whereismyai
Sphinx
Sphinx is a Git hook for agent-assisted development that quizzes users on code diffs before pushes.
Sphinx is a Git hook designed for agent-assisted development. Before an agent's code ships, the tool asks a question about what the code actually does based on the diff. It runs on minimal tokens using existing coding agents, OpenRouter, or OpenAI-compatible endpoints. The system pauses Git on protected branches until the user answers correctly about edge cases and error handling. It works with Codex, Claude Code, Cursor, OpenCode, Pi, and plain Git. User answers are kept separate from the coding agent, and environment files or keys are not opened.
Sphinx at a glance
Key features
- Git hook integration for code pushes
- Interactive code understanding quizzes
- Minimal token usage
- OpenAI-compatible and OpenRouter endpoint support
- Bypass option with skip logging
- Protection for specified Git branches
Use it for
- Reviewing agent-generated code before shipping
- Testing understanding of diff error handling
- Pausing Git pushes until code comprehension is verified
Companions
Tools that articles about Sphinx recommend using with it, each with its job.
- Context7 — Provides up-to-date documentation for AI agents and code editors.
- Ollama — Run local models at zero marginal cost, with code kept on your machine.
- OpenRouter — Access over 500 models and 80 providers through one unified API.
- Daytona — Runs sessions in isolated sandboxes synced to git branches.
- Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
- Oh My OpenCode Slim — Lightweight multi-agent orchestration and background tasks.
Alternatives to Sphinx
- jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
- OpenCode — Works with 75+ model providers, local models, and existing subscriptions
- Orca — Runs multiple AI coding agents simultaneously in isolated workspaces.
- pstack — Improves AI coding agent outcomes with rigorous workflows.
- Reviewer Agent — It uses a separate AI model to review code and prevent premature agent stopping.
- Weft — It enables safe parallel coding agent work without file locks.
- AGENTS.md — It separates agent-specific instructions from human-focused README files.
- Hermes IDE — Run different coding agents side by side in one interface with centralized reviews.
- CodeGraph — It eliminates file crawling, reducing AI agent tool calls by 88% and cutting costs.
- LangChain — Compose exactly the agent your use case needs from model, tools, prompt, and middleware.
- GitAgent — Manage AI agents with familiar git workflows like branching, diffing, and reverting.
- Agent Archive — Hand off coding sessions between Claude Code, Codex, and Cursor across machines.
All Sphinx alternatives