Jev by @typesafeai is now on OpenRouter, in beta. Jev is a System One model. Instead of generating text, it takes your app's state plus a typed question and returns a typed decision with a probability attached. There is no JSON prompting, parsing layer, and nothing to validate Show more
Jev MCP
An MCP server exposing ten Jev judgment tools, including verify, screen, find, rerank, classify, review, and gate, each returning typed probabilities in roughly 150 to 500 ms.
- Category
- Tools & Integrations
- Published by
- Community
- Author
- jkudish
- Added
- 2026-09-20
Tagscommunitytypescriptmcpcoding-agent
Highlights
- Ten tools cover claim verification, content screening, candidate finding, reranking, and classification.
- Typical latency is roughly 150 to 500 ms per judgment at a fraction of a cent.
- Provider keys can be TypeSafe direct, OpenRouter, or Vercel AI Gateway.
- Runs via npx with one-line setup for Claude Code, Codex, Amp, and OpenCode.
Watch out
Early software, and it needs Node 20 or newer plus a TypeSafe or OpenRouter API key.
More like this
An MCP server that puts Jev in the coding loop for Cursor, Codex, and other MCP clients: coding-loop checks, ranking, verification, and review tools.
Tools & Integrations#community#mcp#coding-agent
Communityjev-mcp
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.
Tools & Integrations#community#typescript#mcp
Communityjev-browser
From the community
Posts from builders shipping with Jev right now.
Jev lands on OpenRouter
700 leads scored for $0.09
JEV is INSANE. We gave it 700 high-intent leads and personalised outreach messages. In 40 seconds, it predicted how each message would perform, assigned a confidence score and detected lead-message mismatches. All for just $0.09. JEV can also score leads, analyse buying Show more