ClaudeMap

Claude Code

Anthropic's official agentic coding CLI for the terminal.

SDKs & Toolingofficialclianthropic

Runs Claude in your terminal, edits files, runs shell commands, and orchestrates multi-step engineering workflows directly against your codebase.

What it does

  • Agentic coding in the terminal — edits files, runs shell commands, and navigates your repo autonomously
  • CLAUDE.md project memory — persistent instructions that carry across sessions
  • Tool use out of the box — file editing, bash execution, web search, and MCP server integration
  • Hooks and subagents — event-driven hooks and parallel subagents for custom workflows
  • Built for large repos — reads and reasons across a whole codebase, not single files

When to use it

Best for end-to-end feature work, cross-file refactors, debugging with full repository context, and getting up to speed on an unfamiliar codebase. Less suited for single-shot snippets you'd paste into a chat UI.

Getting started

npm install -g @anthropic-ai/claude-code

Then run `claude` inside your project directory.

Things to know

Requires an Anthropic API key or a Claude subscription. The first query on a large repo can be slower while it builds context. Claude Code can run commands and edit files, so review proposed changes and use the permission prompts to stay in control.

Repository

anthropics/claude-code

Charted

Related on the map

  • E2B

    SDK / Tool

    Open-source secure sandboxes where AI agents run code — the de facto execution layer for agent apps.

    • sandbox
    • code-execution
    • sdk
    • agents
  • FastMCP

    SDK / Tool

    Pythonic framework for building MCP servers — decorators, type hints, and zero boilerplate.

    • framework
    • python
    • mcp
    • type-driven
  • Anthropic's official TypeScript SDK for building agentic applications.

    • official
    • sdk
    • typescript
    • anthropic