#4141st of 43 in Code review and testing
gentleman-guardian-angel
Git pre-commit hook that reviews staged files against AGENTS.md using any LLM
- Stars
- 1.2k
- License
- MIT
- Last commit
- Jul 2026
- Last release
- Jul 2026
- Language
- Shell
947 on 22 Apr 20261,212 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
GGA is a pure Bash CLI that installs a git pre-commit (or commit-msg) hook and sends staged files to an AI provider to check them against coding standards written in AGENTS.md. It supports hosted CLIs and APIs such as Claude, Gemini, Codex and GitHub Models, plus local Ollama and LM Studio. It also offers a CI mode, a full-PR review mode and a cache that skips unchanged files.
Who it is for: Teams wanting AI-enforced coding standards on every commit or PR
Strengths
- Pure Bash core; installs via Homebrew or install.sh, with no runtime framework
- Supports 11 providers, including local Ollama and LM Studio
- Caching skips unchanged files; --pr-mode reviews a whole PR and --ci the last commit
- Runs on macOS, Linux, Windows (Git Bash) and WSL; 266 tests reported
Weaknesses
- Each provider needs its own CLI or API account installed separately
- Review quality depends on how well AGENTS.md is written
- LLM review on every commit adds latency and may send code to third parties
- On Oh My Zsh, the git plugin's gga alias conflicts and needs unalias
What it needs
- no GPU
- Needs Bash 5.0+, git, an AI provider CLI or API (Claude, Gemini, Codex, Ollama, etc.)
- Models: Claude, Gemini, Codex, OpenCode, Cursor Agent
What changed
- v2.10.0 ↗ (opens in a new tab)Breaking
“No migration is required. Existing providers are unchanged. To use Kiro, set PROVIDER="kiro" in .gga or GGAPROVIDER=kiro in the environment.”
- v2.9.0 ↗ (opens in a new tab)Breaking
“Homebrew users can update with:”
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Code review and testing
See all 43| Rank | Project | Score |
|---|---|---|
| 1 | playwrightCross-browser automation and end-to-end test framework for Chromium, Firefox and WebKit | 94 out of 100 |
| 2 | nxMonorepo build system with task caching, affected-only runs and CI integration | 93 out of 100 |
| 3 | open-code-reviewGo CLI that reviews Git diffs with an LLM agent and line-level comments | 92 out of 100 |
| #4 | bendDependent-typed language where AI-written code must prove rules in LAWS.bend | 88 out of 100 |
| #5 | maestroYAML-based UI and end-to-end test framework for Android, iOS and web | 88 out of 100 |