Mines corrections from your AI agent's chat logs to catch recurring drift and overclaiming before the next response ships. A cheap-to-expensive pre-flight gate — regex, then structured scoring, then a pressure probe — plus memory that carries past corrections into similar tasks. MIT, zero dependencies.
Latest release v0.1.12 — Hermeneutic 0.1.12 — native Gemini CLI response gate · 3 Sept 2026
2 files for Codex, OpenCode and Claude Code: hermeneutic AGENTS.md, hermeneutic CLAUDE.md — 1,091 tokens loaded in every session.
AGENTS.md A 740 tok CLAUDE.md A 351 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.