Skip to main content

🤖 Gerrit Agent

AI-Powered Code Review Assistant for Gerrit

PyPI version License: MIT Python 3.10+

Transform your Gerrit code reviews with AI-powered analysis using Claude Code, Gemini CLI, and other advanced Code Agents.

Features • Quick Start • Usage • Documentation • Contributing


📖 Overview

Gerrit Agent is an AI-powered code review platform that integrates cutting-edge Code Agents (Claude Code, Gemini CLI, etc.) with Gerrit Code Review. It provides automated code analysis, intelligent inline comments, and multi-agent review workflows - all directly from your terminal.

Why Gerrit Agent?

  • 🧠 Multiple AI Agents: Use Claude, Gemini, or any Claude Agent Skill Protocol-compatible agent
  • 🎯 Smart Reviews: Multi-agent analysis with confidence scoring (only shows high-confidence findings ≥80%)
  • 💬 Inline Comments: Automatically posts structured feedback directly to Gerrit changes
  • ⚡ Fast CLI: Modern, GitHub CLI-like interface for Gerrit operations
  • 🔌 Extensible: Built on open protocols, works with any compatible Code Agent

✨ Features

🤖 AI Agent Integrations:

  • Claude Code Skill (multi-agent review, confidence scoring)
  • Gemini CLI Extension (natural language reviews)
  • Compatible with Claude Agent Skill Protocol

💻 CLI Operations: List, view, checkout, review changes • Inline comments • JSON/Table output

🛡️ Developer-Friendly: HTTP token auth • Rich terminal UI • .env config • Comprehensive tests


🚀 Quick Start

Install:

pip install gerrit-agent-skill

Configure:

export GERRIT_URL=https://gerrit.example.com
export GERRIT_USERNAME=your_username
export GERRIT_TOKEN=your_http_token

Verify:

gerrit --help

🎯 Usage Modes

🤖 Claude Code Skill

Multi-agent code review with confidence scoring.

# Install skill
claude --skill-dir /path/to/gerrit-agent-skill/skills/gerrit

# Use it
/gerrit:review 12345

Features: 3 specialized analyzers, confidence scoring (≥80%), user confirmation before posting.

📚 Full documentation →


🧠 Gemini CLI Extension

Natural language code reviews with "Principal Software Engineer" persona.

# Install
gemini extensions link https://github.com/madroidmaq/gerrit-agent-skill/gemini-cli-extensions

# Use it
gemini "Review change 12345"
gemini /gerrit:review 12345

📚 Full documentation →


💻 Standalone CLI

GitHub CLI-like experience for Gerrit operations.

# List changes
gerrit list --owner me --status open

# View change
gerrit show 12345 --diff

# Checkout and review
gerrit checkout 12345
gerrit review 12345 --code-review +2 -m "LGTM!"

📚 Full CLI reference →


📚 Documentation


🤝 Contributing

Contributions welcome! See Issues for planned features.

git clone https://github.com/madroidmaq/gerrit-agent-skill.git && cd gerrit-agent-skill
uv sync --extra dev && uv run pytest

📄 License

MIT License - see LICENSE file.


Built with Click, Rich, httpx, Pydantic

If you find this helpful, please ⭐ star the repo!

Report Bug • Request Feature

Metadata

Release files for gerrit-agent-skill 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for gerrit-agent-skill 0.1.0
File Size Uploaded Provenance
gerrit_agent_skill-0.1.0.tar.gz 81.2 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for gerrit-agent-skill 0.1.0
File Interpreter ABI Platform
gerrit_agent_skill-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 108.7 kB

Release files / gerrit_agent_skill-0.1.0.tar.gz

Download URL gerrit_agent_skill-0.1.0.tar.gz
Size 81.2 kB
Tags Source
SHA-256 checksum
How to use checksums
44ddcf21d0f3756cb8c96c772ddce501df0d1c8e0b5a757846d3c050d6fb2f39
BLAKE2b-256 checksum
How to use checksums
c11abe63a3dc1fbf5b4136b14dfca0978a47189a314be79cddb7cc043d222b12
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.9.7

Release files / gerrit_agent_skill-0.1.0-py3-none-any.whl

Download URL gerrit_agent_skill-0.1.0-py3-none-any.whl
Size 27.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
462e63b6285b449e06d08c6b0aadf5207014632bf776784161948f115c5eff04
BLAKE2b-256 checksum
How to use checksums
bad755498c3fb4a90e2df9f8597f4e83f8a66acb6658f8a79397ce008aec7294
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.9.7

Security for gerrit-agent-skill 0.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page