Codex
Actively usedOpenAI's cloud-based software engineering agent — runs in a sandboxed environment to write features, fix bugs, run tests, and submit PRs autonomously from natural language task descriptions.
About Codex
We're still writing the long-form notes for Codex.
In the meantime, the short summary above covers what it does and where it fits in our workflow. Hit Visit site to try it directly, or jump back to the full Tool Stack to keep browsing.
Try Codex yourself.
Open the site in a new tab — no signup required from us.
More in Development
Other tools we use alongside Codex.
Cursor
AI-powered code editor with natural language editing, codebase chat, and intelligent autocomplete for faster development. TESTING for AI-assisted coding workflows.
View toolClaude Code
Anthropic's agentic coding CLI — reads and edits entire codebases, runs tests, commits changes, and works autonomously on complex engineering tasks directly in your terminal.
View tool