Your AI coding agent keeps re-deriving the same fix every session. Give it a memory — a shared, searchable log of lessons it writes after work and auto-recalls before. Claude Code plugin + tiny CLI; works with Cursor / any agent.
Plugin Claude Code
Engineering memory for AI coding agents — a structured cross-project log, a deliberately dumb CLI, and a Claude Code plugin that closes the read-side loop with auto-firing hooks.
Plugin Claude Code
Close the engineering-memory loop: auto-inject relevant prior lessons on session start and on symptom-shaped prompts, plus a /recall command for explicit deep dive.