Claude Code
AnthropicAnthropic's terminal agent: reads the repo, edits files, runs the tests it just broke.
Open-source coding agent for the editor with approval at each step.
Developers who want agentic edits but keep a confirm prompt on each action
People who want autocomplete — this is task-shaped
An editor agent that plans a change, proposes edits, and asks before each file write. The approval-per-step model is the point: it is slower than an autonomous agent and it keeps the human in the loop without a separate review step. The trade is your own model key and a config file.
Anthropic's terminal agent: reads the repo, edits files, runs the tests it just broke.
A code editor built around an agent that can read your whole repo.
Google's open-source terminal agent, wired to Gemini models and MCP servers.
3 alternatives overlap with this one. Compare them →
Pulls LangSmith traces and runs: inputs, outputs, latency, and errors for a project. It turns 'the agent is flaky' into a specific failing step, which is the only wa…
Serves version-specific documentation for thousands of libraries, so an agent stops writing code against an API that changed two releases ago. The practical fix for …
Derive contract tests from an API description, not from the implementation.
Find the code paths with no test, ranked by blast radius.
Turn an incident list into a decision about what to fix next.