Sphinx
Open-source Git hook for agent-assisted coding: before code your agent wrote is pushed to a protected branch, it reads the diff and quizzes you on what the change actually does when things go wrong, and only lets the push through once you answer correctly. Works with Claude Code, Codex, Cursor and OpenCode.
Updated
✨ Try AgentScout's free AI image generator →Good for: writing code
Use cases
About Sphinx
Sphinx is listed in our coding category and is aimed at builders. Open-source Git hook for agent-assisted coding: before code your agent wrote is pushed to a protected branch, it reads the diff and quizzes you on what the change actually does when things go wrong, and only lets the push through once you answer correctly. Works with Claude Code, Codex, Cursor and OpenCode. Pricing, as the maker states it: Free and open source (MIT); questions are generated by a model you choose (your existing coding agent, OpenRouter or any OpenAI-compatible endpoint), so you pay only for those tokens. Maturity: Active. We last checked the official link on 2026-10-21.
What is Sphinx?
Sphinx is an open-source Git hook for agent-assisted development. When you, or your coding agent, push to a branch you protect, Git pauses and Sphinx has a reviewer model that never saw your chat read the diff and ask you what the change does when things go wrong.
Answer wrong and it explains why, then tries a new scenario; answer right and the push continues. Its pitch is that you can outsource the writing but not the understanding. It runs on few tokens using your existing coding agent, OpenRouter or any OpenAI-compatible endpoint, never shows your answers to the coding agent, never opens .env files or keys, and has a logged 'sphinx yolo' escape hatch. It reached the Hacker News front page in October 2026.
Sources: the official README and our directory listing, checked 2026-10-21. Official site: sphinx-six-theta.vercel.app.
Who is Sphinx for?
Developers who ship code written by Claude Code, Codex, Cursor or other agents and want to be sure they understand it before it reaches production.
Sphinx at a glance
- Open source: Yes (MIT License)
- GitHub: parthh01/sphinx · 280 stars · 12 forks (as of Oct 21, 2026)
Key features
- Git pre-push quiz on protected branches
- Questions generated from the actual diff
- Works with Codex, Claude Code, Cursor, OpenCode, Pi or plain Git
- Any model: your agent, OpenRouter or OpenAI-compatible
- Logged skip with 'sphinx yolo'
Sphinx FAQ
What is Sphinx?
Sphinx is an open-source Git hook for agent-assisted development. When you, or your coding agent, push to a branch you protect, Git pauses and Sphinx has a reviewer model that never saw your chat read the diff and ask you what the change does when things go wrong.
Who is Sphinx for?
Developers who ship code written by Claude Code, Codex, Cursor or other agents and want to be sure they understand it before it reaches production.
Is Sphinx free?
Sphinx's pricing, as the maker states it: Free and open source (MIT); questions are generated by a model you choose (your existing coding agent, OpenRouter or any OpenAI-compatible endpoint), so you pay only for those tokens. Check the official site for current plans.
Is Sphinx open source?
Yes. Sphinx is released under the MIT License, according to its GitHub repository.
How do I install it?
npm install -g sphinx-understand, then run sphinx install (Node 22.19+, macOS, Linux or WSL).
What are alternatives to Sphinx?
Similar tools include Vibe Kanban, Trail Code, Kilo Code, Cloudroom, Vicoa and Toad.
Sphinx ratings and reviews
Be the first to rate Sphinx: tap 1 to 5 stars below. A written review is optional.
Sphinx alternatives
Other coding tools in our directory. See all coding tools →
Vibe Kanban
Kanban board for planning and running tasks with Claude Code, Codex and other coding agents.
Trail Code
Context layer that makes Claude Code, Cursor, Codex and other coding agents faster and cheaper on large codebases.
Kilo Code
Open-source AI coding agent for VS Code, JetBrains, the CLI and the cloud that works with 500+ models at no markup.
Cloudroom
Cloudroom runs Claude Code, Codex, Pi and other coding agents in the cloud, each in its own isolated sandbox on its own Git branch, using your own model logins; the Rust core is open source to self-host, and a desktop app manages local and cloud agents.
Vicoa
Vicoa is an agent-native IDE for running Claude Code, Codex, Gemini and 40+ other coding agents in parallel, each on its own git worktree, from desktop, web or phone, with notifications when an agent needs you.
Toad
A terminal front end from Will McGugan (creator of Rich and Textual) for running AI coding agents like Claude Code, Gemini CLI and Codex through one polished, fast interface.
Badge for makers
Built Sphinx? Add this badge to your README or site. It links back to this page. About badges
