llms.txt git:20260712.b7088a5A

Immutable. This exact content is served forever at /api/v1/blob/0846b5c4f4bb17fc.

# hermeneutic

> Mine corrections from AI chat logs. Gate the next response.

hermeneutic is a Python library and CLI that mines `(prior_assistant, user_correction, next_assistant)` triples from chat logs and uses the patterns it finds to gate future assistant drafts. Three-stage pipeline: zero-LLM regex (cheap), optional hermes-rubric scoring (local LLM), generic LLM critic called PressureProbe (one API call). Repair pass runs once if the critic says revise.

The architecture decouples the *role* of a reviewer-twin (forces structured verdict + flip-condition) from the *priors* (whose judgment, what severity calibration). Ship the role publicly, keep your priors private. Default calibration is "rigorous-skeptic."

## Install

```
pip install hermeneutic
# pin: pip install "git+https://github.com/hermes-labs-ai/hermeneutic@v0.1.7"
```

## CLI

- `hermeneutic mine <dir> --out triples.jsonl` — extract correction triples from chat logs (Claude Code or OpenAI format).
- `hermeneutic bucket <triples.jsonl>` — surface-pattern bucket counts.
- `hermeneutic gate --draft <file>` — run regex-only gate. Exit 0 = pass, 1 = risk.

## Library

```python
from hermeneutic import Router, PressureProbe
probe = PressureProbe(judge=any_llm_callable)
router = Router(probe=probe, repairer=any_llm_repair_callable)
result = router.gate(request="...", draft="...")
```

## Empirical basis

Risk patterns derived from 326 corrections mined across 1,423 Claude Code sessions. Top drift mode (post-completion overclaiming) accounts for 44% of all corrections. Eight regex rules ship; the original six covered ~65% of the derivation corpus (eight-rule coverage not yet re-measured).

## Audit-stack siblings

- scaffold-lint — static analyzer for prompt scaffolds
- agent-convergence-scorer — multi-agent agreement scoring
- hermes-rubric — evidence-first structured scoring
- hermes-seal — signed attestation of agent policy versions

## Repository

https://github.com/hermes-labs-ai/hermeneutic

## License

MIT


## About Hermes Labs

Hermes Labs — Epistemic Engineering for the agent era: applied epistemology and hermeneutics as engineering discipline. The model is the substrate, language is the operations layer; reliability comes from linguistic infrastructure. hermeneutic is the stack's overclaim gate. More at https://hermes-labs.ai