Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to th
The best way for Claude Code, Codex, and pi to work with Jev: hand the tasks that need no text output to Jev — faster steps, fewer tokens, tasks done sooner and better.
It makes the LLM and Jev true collaborators: when content needs to be written, the LLM takes over; when a step just needs a fast decision, Jev executes it.
Directions task: Jev clicks, the LLM types — 10 decisions (p50 274 ms) · 4 writes; Jev rejects a wrong route, the LLM rewrites Context compaction — 200 messages judged in 7 calls, one LLM paragraph replaces the dropped pile; recall 3/3
Pong: ball speed = decision latency — 86 Jev decisions in 20 s vs 6 (haiku) and 3 (gemini) called the usual way; enum-constrain both and the gap is 3× Gate every shell command — dangerous ones denied in ~230 ms with a reason, zero LLM tokens
Every demo is a rerunnable script in bench/examples/; all numbers, methodology, variance and caveats: bench/RESULTS.md · third-party measurements: docs/evidence.md.
Set one key in the environment your agent runs in (JEVBACKEND=mock for a keyless dry run):
Provider Env var --- --- TypeSafe direct TYPESAFEAPIKEY OpenRouter OPENROUTERAPIKEY Vercel AI Gateway AIGATEWAYAPIKEY
npx -y jev-use doctor checks the wiring. Judged state goes to the provider you configure; JEVBACKEND=mock stays local. Plugin form with the routing skill and the PreToolUse gate: harness/claude-code · harness/codex.
npm i jev-use — zero runtime dependencies on the judgment path:
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/shitianfang--jev-use.html)
Fast, cheap, probability-scored decisions for coding agents, scripts and CI. CLI + MCP server + Claude Code plugin for the OpenAI Decisions API and Jev (TypeSafe AI).
MohammadHijjawi97/since-cutoffFind which APIs of your pinned Python dependencies changed after your coding model's training cutoff, and give the agent short AGENTS.md / CLAUDE.md notes from a static API diff. No model calls, no AP
abhishekswe/agent-fastpathJev MCP server: a decision layer for coding agents, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with ca
osaxyz/sepiaceLong-term memory for coding agents. The sepiace plugin for Claude Code and Codex.
noteflowai/dsh-skills-anywhereReuse Agent Skills across DeepSeek Harness and MCP. Check local SKILL.md files in the browser or CI, with parser diagnostics, file hashes and clear exit codes. Try the Hugging Face playground.
dongnguyenvie/bashcut-agent-kitBashCut's agent kit: editing skills (footage survey, beat cuts, audio mix, captions, colour, voiceover…) and the BashCut MCP server for Claude Code and Codex.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.