I built a dev tool that "evolves" code with AI — REAP

The Problem If you've been building with AI agents (like Claude Code), you've probably encountered these problems: Context loss — Start a new session and your context is gone. You end up clinging to long sessions just to avoid losing everything the AI has learned. Stale documentation — You try to persist knowledge in READMEs and CLAUDE.md files, but they quietly go stale as the project moves forward. AI going rogue — Sometimes the AI just ignores your carefully crafted docs and does its own thing anyway. We're all stuck at the same bottleneck — the context window just isn't enough for long-running projects. I tried existing tools like spec-kit and superpower — they're decent for one-off feature work, but didn't quite fit for sustained, long-term development. What I Built So I built REAP (Recursive Evolutionary Autonomous Pipeline) — an open-source CLI tool inspired by generational evolution in biology. The idea: AI and humans evolve software across generations. Genome (Design & Kno