Jev directory
CommunityJev Tools & CLIs
Jev Kit — leighefford
An npm package of Jev-powered tools you can run from the terminal, browser, Claude or ChatGPT. It ships Laugh Track, Steering Wheel, Semantic Bisect, Collision Engine and a jev_ask tool, all on your own Jev key.
- Stars
- 1
- Reading time
- 2 min
- Published by
- Community
- Added
- Oct 2026
This is one of several Jev listings for the same project. The canonical entry is Jev Kit — jonathanavis96.
Highlights
- Published on npm as @leighefford/jev-kit; unrelated to the separate jev-kit package.
- Laugh Track simulates 200 people reacting line by line to a speech, set or pitch.
- A 13-line wedding speech cost $0.00097 in Jev calls.
- Runs as an MCP server for Claude Code, Claude Desktop, Cursor, Windsurf, Zed and ChatGPT.
- The browser page serves at 127.0.0.1:4747 and only accepts requests from itself.
Questions about this entry
Short answers drawn from the linked project or page.
Either a Vercel AI Gateway key or a TypeSafe key from console.typesafe.ai/keys. Audio transcription needs a Vercel AI Gateway key; a TypeSafe key covers Jev calls only.
The browser page saves it to ~/.config/jev-kit/config.json, readable only by you. On a Mac you can keep it in the Keychain instead, or set AI_GATEWAY_API_KEY or TYPESAFE_API_KEY in the environment.
Run claude mcp add jev-kit -e AI_GATEWAY_API_KEY=your_key -- npx -y @leighefford/jev-kit. If the key is already in your Keychain, leave out the -e flag. Claude Desktop, Cursor, Windsurf and Zed use the same npx command.
MP3, M4A, WAV or WebM up to 24 MB, or a recording made straight from your microphone. Transcription runs through Vercel AI Gateway with openai/whisper-1 at about $0.006 per minute.
Run npx -y @leighefford/jev-kit serve --http --port 3333, put a tunnel such as cloudflared in front of it, then add the tunnel URL plus the printed secret path as a connector in ChatGPT developer mode.
Steering Wheel judges every sentence of a draft, Semantic Bisect is git bisect for bugs a test cannot catch, Anything-vs-Anything Physics is a common-sense rulebook, and Collision Engine scores pairs of notes for surprising and useful combinations.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Playwright CLI + Jev vs Playwright MCP
X: Text-to-screenshot (Malay Vasa)
X: Google's MediaPipe Decision Maker, tested in the browser
X: Jev in front of the HeyGen MCP
More Jev resources like this
A browser-use agent where Jev picks one action per step from a page's interactive elements. Runs as an MCP server, CLI, or library and returns a step trace, screenshot, and console errors.
Jev Tools & CLIs#community#typescript#mcp
Community
jkudish/jev-browserJavaScript
jkudish/jev-browserJavaScriptA TypeScript browser agent for ego lite that turns one natural-language goal into CLICK, TYPE_TEXT, or SELECT on a numbered element table, with Jev choosing the operation and target in one request.
Jev Tools & CLIs#community#typescript#browser
Community
romaluev/jev-egoTypeScript
romaluev/jev-egoTypeScriptA provider-neutral CLI, MCP server and Claude Code plugin that asks yes/no, pick-one, rate or rank questions about text and gets probabilities instead of paragraphs. Backends include Jev (TypeSafe or via OpenRouter), OpenAI's Decisions API, and Claude with an existing Claude Code login. MIT, Node 20+.
Jev Tools & CLIs#community#github#typescript
Community
adityajha2005/decisionkitTypeScript
adityajha2005/decisionkitTypeScriptA git host for agents where every push and pull request gets a typed Jev review, every branch move a signed certificate, and sites deploy from a repo.
Jev Tools & CLIsPlayground#community#playground#code-review
Community
An MCP server and agent skill that verifies coding-agent work by driving the real running app and returning pass, fail, or couldn't-tell verdicts with the file:line to fix; its listing frames the approach as Jev-style machine-native runtime perception.
Jev Tools & CLIs#community#typescript#mcp
Community
reticlehq/reticleTypeScript
reticlehq/reticleTypeScriptVercel Labs' terminal CLI for the AI SDK: its `ai evaluate` command answers named Boolean, Choice, and Score questions, with Jev as the default evaluation model and one unchanged input shared across all questions.
Jev Tools & CLIs#community#typescript#cli
Community
vercel-labs/ai-cliTypeScript
vercel-labs/ai-cliTypeScriptFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.