Co-Pilot / 辅助式
更新于 a month ago

moai-rank

Mmodu-ai
0.0k
modu-ai/moai-rank
80
Agent 评分

💡 摘要

MoAI Rank是一个用于跟踪Claude Code令牌使用和编码会话的竞争平台。

🎯 适合人群

希望跟踪编码效率的AI开发者学习AI编排和编码实践的学生希望提高技能的开源贡献者对竞争编码感兴趣的技术爱好者监督AI开发团队的项目经理

🤖 AI 吐槽:编码的排行榜?终于有办法量化我的拖延症了!

安全分析中风险

该项目将API密钥存储在本地JSON文件中,如果文件系统被攻破,则存在风险。为减轻此风险,请确保适当的文件权限,并考虑加密敏感数据。

MoAI Rank - Claude Code Agent Leaderboard

Next.js TypeScript PostgreSQL Clerk License

A competitive leaderboard platform for tracking Claude Code token usage. Track your AI coding sessions, compete with the community, and discover your own coding style through Agentic Coding Analytics.

English | 한국어 | 日本語 | 中文

⚠️ Important Notice (2025-01-25)

Due to a production environment migration, all existing accounts have been reset. If you were previously registered, please sign up again at rank.mo.ai.kr. We apologize for any inconvenience.


📚 Everyone's AI Agentic Coding Lecture

This project was created as a lecture example demonstrating practical MoAI-ADK usage.

🎯 Project Purpose

Experience a new dimension of agentic coding!

MoAI Rank was created for the following learning purposes:

  • Real-world AI Agent Orchestration: A complete system built through collaboration of 20 specialized agents
  • SPEC-First TDD Realization: Perfect quality process from specifications to tests
  • Scalable Architecture: Production-ready code with caching, data retention policies, and performance optimizations
  • Open Source Contribution: Releasing all code to contribute to community learning

⚠️ Development Environment

48-Hour Hacking Project

This project was intensively built using MoAI-ADK over 48 hours. A practical example demonstrating rapid development in real-world environments.

Development Characteristics:

  • Core functionality implemented using MoAI-ADK's /moai:alfred /moai:loop fully autonomous automation commands
  • Cost-effective development using GLM 4.7 and Claude Opus in hybrid
  • Worktree parallel development for simultaneous development of independent functional modules

Testing Insufficiency Notice:

  • Due to the 48-hour development, sufficient testing may not have been conducted
  • If you find any errors or improvements, please leave them at GitHub Issues
  • Community contributions make the project more robust

🔗 Related Projects


🚀 Before You Start: Install MoAI-ADK

To use MoAI Rank, MoAI-ADK must be installed first.

What is MoAI-ADK?

MoAI-ADK is an AI development framework that creates quality code.

  • SPEC-First TDD: 90% rework reduction with clear specifications
  • AI Orchestration: 20 specialized agents + 48 skills
  • Multi-language Support: Automatic Korean/English/Japanese/Chinese support
  • Worktree Parallel Development: Unlimited parallel work in completely isolated environments
  • MoAI Rank: Motivation through vibe coding leaderboard

Quick Installation

# Method 1: Quick Installation (Recommended) curl -LsSf https://modu-ai.github.io/moai-adk/install.sh | sh # Method 2: Manual Installation # Step 1: Install uv (macOS/Linux) curl -LsSf https://astral.sh/uv/install.sh | sh # Step 2: Install MoAI-ADK uv tool install moai-adk

🎮 MoAI Rank CLI Commands

Once MoAI-ADK is installed, you can use the MoAI Rank CLI.

Command Overview

moai rank [OPTIONS] COMMAND [ARGS]... MoAI Rank - Claude Code Token Usage Leaderboard Track your Claude Code sessions and compete on the leaderboard. Web dashboard: https://rank.mo.ai.kr Options: --help Show help message Commands: login Login to MoAI Rank via GitHub OAuth (alias: register) status Show current rank and statistics exclude Exclude project from session tracking include Re-include previously excluded project logout Remove stored MoAI Rank credentials

Detailed Command Explanations

1. login - GitHub OAuth Login

moai rank login

Note: moai rank register is still supported as an alias for backward compatibility.

How It Works:

  1. Opens browser for GitHub OAuth authentication
  2. Automatically generates and stores API key after successful authentication
  3. Installs global hook to start automatic session tracking
  4. Securely stores API key in ~/.moai/rank/credentials.json

Execution Example:

❯ moai rank login ╭──────────────────────────────── Login ───────────────────────────────╮ │ MoAI Rank Login │ │ │ │ This will open your browser to authorize with GitHub. │ │ After authorization, your API key will be stored securely. │ ╰──────────────────────────────────────────────────────────────────────╯ Opening browser for GitHub authorization... Waiting for authorization (timeout: 5 minutes)... ╭─────────────────────────── Login Complete ───────────────────────────╮ │ Successfully logged in as your-github-id │ │ │ │ API Key: moai_rank_a9011fac_c... │ │ Stored in: ~/.moai/rank/credentials.json │ ╰──────────────────────────────────────────────────────────────────────╯ ╭───────────────────────── Global Hook Installed ──────────────────────╮ │ Session tracking hook installed globally. │ │ │ │ Your Claude Code sessions will be automatically tracked. │ │ Hook location: ~/.claude/hooks/moai/session_end__rank_submit.py │ │ │ │ To exclude specific projects: │ │ moai rank exclude /path/to/project │ ╰──────────────────────────────────────────────────────────────────────╯

2. sync - Sync Session Data

moai rank sync

Synchronizes local Claude Code session data to the MoAI Rank server.

Example Output:

❯ moai rank sync Syncing 2577 session(s) to MoAI Rank Phase 1: Parsing transcripts (parallel: 20 workers) Parsing transcripts ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% (2577/2577) Phase 2: Submitting 1873 session(s) (batch mode) Batch size: 100 | Batches: 19 Submitting batches ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% (19/19) Sync Complete ✓ Submitted: 0 ○ Skipped: 704 (no usage or duplicate) ✗ Failed: 500

3. status - Check My Rank

moai rank status

How It Works:

  • Calls /api/v1/rank endpoint with stored API key
  • Retrieves user-specific ranking data from server
  • Displays daily/weekly/monthly/all-time ranks and statistics

Execution Example:

❯ moai rank status ╭────────────────────────────── MoAI Rank ─────────────────────────────╮ │ your-github-id │ │ │ │ 🏆 Global Rank: #42 │ ╰──────────────────────────────────────────────────────────────────────╯ ╭───── Daily ──────╮ ╭───── Weekly ─────╮ ╭──── Monthly ─────╮ ╭──── All Time ────╮ #12 │ │ #28 │ │ #42 │ │ #156 │ ╰──────────────────╯ ╰──────────────────╯ ╰──────────────────╯ ╰──────────────────╯ ╭─────────────────────────── Token Usage ──────────────────────────────╮ 1,247,832 total tokens │ │ │ │ Input ██████████████░░░░░░ 847,291 (68%)│ Output ██████░░░░░░░░░░░░░░ 400,541 (32%)│ │ │ Sessions: 47╰──────────────────────────────────────────────────────────────────────╯ ● Hook: Installed | https://rank.mo.ai.kr

4. exclude/include - Project Management

# Exclude current project moai rank exclude # Exclude specific path moai rank exclude /path/to/private # Wildcard patterns moai rank exclude "*/confidential/*" # List excluded projects moai rank list-excluded # Re-include moai rank include /path/to/project

Privacy Protection:

  • Sensitive projects can be excluded from tracking
  • Data from excluded projects is not sent to the server

5. logout - Logout

moai rank logout
  • Removes stored API key
  • Removes global hook
  • Stops all tracking

📊 Collected Metrics

| Metric | Description | Collected | | ---------------- | ----------------------------------- | --------- | | Token Usage | Input/Output tokens, Cache tokens | O | | Tool Usage | Read, Edit, Bash usage counts | O | | Model Usage | Opus, Sonnet, Haiku breakdown | O | | Code Metrics | Added/deleted lines, modified files | O | | Session Info | Duration, turn count, timestamps | O | | Code Content | Actual code content | X | | File Paths | File paths within project | X | | Prompts | Conversation content with Claude | X |

Guarantee: Collected data contains only numerical metrics; code content or conversation details are never transmitted.


Table of Contents

五维分析
清晰度8/10
创新性8/10
实用性9/10
完整性8/10
可维护性7/10
优缺点分析

优点

  • 鼓励竞争编码和社区参与
  • 提供编码会话的详细指标
  • 支持多种语言以提高可及性

缺点

  • 有限的测试可能导致错误
  • 需要安装额外的框架
  • 会话跟踪的隐私问题

相关技能

pytorch

S
toolCode Lib / 代码库
92/ 100

“它是深度学习的瑞士军刀,但祝你好运能从47种安装方法里找到那个不会搞崩你系统的那一个。”

agno

S
toolCode Lib / 代码库
90/ 100

“它承诺成为智能体领域的Kubernetes,但得看开发者有没有耐心学习又一个编排层。”

nuxt-skills

S
toolCo-Pilot / 辅助式
90/ 100

“这本质上是一份组织良好的小抄,能把你的 AI 助手变成一只 Nuxt 框架的复读机。”

免责声明:本内容来源于 GitHub 开源项目,仅供展示和评分分析使用。

版权归原作者所有 modu-ai.