Claude Code
Anthropic’s official agentic coding tool that runs in the terminal, IDE, and web.
Claude Code is Anthropic's official agentic coding tool. It runs in your terminal, integrates with IDEs like VS Code and JetBrains, and is also available on the web. Rather than acting as an autocomplete, it operates as an agent: it reads your codebase, plans changes, edits files, runs commands, and iterates against test or build feedback.
It is aimed at developers who want an assistant that works directly inside an existing project with full repository context, instead of copy-pasting snippets into a chat window.
Highlights
- Runs in the terminal, in IDE extensions, and on the web
- Agentic workflow: searches, edits files, runs commands, and self-corrects from output
- Repository-aware context, with project conventions captured in a
CLAUDE.mdfile - Extensible via MCP servers, custom slash commands, subagents, and hooks
- Git-native: can stage, commit, and open pull requests on request
How it fits an AI-assisted workflow
Install and start it from a project root:
npm install -g @anthropic-ai/claude-code
cd your-project
claudeTreat it as a pair working in your repo: describe a task, review the diff it proposes, and let it run tests before you commit. A CLAUDE.md file lets you encode build commands, architecture notes, and conventions so each session starts with shared context.
Good to know
NOTE
Claude Code requires a paid plan (Claude Pro/Max subscription or Anthropic API usage). Because it can run commands and modify files, review its proposed changes before committing, and use a version-controlled branch when granting broader autonomy.
Related
- AI Coding Agents in 2026: The Open-Source & CLI EditionCursor and Windsurf vs the open-source agents — Cline, Aider, Codex CLI, Roo Code, and more. Who should bring their own model, and when to stay in the terminal.
- Cursor vs Claude Code vs GitHub Copilot vs Windsurf in 2026A practical, opinionated comparison of the four mainstream AI coding tools — form factor, agentic depth, model choice, and who each one is for.
- AmpSourcegraph's agentic coding tool — a CLI and editor extensions tuned for frontier-model coding.
- Codex CLIOpenAI's open-source terminal coding agent with sandboxed execution and two-layer approval controls.
- DevinCognition's autonomous AI software engineer that works in its own cloud workspace with an editor, terminal, and browser.
- Gemini CLIGoogle's open-source terminal AI agent powered by Gemini models, with a 1M-token context window and built-in tools.
- GooseBlock's open-source, on-machine AI agent that is MCP-native and model-agnostic, with a CLI and desktop app.
- Playwright MCPMicrosoft's open-source MCP server that gives AI agents structured browser automation via Playwright's accessibility tree.
- WarpA modern, AI-powered terminal with an agent mode that can run and chain commands across your codebase.