Open-source projects built on TypeSafe's Jev decision model, security-graded: the jev-ultrafast browser agent, openjev, fast-jev-compaction, Jev code review tools and MCP servers. Vet before you install.
TypeSafe Jev tools are AI-powered software designed to help developers and teams tackle typesafe jev-related tasks more efficiently. These tools are typically published as open-source projects on GitHub and can be integrated into existing workflows via MCP (Model Context Protocol), Claude Skills, or standalone agent frameworks. On Agent Skills Hub, we index 68 quality-scored typesafe jev tools across languages including Python, TypeScript, JavaScript.
In 2026, the AI agent ecosystem is maturing rapidly. TypeSafe Jev tools can significantly boost development efficiency by automating repetitive tasks, reducing human error, and providing intelligent suggestions. The top 3 tools — jev-ultrafast, openjev, fast-jev-compaction — have earned an average of 632 GitHub stars, reflecting strong community validation. 50 of the listed tools come with clear open-source licenses, ensuring freedom to use and modify.
When choosing a typesafe jev tool, consider these factors: 1) Community activity — GitHub stars and recent commit frequency indicate reliability; 2) Integration method — check if it supports MCP, Claude, or your preferred agent framework; 3) Language compatibility — the most common language in this list is Python; 4) Quality score — Agent Skills Hub's composite score evaluates code quality, documentation completeness, and maintenance activity. Our recommendation: start with jev-ultrafast — it ranks highest in both star count and quality score.
Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.
Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.
Open-source AI Trading OS, agent trading, and vibe trading, with Jev System One integration. Research, build Python strategies, backtest, and paper/live trade across crypto, stocks, and forex. Launch your own multi-tenant trading SaaS with built-in user management, billing, payments, and settlement.
Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.
tiny Jev-like model built on top of Qwen2.5-0.5B you can train and run on your MacBook
AI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.
VexJoy AI Agent with Jev Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with reviews, tests, and a learning loop.
Software factory foreman based on TypeSafe's Jev model
A staged code-review workflow and local dashboard built with TypeSafe Jev.
Turn any open model into a classifier/jev endpoint
A TypeSafe/Jev agent that plays Super Mario Bros. from structured emulator state.
```powershell
py -3.13 -m venv .venv
.venv\Scripts\python -m pip install -e ".[mario,dev]"
$env:TYPESAFE_API_KEY = "your-key"
```
Tax document page classifier built on Jev decisions. 100% strict accuracy across 261 IRS forms, ~$0.001 per page.
Search the web with TypeSafe's Jev: source selection, query understanding and relevance ranking. Built with Search1API.
Route to the cheapest model in claude code for your task using jev-router
Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev.
5–10x faster browser operations: Jev clicks, Codex thinks and verifies. Built at EZCollegeApp.
One CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain, Jev for cheaper steps. Microduck, Open Duck Mini, LeRobot, XLeRobot, AlohaMini, ToddlerBot or any ROS base. Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM. Simulator, .duck safety contracts, MCP, memory between runs, flocks.
Jev-compatible API endpoint based on open models (prefill-only)
Self-hosted, versioned skills library for AI agents. MCP, scoped clients, and optional Jev recommendations.
Build calibrated AI classifiers from human feedback using Jev and GEPA.
```shell
uv tool install jev-align
export TYPESAFE_API_KEY="..." # Or use Vercel or Cloudflare below
export OPENAI_API_KEY="..." # or ANTHROPIC_API_KEY / GEMINI_API_KEY
jeva
```
Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.
Open, Jev-compatible System One decision server on DiffusionGemma
An educational Jev-like visual inference experiment on Apple Silicon: shared context, direct candidate scoring, and local visual demos.
Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)
A self-hosted drop-in replacement for TypeSafe's jev, powered by GliFormer.
WXT browser extension: Jev-powered page clutter removal with reusable template rules.
Control a real browser by voice. Jev (TypeSafe System One) decides intent + target in ~300 ms per spoken word; Playwright acts — often before you finish the sentence.
Fast, cheap, typed judgments from TypeSafe's Jev model, as MCP tools.
Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)
mcp connector to give your AI agent direct access to typesafe ai's jev model
Astra planner and JEV controller for Minecraft, with native recording, tested routes, and run verification.
A skill for writing and improving programs that call Jev, TypeSafe's System One model
```
/plugin marketplace add dbreunig/building-with-jev-skill
/plugin install jev@building-with-jev
```
Claude Code plugin: trim long Bash output with TypeSafe Jev before the model sees it
grep by meaning, across languages. TypeSafe Jev scores every line against a meaning; combine meanings with AND/OR/NOT. 意味で探す grep。日本語で英語を、英語で日本語を検索できる
TypeSafe Jev as a decision layer for the Pi coding agent: a measured tool-call gate plus jev_ask for typed, calibrated answers
```bash
pi install npm:@y0usaf/pi-jev
```
A playable Three.js driving simulator with Jev-powered autopilot
A lightweight Jev-powered router for models, tools, and subagents
Guardrails for Pi built on pi-typesafe that steer the agent instead of interrupting you: Jev judges irreversible and off-task tool calls, detects stuck loops, checks unverified done claims, flags slop
Bounded TypeSafe Jev workflows for coding agents.
A small, type-safe client for asking AI questions about your data, powered by TypeSafe Jev.
```sh
npx nypm i advocaat
```
Rust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks, structured JSON, abstention, and local feedback. Requires a TypeSafe API key.
Camera-only autonomous drone in MuJoCo with a small judgment model (TypeSafe Jev) in the loop at 2.5Hz
A small open decision model: state + typed questions -> calibrated probabilities. A Jev / System One re-creation on Qwen3.5.
Per-turn model & reasoning routing for Codex, driven by Jev (TypeSafe System One): picks the model, thinking depth and speed mode for every turn.
The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.
Detect youtube sponsor segment with live audio and transcript powered by Jev
Put a live Jev (TypeSafe) meter on any video: every sentence scored, rendered as a 16:9 edit
Fish-style zsh history autosuggestions ranked by Jev (TypeSafe)
```sh
git clone <this repo> ~/.zsh/jev-shell-history
cd ~/.zsh/jev-shell-history && npm install
```
EmbodiedJev: MuJoCo robot decision workbench with MiniCPM5-2B, Jev and compatible model APIs
An awesome collection of Jev use cases, workflows, and agent skills.
```bash
npm install -g jev-gateway
```
🧹 Fun project: a Chrome extension that asks a tiny AI decision model (TypeSafe Jev) "is this DOM element an ad?" and pops it off the page. BYOK, no backend, not a real ad blocker.
Jev-powered element selection for your agent’s existing computer-use tools
CLI that picks Cursor, Claude Code, Codex, or OpenCode + model/effort for a task, then launches it. Powered by Jev and Herdr
Say it, and your Mac does it. A computer-use harness on Jev that reads the screen through Accessibility. Fast, no vision model
```sh
bash build.sh
open "$HOME/Applications/Desktop Voice.app"
```
| Tool | Stars | Language | License | Score |
|---|---|---|---|---|
| jev-ultrafast | ★ 10.6k | Python | MIT | 78 |
| openjev | ★ 1.4k | Python | MIT | 70 |
| fast-jev-compaction | ★ 4.7k | TypeScript | MIT | 84 |
| typesafe-computer-use | ★ 573 | Python | MIT | 71 |
| QuantDinger | ★ 11.8k | Python | Apache-2.0 | 74 |
| SemIf | ★ 2.2k | Python | MIT | 69 |
| jevlike | ★ 1.0k | Python | MIT | 63 |
| kev | ★ 743 | Python | Apache-2.0 | 72 |
| reticle | ★ 730 | TypeScript | — | 66 |
| Jev-cu | ★ 426 | JavaScript | — | 64 |
| vexjoy-agent | ★ 421 | Python | MIT | 73 |
| foreman | ★ 417 | Python | MIT | 66 |
| jev-review | ★ 388 | TypeScript | MIT | 70 |
| simple-jev | ★ 348 | Python | — | 61 |
| jev-experiments | ★ 324 | TypeScript | — | 45 |
| typesafe-mario | ★ 293 | Python | — | 66 |
| tax-doc-classifier | ★ 288 | TypeScript | Apache-2.0 | 73 |
| jev-search | ★ 270 | TypeScript | MIT | 71 |
| mobile-jev | ★ 260 | JavaScript | MIT | 60 |
| jev-router | ★ 235 | JavaScript | MIT | 66 |
| pg-jev | ★ 233 | Shell | — | 69 |
| jev-browser-use | ★ 228 | JavaScript | MIT | 65 |
| quackd | ★ 212 | Python | Apache-2.0 | 61 |
| openjev-sglang | ★ 209 | Python | — | 69 |
| skillbox | ★ 208 | TypeScript | MIT | 68 |
| jev-align | ★ 205 | Python | Apache-2.0 | 65 |
| jev-review | ★ 177 | TypeScript | MIT | 68 |
| jev-browser | ★ 168 | TypeScript | MIT | 61 |
| openjev | ★ 168 | Python | Apache-2.0 | 64 |
| jev-visual | ★ 163 | Python | MIT | 70 |
| perch | ★ 162 | JavaScript | MIT | 60 |
| hermes-jev-skills | ★ 158 | Python | MIT | 66 |
| jeff | ★ 148 | Python | MIT | 74 |
| unclutter | ★ 141 | TypeScript | MIT | 65 |
| jev-voice-browser | ★ 141 | JavaScript | MIT | 64 |
| jev-mcp | ★ 140 | TypeScript | MIT | 72 |
| openJev-verdict-2.0 | ★ 133 | Python | — | 69 |
| typesafe-mcp | ★ 127 | Go | MIT | 75 |
| minecraft-agent | ★ 127 | JavaScript | — | 59 |
| building-with-jev-skill | ★ 123 | — | — | 70 |
| jev-pruner | ★ 121 | TypeScript | MIT | 62 |
| jev-semgrep | ★ 107 | JavaScript | — | 70 |
| pi-jev | ★ 106 | TypeScript | MIT | 70 |
| jevpilot | ★ 106 | JavaScript | — | 64 |
| JevRouter | ★ 102 | TypeScript | MIT | 64 |
| pi-warden | ★ 100 | TypeScript | MIT | 71 |
| Jev-X-Sentiment-Analysis | ★ 100 | Python | — | 62 |
| jev-eval-agent | ★ 96 | HTML | — | 60 |
| stanley-code | ★ 87 | TypeScript | MIT | 64 |
| advocaat | ★ 85 | TypeScript | MIT | 70 |
| skillranker | ★ 83 | Rust | — | 66 |
| jev-drone | ★ 83 | Python | MIT | 60 |
| reflex | ★ 82 | Python | MIT | 61 |
| jev-codex-router | ★ 80 | Python | MIT | 73 |
| von | ★ 78 | Python | Apache-2.0 | 59 |
| youtube-sponsor-detection | ★ 75 | JavaScript | — | 69 |
| jevmeter | ★ 72 | Python | MIT | 55 |
| jev-shell-history | ★ 68 | TypeScript | — | 59 |
| embodied-jev | ★ 67 | Python | MIT | 54 |
| jev-skill | ★ 64 | Python | MIT | 67 |
| open-jev | ★ 63 | Python | — | 56 |
| jev-gateway | ★ 62 | TypeScript | MIT | 62 |
| typesafe-adblock | ★ 58 | JavaScript | MIT | 64 |
| jev-browser | ★ 56 | JavaScript | MIT | 72 |
| save-token-jev-clean | ★ 56 | TypeScript | MIT | 65 |
| jev-chat | ★ 56 | TypeScript | MIT | 74 |
| agent-router | ★ 52 | TypeScript | MIT | 68 |
| jev-use | ★ 51 | Swift | MIT | 72 |
The top typesafe jev tools in 2026 are jev-ultrafast, openjev, fast-jev-compaction. Agent Skills Hub ranks 68 options by GitHub stars, quality score (6 dimensions including completeness, examples, and agent readiness), and recent activity. The list is rebuilt every 8 hours from live GitHub data.
jev-ultrafast (10.6k stars) is the most adopted choice for general typesafe jev workflows, written in Python. openjev (1.4k stars) is a strong alternative. Pick by your existing stack: match the language and runtime your team already uses to minimize integration cost. If unsure, start with jev-ultrafast — it has the deepest community and the most examples online.
Avoid pre-built typesafe jev tools when (1) your use case requires deep customization that the tool's plugin system doesn't support, (2) you have strict compliance requirements that ban third-party dependencies, (3) the tool's maintenance is inactive (last commit >6 months ago), or (4) your data volume is small enough that a 50-line custom script is cheaper than learning the tool. For most production workflows above 100 requests/day, the time savings from a maintained tool outweigh the customization loss.
TypeSafe Jev focuses specifically on open-source projects built on typesafe's jev decision model, security-graded: the jev-ultrafast browser agent, openjev, fast-jev-compaction, jev code review tools and mcp servers. vet before you install. browser-use, Playwright MCP & AI Browser Agents is a related but distinct category — see https://agentskillshub.top/best/browser-automation/ for those tools. The two often appear in the same agent pipeline but solve different problems: choose typesafe jev when your primary goal is the specific task, and browser-use, playwright mcp & ai browser agents when the workflow is broader.
For most teams, yes. jev-ultrafast has 10.6k stars worth of community testing, handles edge cases you haven't thought of, and ships with documentation. Build your own only when (1) your requirements are deeply non-standard, (2) you have a security/compliance reason to avoid OSS dependencies, or (3) the maintenance burden is small enough (<200 lines of code) that you'll save time long-term. The break-even point is usually around 2-3 weeks of dev time saved.
Most typesafe jev tools listed are open source under permissive licenses (MIT, Apache 2.0). A handful offer paid managed/cloud versions on top of free self-hosted core. Always check the LICENSE file on each tool's GitHub repository before commercial use — some use AGPL or non-commercial restrictions that may not fit your deployment model.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: