Terminal Agent
Claude Code
Anthropic's official CLI agent that reads, edits, and runs code directly in your terminal — built for multi-step, agentic coding tasks.
Claude Code runs in your terminal and works like a senior engineer with full access to your codebase: it can search files, run shell commands, edit code across multiple files, run tests, and commit changes — all while narrating what it’s doing.
Why it stands out
- Agentic by default. It plans multi-step tasks (refactors, migrations, bug hunts) and executes them end-to-end rather than answering one prompt at a time.
- Terminal-native. No IDE lock-in — it works with whatever editor, shell, and tooling you already use.
- Extensible. Supports custom subagents, skills, hooks, and MCP servers for connecting to external systems.
Good for
Developers who want an agent that can operate autonomously across a whole repository — large refactors, dependency upgrades, or building a feature from a plain-English spec.