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.
Instructions file CodexOpenCode
AGENTS.md instructions for hermes-labs-ai/hermeneutic, covering agents.md — using hermeneutic from a coding agent, what this tool does, when to invoke it, programmatic use and calibration.
Instructions file Claude Code
Claude Code instructions for hermes-labs-ai/hermeneutic: Read AGENTS.md first — it is the canonical in-session protocol for coding agents using or modifying this repo, and everything there applies to Claude Code sessions too.