ccb # 以 nodejs 打开 claude code ccb-bun # 以 bun 形态打开 ccb update # 更新到最新版本 CLAUDEBRIDGEBASEURL=https://remote-control.claude-code-best.win/ CLAUDEBRIDGEOAUTHTOKEN=test-my-key ccb --remote-control # 我们有自部署的远程控制 一定要最新版本的 bun 啊, 不然一堆奇奇怪怪的 BUG!!! bun upgrade!!! powershell -c "irm bun.sh/install.ps1 | iex"
Which Claude do you like? The open source one is the best.
牢 A (Anthropic) 官方 Claude Code 完整复原的工程化项目。虽然很难绷, 但是它叫做 CCB(踩踩背)... 而且, 我们实现了企业版或者需要登陆 Claude 账号才能使用的特性, 并在此基础上扩展了更多好玩的特性。
Peri Code:Claude Code 兼容的 Rust Agent,多年大模型经验匠心制作,国内大模型(DeepSeek/GLM)精调,CPU/内存极致优化,在开发版/树莓派上也能跑 CC 一样的体验。
文档在这里 | 留影文档在这里 | Discord 群组,群主在线答疑
| 特性 | 说明 | 文档 |
|---|---|---|
| Claude 群控技术 | Pipe IPC 多实例协作:同机 main/sub 自动编排 + LAN 跨机器零配置发现与通讯,/pipes 选择面板 + Shift+↓ 交互 + 消息广播路由 | Pipe IPC / LAN |
| ACP 协议一等一支持 | 支持接入 Zed、Cursor 等 IDE,支持会话恢复、Skills、权限桥接 | 文档 |
| Remote Control 私有部署 | Docker 自托管远程界面, 可以手机上看 CC | 文档 |
| Langfuse 监控 | 企业级 Agent 监控, 可以清晰看到每次 agent loop 细节, 可以一键转化为数据集 | 文档 |
| Web Search | 内置网页搜索工具, 支持 bing 和 brave 搜索 | 文档 |
| Poor Mode | 穷鬼模式,关闭记忆提取和键入建议,大幅度减少并发请求 | /poor 可以开关 |
| Channels 频道通知 | MCP 服务器推送外部消息到会话(飞书/Slack/Discord/微信等),--channels plugin:name@marketplace 启用 | 文档 |
| 自定义模型供应商 | OpenAI/Anthropic/Gemini/Grok 兼容 (/login) | 文档 |
| Voice Mode | 语音输入,支持豆包语言输入(/voice doubao) | 文档 |
| Computer Use | 屏幕截图、键鼠控制 | 文档 |
| Chrome Use | 浏览器自动化、表单填写、数据抓取 | 自托管 原生版 |
| Sentry | 企业级错误追踪 | 文档 |
| GrowthBook | 企业级特性开关 | 文档 |
| /dream 记忆整理 | 自动整理和优化记忆文件 | 文档 |
不用克隆仓库, 从 NPM 下载后, 直接使用
npm i -g claude-code-best
# bun 安装比较多问题, 推荐 npm 装
# bun i -g claude-code-best
# bun pm -g trust claude-code-best @claude-code-best/mcp-chrome-bridge
ccb # 以 nodejs 打开 claude code
ccb-bun # 以 bun 形态打开
ccb update # 更新到最新版本
CLAUDE_BRIDGE_BASE_URL=https://remote-control.claude-code-best.win/ CLAUDE_BRIDGE_OAUTH_TOKEN=test-my-key ccb --remote-control # 我们有自部署的远程控制
安装/更新失败? 先
npm rm -g claude-code-best清理旧版本,再npm i -g claude-code-best@latest。仍失败则指定版本号:npm i -g claude-code-best@<版本号>
一定要最新版本的 bun 啊, 不然一堆奇奇怪怪的 BUG!!! bun upgrade!!!
安装 Bun:
# Linux 和 macOS
curl -fsSL https://bun.sh/install | bash
# Windows (PowerShell)
powershell -c "irm bun.sh/install.ps1 | iex"
安装后的操作:
让当前终端识别 bun 命令
安装脚本会把 ~/.bun/bin 写入对应的 shell 配置文件。macOS 默认 zsh 环境通常会看到:
Added "~/.bun/bin" to $PATH in "~/.zshrc"
可以按安装脚本提示重启当前 shell:
exec /bin/zsh
如果你使用 bash,重新加载 bash 配置:
source ~/.bashrc
Windows PowerShell 用户关闭并重新打开 PowerShell 即可。
验证 Bun 是否可用
bun --help
bun --version
如果已经安装过 Bun,更新到最新版本
bun upgrade
curl -fsSL https://bun.sh/install | bash、bun --help、bun --version、bun upgradepackage.json 的目录。cd /path/to/claude-code
bun install
# 开发模式, 看到版本号 888 说明就是对了
bun run dev
# 构建
bun run build
构建采用 code splitting 多文件打包(build.ts),产物输出到 dist/ 目录(入口 dist/cli.js + 约 450 个 chunk 文件)。
构建出的版本 bun 和 node 都可以启动, 你 publish 到私有源可以直接启动
如果遇到 bug 请直接提一个 issues, 我们优先解决
首次运行后,在 REPL 中输入 /login 命令进入登录配置界面,选择 Anthropic Compatible 即可对接第三方 API 兼容服务(无需 Anthropic 官方账号)。
选择 OpenAI 和 Gemini 对应的栏目都是支持相应协议的
需要填写的字段:
| 📌 字段 | 📝 说明 | 💡 示例 |
|---|---|---|
| Base URL | API 服务地址 | https://api.example.com/v1 |
| API Key | 认证密钥 | sk-xxx |
| Haiku Model | 快速模型 ID | claude-haiku-4-5-20251001 |
| Sonnet Model | 均衡模型 ID | claude-sonnet-4-6 |
| Opus Model | 高性能模型 ID | claude-opus-4-6 |
ℹ️ 支持所有 Anthropic API 兼容服务(如 OpenRouter、AWS Bedrock 代理等),只要接口兼容 Messages API 即可。
所有功能开关通过 FEATURE_<FLAG_NAME>=1 环境变量启用,例如:
FEATURE_BUDDY=1 FEATURE_FORK_SUBAGENT=1 bun run dev
各 Feature 的详细说明见 docs/features/ 目录,欢迎投稿补充。
TUI (REPL) 模式需要真实终端,无法直接通过 VS Code launch 启动调试。使用 attach 模式:
终端启动 inspect 服务:
bun run dev:inspect
会输出类似 ws://localhost:8888/xxxxxxxx 的地址。
VS Code 附着调试器:
src/ 文件中打断点我们新加了一个 teach-me skills, 通过问答式引导帮你理解这个项目的任何模块。(调整 sigma skill 而来)
# 在 REPL 中直接输入
/teach-me Claude Code 架构
/teach-me React Ink 终端渲染 --level beginner
/teach-me Tool 系统 --resume
--resume 从上次进度继续学习进度保存在 .claude/skills/teach-me/ 目录下,支持跨主题学习者档案。
docs/ 目录,欢迎投稿 PR本项目仅供学习研究用途。Claude Code 的所有权利归 Anthropic 所有。
Claude Code Tutorial for Beginners
Kevin Stratvert · 857K views
Claude Code - Full Tutorial for Beginners
Tech With Tim · 1148K views
FULL Claude Code Tutorial for Beginners in 2026! (Step-By-Step)
Tech With Tim · 328K views
“https://xcancel.com/Fried_rice/status/2038894956459290963 Related ongoing thread: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode - https://news.ycombinator.com/item?id=47586778”
“Related ongoing thread: Claude Code's source code has been leaked via a map file in their NPM registry - https://news.ycombinator.com/item?id=47584540 Also related: https://www.ccleaks.com”
“The architect behind Claude Code reveals the three things Anthropic looks for in a good hire - Fortune — Fortune”
“The Anthropic leader who built Claude Code says he ditched prompting — now he just writes loops. - The New Stack — The New Stack”
“Claude Fable 5 and Claude Mythos 5 - Anthropic — Anthropic”
AI
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: 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
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
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,