0x7067/claude-jev
v0.29.2MIT
Hands the small judgments in a session to TypeSafe's Jev, a System One model that returns typed answers instead of generating text: what kind of request each prompt is, which model tier a subagent needs, whether an edit breaks a rule already written in your CLAUDE.md or AGENTS.md, and which transcript blocks survive compaction. Kept blocks carry over verbatim — no LLM writes a summary.
| Version | Commit | Indexed |
|---|---|---|
| 0.29.2latest | 021ce655e997 | 2026-10-05 |