GitHub Open Source Insight
Computed at Sep 11, 2026GitHub repo leaderboard by stars, growth rate and activity.
tirth8205
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Python31,293 starslast pushed 2 weeks agoovity
alibaba
Fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
Go22,163 starslast pushed Yesterdaymillionco
Your agent writes bad React. This catches it
TypeScript14,808 starslast pushed 2 days agoThe-PR-Agent
🚀 PR Agent: The Original Open-Source PR Reviewer. This project is not the Qodo free tier.
Python12,924 starslast pushed Yesterdayreviewdog
🐶 Automated code review tool integrated with any code analysis tools regardless of programming language
Go9,571 starslast pushed Yesterdaymodem-dev
Review-first terminal diff viewer for agentic coders
TypeScript9,201 starslast pushed Yesterdaybacknotprop
Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.
TypeScript8,580 starslast pushed YesterdayjnMetaCode
🦸 AI 编程超能力 · 中文增强版 — superpowers（250k+ ⭐）完整汉化 + 4 个中国原创 skills，让 Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemini CLI / Qoder 等 26 款 AI 编程工具真正会干活
JavaScript8,043 starslast pushed YesterdayGentleman-Programming
Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Spec-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in.
Go6,564 starslast pushed 24 hours ago
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | tirth8205 Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows. | Python | 31,293 | last pushed 2 weeks ago | |
| 2 | ovity GitHub on steroids | JavaScript | 23,244 | last pushed 2 years ago | |
| 3 | alibaba Fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible. | Go | 22,163 | last pushed Yesterday | |
| 4 | millionco Your agent writes bad React. This catches it | TypeScript | 14,808 | last pushed 2 days ago | |
| 5 | The-PR-Agent 🚀 PR Agent: The Original Open-Source PR Reviewer. This project is not the Qodo free tier. | Python | 12,924 | last pushed Yesterday | |
| 6 | reviewdog 🐶 Automated code review tool integrated with any code analysis tools regardless of programming language | Go | 9,571 | last pushed Yesterday | |
| 7 | modem-dev Review-first terminal diff viewer for agentic coders | TypeScript | 9,201 | last pushed Yesterday | |
| 8 | backnotprop Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click. | TypeScript | 8,580 | last pushed Yesterday | |
| 9 | jnMetaCode 🦸 AI 编程超能力 · 中文增强版 — superpowers（250k+ ⭐）完整汉化 + 4 个中国原创 skills，让 Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemini CLI / Qoder 等 26 款 AI 编程工具真正会干活 | JavaScript | 8,043 | last pushed Yesterday | |
| 10 | Gentleman-Programming Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Spec-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in. | Go | 6,564 | last pushed 24 hours ago |
All · 11,474