#1515th of 22 in Code review and testing
git-lrc
Git pre-commit hook that runs an AI review on each staged diff
- Stars
- 1.5k
- License
- custom license
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Go
443 on 3 Apr 20261,478 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
git-lrc is a Go CLI that hooks into git commit and sends the staged diff to an AI reviewer, then opens a local browser UI with inline comments, severity badges and risk-ranked hunks. Each commit gets a status line in the git log (ran, vouched or skipped, with iteration count and coverage). It uses the LiveReview service with a Gemini key by default, and also supports OpenAI, Claude, DeepSeek and OpenRouter keys.
Who it is for: Developers who want AI review of every commit, especially AI-written code
Strengths
- Triggers on git commit, so it works across editors and AI assistants
- Records review status, iterations and coverage in each commit's git log message
- Agent mode returns JSON non-interactively for coding agents and CI
- Supports BYOK connectors: OpenAI, Claude, DeepSeek, OpenRouter, Anthropic-compatible APIs
Weaknesses
- Setup needs a LiveReview account (Hexmos sign-in); review is not fully local
- Free tier capped at 30k LOC per month; paid plans beyond that
- Self-hosting, SSO and custom domains are Enterprise-only
- License is reported as NOASSERTION, so terms are unclear
What it needs
- no GPU
- Needs LiveReview account (Hexmos sign-in), Gemini API key or other AI provider key, codebase-memory-mcp (optional, auto-installed for risk scoring)
- Models: Gemini, OpenAI, Claude, DeepSeek, OpenRouter
Quick answers
Is git-lrc open source?
Its code is public on GitHub under its own license terms; read them before you use it at work.
Also in Code review and testing
See all 22| Rank | Project | Score |
|---|---|---|
| 1 | playwrightCross-browser automation and end-to-end test framework for Chromium, Firefox and WebKit | 94 out of 100 |
| 2 | open-code-reviewCLI that reviews Git diffs with an LLM agent and line-level comments | 91 out of 100 |
| 3 | react-doctorCLI that scans React codebases for state, performance, security and accessibility issues | 89 out of 100 |
| #4 | pr-agentLLM pull request reviewer that comments via /review, /describe and /improve | 86 out of 100 |
| #5 | e2eAI-driven end-to-end testing framework for web and mobile apps | 86 out of 100 |