Claude Code plugin turns hooks into persistent memory shared across Codex and Cursor
blaizedsouza · x · 2026-11-22
A new article explains a Claude Code plugin that turns hooks into agent memory:
- Why not MCP memory tools: they depend on the model deciding to save, which rarely happens in long sessions; hooks run every time
- Mechanism: the plugin records prompts, tool calls, results and answers as you work, then cognee turns them into a knowledge graph and short lessons at session end
- Cross-tool sharing: Codex, Cursor and OpenCode write to the same memory, so insights from a morning Claude Code session surface in an afternoon Codex session
The piece also engages Kevin Liao's "agents need documentation, not memory" critique, offering hooks-based automation as a middle path.
More from coding & agent
- Browser dragon-in-your-hand demo built with Three.js, MediaPipe hand tracking and WebRTC — techartist_ · 2026-11-22
- Developer Praises Google Antigravity's Agent Swarm UX — majidmanzarpour · 2026-11-22
- Store Scraper MCP exposes App Store and Google Play data to AI agents — modelcontextprotocol · 2026-11-22
- etapa MCP offers a free AI cycling coach for beginners — modelcontextprotocol · 2026-11-22
- Brandon Galang: As Models Get Capable, UX Scaffolding Melts Away in Favor of Context Flow — brandongalang · 2026-11-22
- Simon Willison on evals, going weird, and tools for Pulitzer-level journalism — TheTuringPost · 2026-11-22