本仓库通过 npm 发布包（@anthropic-ai/claude-code）内附带的 source map（cli.js.map）还原的 TypeScript 源码，版本为 2.1.88。 restored-src/src/ ├── main.tsx # CLI 入口 ├── tools/ # 工具实现（Bash、FileEdit、Grep、MCP 等 30+ 个） ├── commands/ # 命令实现（commit、review、config 等 40+ 个） ├── services/ # API、MCP、分析等服务 ├── utils/ # 工具函数（git、model、auth、env 等） ├── context/ # React Context ├── coordinator/ # 多 Agent 协调模式 ├── assistant/ # 助手模式（KAIROS
claude-code-sourcemap
[!WARNING] This repository is unofficial and is reconstructed from the public npm package and source map analysis, for research purposes only. It does not represent the original internal development repository structure.
本仓库为非官方整理版，基于公开 npm 发布包与 source map 分析还原，仅供研究使用。 不代表官方原始内部开发仓库结构。 一切基于L站"飘然与我同"的情报提供
概述
本仓库通过 npm 发布包（@anthropic-ai/claude-code）内附带的 source map（cli.js.map）还原的 TypeScript 源码，版本为 2.1.88。
来源
- npm 包：@anthropic-ai/claude-code
- 还原版本：
2.1.88 - 还原文件数：4756 个（含 1884 个
.ts/.tsx源文件） - 还原方式：提取
cli.js.map中的sourcesContent字段
目录结构
restored-src/src/
├── main.tsx # CLI 入口
├── tools/ # 工具实现（Bash、FileEdit、Grep、MCP 等 30+ 个）
├── commands/ # 命令实现（commit、review、config 等 40+ 个）
├── services/ # API、MCP、分析等服务
├── utils/ # 工具函数（git、model、auth、env 等）
├── context/ # React Context
├── coordinator/ # 多 Agent 协调模式
├── assistant/ # 助手模式（KAIROS）
├── buddy/ # AI 伴侣 UI
├── remote/ # 远程会话
├── plugins/ # 插件系统
├── skills/ # 技能系统
├── voice/ # 语音交互
└── vim/ # Vim 模式
声明
- 源码版权归 Anthropic 所有
- 本仓库仅用于技术研究与学习，请勿用于商业用途
- 如有侵权，请联系删除
Videos
Tragic mistake... Anthropic leaks Claude’s source code
Fireship · 3213K views
BREAKING: Claude Code source leaked
Theo - t3․gg · 198K views
Claude Code Source Code Just Leaked… 8 Things You Must Do
Nate Herk | AI Automation · 130K views
What people are saying
“tl;dr Please point me to a true beginner’s reference/tutorial on networking. Gradually, patiently, persistently, over the past ten years and more, I moved from Windows and Mac to all FOSS apps and then full Linux. Doing …”
HN↑ 185kickaha↗
“I'm thinking about having a beefy desktop computer at home and using some kind of remote desktop solution to connect to it from other places (e.g co-working spaces). I have good bandwidth (250+ Mbit both ways) with low l…”
HN↑ 45filleokus↗
“Firstly I am an aspiring web developer. Everyone has been saying "linux, learn linux" to me. I'm not understanding why that's the case. But personally, I love linux because it makes my life easier. No BSODs, no need to r…”
HN↑ 18shivajikobardan↗
“I am considering a new laptop, to replace my ageing MacBook, and would like to move to Linux. Does anyone have any recommendations for quality developer machines? I am suprised in particular it seems hard to get a machin…”
HN↑ 8CJefferson↗
“Every time I browse web sites on Linux (Ubuntu), the web sites look a little "washed out". On the other hand, every time I browse web sites on MacOS, the web sites look vibrant, with nice saturated colors and clear, easy…”
HN↑ 3g42gregory↗
You might also like
AI
career ops
Companies use AI to filter candidates. I just gave candidates AI to choose companies. Career-Ops (career-ops.org, also known as careerops) turns any AI coding CLI into a full job search command center. Instead of manually tracking applications in a spreadsheet, you get an AI-powered pipeline that: Career-ops is agentic: Claude Code navigates career pages with Playwright, evaluates fit by reasoning about your CV vs the job description (not keyword matching), and adapts your resume per listing.
AI
CLI Anything
CLI-Anything: Bridging the Gap Between AI Agents and the World's Software 🌐 CLI-Hub: pip install cli-anything-hub then cli-hub install — browse, install, and manage all community-built CLIs. Want to add your own? Open a PR — the hub updates instantly. 🎬 See Demos: Watch AI agents use generated CLIs plus preview, live preview, and trajectory loops to produce real artifacts — CAD builds, 3D scenes, diagrams, gameplay, subtitles, and more.
AI
odysseus
A self-hosted AI workspace -- meant to be the self-hosted version of the UI experience you get from ChatGPT and Claude. But with more jank and fun. Running on your own hardware, with your own data -- local-first, privacy-first, and no trojan. A full, hover-to-play tour lives on the landing page (docs/index.html). Defaults work out of the box: clone, run, then configure models/search/email inside Settings. Only edit .env for deployment-level overrides like APPBIND, APPPORT, AUTHENABLED, DATABASEURL, or a pre-seeded admin password.
AI
ai engineering from scratch
Most AI material teaches in scattered pieces. A paper here, a fine-tuning post there, a flashy agent demo somewhere else. The pieces rarely line up. You ship a chatbot but can't explain its loss curve. You hook a function to an agent but can't say what attention does inside the model that's calling it. This curriculum is the spine. 20 phases, 503 lessons, four languages: Python, TypeScript, Rust, Julia. Linear algebra at one end, autonomous swarms at the other. Every algorithm gets built from raw math first. Backprop. Tokenizer. Attention. Agent loop. By the time PyTorch shows up, you already know what it's doing under the hood. Each lesson runs the same loop: read the problem, derive the math, write the code, run the test, keep the artifact. No five-minute videos, no copy-paste deploys,