read article

From the Jev community

Watch walkthroughs, read the threads, and see what builders are posting.

YouTube: Maximilian Schwarzmüller on the new kind of model that beats LLMs in the areas it was built for.

YouTube: Albert Olgaard tests Jev and explains why System One models matter.

YouTube: Hunter Bohm on pricing, parallel decisions, whether Jev is actually new, and his own Astra plus Jev benchmark.

Hacker News: Thread on Selmar's Jev code-review calibration notes and ordering.py comparisons.

Lectem2 pointsCalibrating Jev as a Code ReviewerRead the thread on Hacker News

Hacker News: Qualitative researchers classifying participant free text with Jev at negligible cost.

effisfor13 pointsI was impressed by Jev, please explain why I shouldn't beRead the thread on Hacker News

Hacker News: Show HN for public Minecraft PvP where a diffusion LM picks moves from structured state.

2 pointsShow HN: Minecraft PvP against DiffusionGemma-as-Jev, 24 ms per decisionRead the thread on Hacker News

Hacker News: A one-token logprob wrapper that also classifies webcam frames.

allanrbo151 pointsA single function Jev-like wrapper for LLMs, including vision modelsRead the thread on Hacker News

Follow @typesafeai