Auto-review code changes on git commit using external AI CLIs (Codex, Gemini CLI, etc.)
@agentproto/runtime-profile-standard — reference file-mode MultiAgentRuntime profile. Drops a Claude Code reviewer sub-agent, session-start + user-prompt-submit hooks, an `/ap-swarm` slash command, and an example local swarm manifest into a repo so `agent
AWS SDK for JavaScript Codeguru Reviewer Client for Node.js, Browser and React Native
Install Claude Code skills with one command — npx maryann-skills <skill-name>
A comprehensive framework for AI-assisted development with Claude Code. Install standardized rules, agents, and commands for your projects.
Use Claude Code as an external reviewer from Codex.
Core TypeScript SDK for Agent Relay communication. The SDK gives agents and applications three public capabilities: messaging, delivery, and actions.
Lightweight harness-first flow toolkit for coding agents
SDK for building AI agents with Claude Code's capabilities. Programmatically interact with Claude to build autonomous agents that can understand codebases, edit files, and execute workflows.
An iterative AI task execution framework. Orchestrates multi-phase autonomous work using Claude or Codex engines.
Use Claude, Anthropic's AI assistant, right from your terminal. Claude can understand your codebase, edit files, run terminal commands, and handle entire workflows for you.
Native binary for Claude Code on linux-x64
Production-ready AI agent orchestration platform with 66 specialized agents, 213 MCP tools, ReasoningBank learning memory, and autonomous multi-agent swarms. Built by @ruvnet with Claude Agent SDK, neural networks, memory persistence, GitHub integration,
Claude Code Sprint Gate — autonomous sprint lifecycle manager with pluggable scorecards. v8.3 introduces multi-agent mode foundation — master is the default role; /sprint-role slash command + role file mechanism + per-session NATO nickname auto-assignment
A CLI that orchestrates Claude Code agents to execute software engineering work items through TDD. Describe what to build; tap creates tickets and drives agents through RED → GREEN → REFACTOR until each task is completed.
Chinese-first Codex PR-first / plan-first implementation harness.
Coordinate AI coding agents in shared cubes. Works with Claude Code and Codex. Create projects, assign roles, and share a live activity log.
External web reviewer for Claude Code plan mode.
Reference implementation of the Cloverleaf methodology as Claude Code skills. Implements the Tight Loop (Implementer + Reviewer).
Native binary for Claude Code on win32-x64
Multi-agent orchestration MCP server. Claude orchestrates; GLM, Codex, and agy do the work.
Native binary for Claude Code on darwin-arm64
KERN MCP server — compile, review, and analyze .kern files via MCP
MCP server for Claude Code - Get second-opinion feedback from Codex/Gemini CLIs
PrReview collects PR data from GitHub (description, commits, comments, linked issues, and code changes) and formats it as XML. Paste this XML into any LLM like ChatGPT or Claude to get helpful code reviews.
A lightweight harness that keeps Claude Code working autonomously until success criteria are met. Supports any code review system (CodeRabbit, GitHub Copilot, etc.) and any CI provider. The loop: plan -> work -> check -> work -> check -> done
cangming-ai-dev-kit provides cross-agent development skills (plan-first, safe-code-change, code-review, verify-before-done), domain-specific knowledge (Flutter/Dart, HarmonyOS/ArkTS/ArkUI), and shell scripts. Install with `gem install` and use the CLI to sync skills to Claude Code or Codex.
A CLI wrapper around `rails new` that applies preset flags (-d postgresql -T --api --minimal), adds a curated set of gems (RSpec, RuboCop, factory_bot, Bullet, SimpleCov, test-prof), and bootstraps Claude Code slash commands for common development tasks (fix, lint, commit, review-pr, add-tests, code-coverage, docs, deliver).