I Built “Git for AI Workflows” Because AI Agents Have Zero Memory of What They Did

Everyone is building AI agents. Almost nobody can audit them. You give an LLM a prompt. It calls tools. Generates outputs. Changes workflows. Makes decisions. And two days later? Nobody knows: what prompt was used which agent triggered it what actually changed which version of the workflow produced the result why the output suddenly shifted That felt insane to me. So I built: AI Audit Shelf A lightweight, open‑source system that brings Git‑like versioning to AI workflows....