Anthropic’s CLI for Claude — the coding agent
Claude Code is Anthropic’s official CLI for coding with Claude. Explore skills, MCP servers, frameworks, and tools built for the Claude Code ecosystem.
npm install -g @anthropic-ai/claude-codeRequires Node.js 18+. Works on macOS, Linux, and WSL.
cd your-project && claudeOpens an interactive session. Claude reads your codebase and helps you code.
Add skills (custom slash commands), MCP servers (external tools), hooks (lifecycle events), and agents for complex tasks.
One command. Takes about 30 seconds.
Check if you have Node.js
node --versionYou need v18 or higher. If you see a number like v20.11.0, you're good. If you get "command not found", go to nodejs.org and install it first.
Install Claude Code globally
npm install -g @anthropic-ai/claude-codeThis installs the claude command on your machine. Runs on macOS, Linux, and Windows (WSL).
Verify it worked
claude --versionYou should see a version number. If you do, you're ready to go.
Point it at your code and start talking.
Open your terminal
On Mac: Spotlight → type "Terminal". On Windows: open WSL or Windows Terminal.
Navigate to your project folder
cd ~/my-projectReplace ~/my-project with the actual path to your project.
Start Claude Code
claudeThat's it. Just type claude and hit Enter.
First time? Log in
It'll open a browser window to authenticate with your Anthropic account. Log in, come back to the terminal, and you're connected.
Start talking
Claude automatically reads your project files. Just describe what you want: "add a login page", "fix the failing test", "refactor this function".
Everything you need to know to not feel lost.
Send your message
Cancel what Claude is doing right now
Exit Claude Code completely
Scroll through your message history
/helpSee all available commands
/clearWipe the conversation and start fresh
/compactSummarize and shrink the conversation
/costSee how much this session has cost so far
Pro tip: When Claude wants to edit a file or run a command, it'll ask for permission. Press y to allow, n to deny. You can also type ! to allow and stop asking for that type of action.
The strongest lanes in this ecosystem, ranked by visible public proof.
6 tracked builds
5 tracked builds
5 tracked builds
6 tracked builds
4 tracked builds
5 tracked builds
Filter the ranked board by type, timing, and proof signal.
15 signals found
DSH 官方公众号收录的 TUI 补位插件:Claude Code 风,鲸鱼顶栏/实时状态/流式思考/双击 Esc 回滚/上下文进度+TPS。npm 一键装。 DSH official WeChat featured TUI plu...
DSH 官方公众号收录的 TUI 补位插件:Claude Code 风,鲸鱼顶栏/实时状态/流式思考/双击 Esc 回滚/上下文进度+TPS。npm 一键装。 DSH official WeChat featured TUI plugin — Claude Code style: whale bar, live status, streaming thoughts, double-Esc rollback, context bar + TPS. npm one-click.
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS...
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.
AI handles execution, humans own the direction, and every run becomes an inspectable research artifact on disk.
AI handles execution, humans own the direction, and every run becomes an inspectable research artifact on disk.
A terminal workbench in pure Rust: shells, persistent sessions, SSH, coding agents. GPU-rendered on Zed's gpui, VT co...
A terminal workbench in pure Rust: shells, persistent sessions, SSH, coding agents. GPU-rendered on Zed's gpui, VT core from Alacritty.
Wayland - The AI Agent That Perceives. Reasons. Acts. Evolves.
Wayland - The AI Agent That Perceives. Reasons. Acts. Evolves.
30 sec to give your AI agents persistent memory. Reduce 90% token consumption while also maintaining quality.
30 sec to give your AI agents persistent memory. Reduce 90% token consumption while also maintaining quality.
Open-source Claude Managed Agents API implementation and self-hosted Claude Tag-style agent runtime. Drop-in compatib...
Open-source Claude Managed Agents API implementation and self-hosted Claude Tag-style agent runtime. Drop-in compatible; runs on Cloudflare Workers/Durable Objects or Node.js. Apache 2.0.
Stop letting your work go unnoticed. Meridian keeps an automatic work journal of what you worked on and what you fini...
Stop letting your work go unnoticed. Meridian keeps an automatic work journal of what you worked on and what you finished, summarised daily, and automatically drafts your project tickets for you.
A curated, battle-tested AI-coding toolkit: Claude Code plugins, subagent orchestration, quality gates, and ready-to-...
A curated, battle-tested AI-coding toolkit: Claude Code plugins, subagent orchestration, quality gates, and ready-to-copy prompts, extracted from real production use.. An open-source agent for the AI coding ecosystem.
Automated quality checks that nudge AI coding agents toward better habits
Automated quality checks that nudge AI coding agents toward better habits
Build an AI agent harness in Rust, from a minimal loop to tools, subagents, memory, teams, worktrees, MCP, and type...
Build an AI agent harness in Rust, from a minimal loop to tools, subagents, memory, teams, worktrees, MCP, and typed tool routing.
Plan-first companion for Claude Code - draft the plan, learn every Claude Code feature inline, run it as a crew, and...
Plan-first companion for Claude Code - draft the plan, learn every Claude Code feature inline, run it as a crew, and see your token usage. Local-first, no API key.
Let Claude edit your Figma file for you — bulk-rename layers, swap variants, bind colour variables, pour in real copy...
Let Claude edit your Figma file for you — bulk-rename layers, swap variants, bind colour variables, pour in real copy. Describe the change in plain words, watch it land in the file in seconds. A small plugin keeps Figma talking to your terminal.
The open-source AI agent control plane: MCP firewall, model gateway with budgets, human approvals, runtime observabil...
The open-source AI agent control plane: MCP firewall, model gateway with budgets, human approvals, runtime observability, and audit trails
Shunt Claude Code agents to any model — selective, per-agent inference-layer routing proxy
Shunt Claude Code agents to any model — selective, per-agent inference-layer routing proxy