WhySpec is a spec-driven development framework with "reasoning" layer for AI coding agents: an open-source CLI and agent skill set that helps you plan before coding, capture what actually happened after coding, and preserve the why behind each change for future chats, debugging, and reviews. MIT licensed, works offline, no account needed. Works with Claude Code, Cursor, Copilot, Codex CLI, and more.
GitWhy is the context layer for git. It helps developers save the reasoning behind AI-generated code, link it to commits, and surface it in GitHub PRs for review. It works with Claude Code, Cursor, and other coding agents.
We built GitWhy after running into a simple problem: AI could help write the code, but the reasoning behind it was getting lost. The prompt, trade-offs, and decisions stayed in the chat window, while the team only saw the diff.
GitWhy is the context layer for git that captures the prompt, reasoning, decisions, and changed files from Claude Code, Cursor, and other coding agents, tied to the commits that produced them. Share that context with your team and surface it directly in GitHub PRs for faster, clearer reviews.
