Submit a project
jev-use
By shitianfang
Source description: 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 the LLM
Repository description
The repository describes its purpose as: 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 the LLM
Source evidence
The daily check found an explicit Jev / TypeSafe AI connection in the original README and implementation files at the same commit.
The best way for Claude Code, Codex, and [pi](https://github.com/badlogic/pi-mono) to work with [Jev](https://typesafe.ai/blog/introducing-system-one-models-and-jev): hand the tasks that need no text output to Jev — faster steps, fewer tokens, tasks done sooner and better.
Automatically source-checked: public repository, pinned README, and implementation files. Not run, benchmarked or security-audited.
