Claude Code: the coding agent lands in the terminal
In one sentence Anthropic ships Claude Code alongside Claude 3.7 Sonnet: a CLI that reads the codebase, edits files, runs commands, runs tests, makes commits — the 'agent in terminal' pattern goes mainstream.
Anthropic releases Claude Code, a coding assistant that runs in the terminal. It's not an editor plugin: it's a command that, given a task ("add tests to function X", "explain this codebase", "upgrade dependency Y"), reads the files, proposes changes, applies them, and reruns the tests.
The difference with Copilot isn't the model, it's the posture: instead of suggesting one line at a time, it works on entire tasks and keeps you in the loop.
For people who run servers, write scripts, maintain personal repos, this is the first AI agent that makes sense to "let loose" on a real task, supervising at the end rather than word by word.
Companies
Anthropic
Tools
Claude Code, Claude 3.7 Sonnet
Tags
Sources