Turn corrections from AI agent logs into guidance for similar tasks. Local memory with semantic retrieval, prompt-context hooks, and response checks.
Latest release v0.1.15 — Hermeneutic 0.1.15 — offline correction evidence with public evaluation · 20 Oct 2026
3 files for Codex, OpenCode and Claude Code: hermeneutic AGENTS.md, hermeneutic CLAUDE.md, hermeneutic — 1,663 tokens loaded in every session.
AGENTS.md A 1,312 tok CLAUDE.md A 351 tok .agents/skills/hermeneutic/SKILL.md A 73 tok These files are hermes-labs-ai/hermeneutic's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.