MCP server giving AI coding agents offline, token-efficient persistent memory — recall decisions, patterns, and bugs across sessions with 68.5% fewer tokens than re-reading context. No LLM, no server; works with 15+ agents.
Latest release v4.3.5 — 4.3.5 · 5 Aug 2026
1 file for Codex and OpenCode: toon-memory AGENTS.md — 666 tokens loaded in every session.
AGENTS.md A 666 tok These files are LuiggiVal08/toon-memory's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.