hermes-labs-ai/lintlang

142 stars · Last commit 2026-10-16

Static analysis for AI agent configs, tool descriptions, and system prompts — catches vague tool descriptions, missing stop conditions, and schema gaps before they reach runtime. Zero-LLM, deterministic checks, built for CI.

README preview

<div align="center">

# LintLang

<img src="assets/lintlang-header.jpg" alt="LintLang — catch agent failures before your agent runs" width="960">

**Catch agent failures before your agent runs.**

[![CI](https://github.com/hermes-labs-ai/lintlang/actions/workflows/ci.yml/badge.svg)](https://github.com/hermes-labs-ai/lintlang/actions/workflows/ci.yml)
[![PyPI](https://img.shields.io/pypi/v/lintlang)](https://pypi.org/project/lintlang/)
[![Downloads](https://img.shields.io/pypi/dm/lintlang?label=downloads%2Fmonth)](https://pypistats.org/packages/lintlang)
[![Python](https://img.shields.io/pypi/pyversions/lintlang)](https://pypi.org/project/lintlang/)
[![License](https://img.shields.io/pypi/l/lintlang)](LICENSE)
[![OpenSSF Scorecard](https://api.securityscorecards.dev/projects/github.com/hermes-labs-ai/lintlang/badge)](https://scorecard.dev/viewer/?uri=github.com/hermes-labs-ai/lintlang)

[Product page](https://lintlang.ai/) · [Playground](https://hermes-labs.ai/lintlang#playground) · [PyPI](https://pypi.org/project/lintlang/) · [Docs](llms-full.txt) · [简体中文](docs/zh-CN/README.md)

</div>

LintLang is a local, deterministic static linter for the instructions and tool interfaces an AI agent is given. It flags ambiguous tool choices, mixed output formats, schema gaps, missing bounds, and other setup defects before the agent runs.

View full repository on GitHub →