The AI Ranking Chart · GitHub repos

⭐ Coding

Live standings, refreshed daily. Votes count toward the November 2026 edition.

25 ranked · computed Oct 28
  1. 1
    new

    《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码

    73
  2. 2
    new

    CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

    71
  3. 3
    new

    AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,400+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.

    70
  4. 4
    new

    A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent

    67
  5. 5
    new

    The world's most flexible commerce platform for agents and developers

    65
  6. 6
    new

    Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.

    65
  7. 7
    new

    An open-source AI coding agent that lives in your terminal.

    63
  8. 8
    new

    Vibe Coding 从入门到精通教程|AI 结对编程工作流|Prompt、Skill、Workflow、上下文管理、codex实战指南

    60
  9. 9
    new

    Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent.

    59
  10. 10
    new

    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.

    59
  11. 11
    new

    Free, local tool to track AI coding token usage and cost across 37 tools and agents (Claude Code, Cursor, Codex, Gemini and more), by model, project, and task. npx codeburn

    54
  12. 12
    new

    Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Organic-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in.

    53
  13. 13
    new

    DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

    52
  14. 14
    new

    Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.

    46
  15. 15
    new

    The all-in-one local AI studio for your desktop: chat, image and video generation and a coding agent in one free, open source app. Windows and Linux. No Docker, no terminal, no cloud required.

    42
  16. 16
    new

    🎃 A fast, out-of-the-box macOS terminal built for AI coding.

    42
  17. 17
    new

    Project management skill system for Agents that uses GitHub Issues and Git worktrees for parallel agent execution.

    39
  18. 18
    new

    Code search MCP for Claude Code. Make entire codebase the context for any coding agent.

    38
  19. 19
    new

    🦸 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

    38
  20. 20
    new

    The most comprehensive Claude Code guide: agentic workflows, hooks, skills, MCP servers, quizzes, and production-ready templates. 430K+ lines.

    37
  21. 21
    new

    Git as the control plane for AI-native software engineering | AI Native 软件工程的 Git 变更控制手册

    37
  22. 22
    new

    Run any process, on your machine or in an AI agent's environment, as if it were a pod in your Kubernetes cluster: real env vars, DNS, network, traffic.

    35
  23. 23
    new

    AI coding platform for teams

    30
  24. 24
    new

    Multi-engine AI coding desktop client (Tauri). Claude Code, Codex, Gemini, OpenCode, DeepSeek Harness and more in one GUI.

    30
  25. 25
    new

    A harness optimized to smaller LLMs

    24

How scores work: data 60% · community 30% · editor 10%. /rankings/methodology →