djasdh/interest-memory

README excerpt

English 中文 interest-memory — Long-term memory for AI agents One 50MB process instead of a Postgres + Redis + vector DB stack. Agents forget everything between sessions. Not the model's fault — they lack a real memory layer. interest-memory is a standalone memory backend: at the end of a session it extracts interest points from the transcript, verifies and cleans them, and writes them into a local knowledge base; at the start of the next session it recalls and injects relevant context. The entire footprint: one 18MB binary + one SQLite file . The unit of memory is the interest point : semantically similar ones are merged automatically, and each one is written into the knowledge base as a wiki page by an LLM-driven agent loop — the knowledge base converges with use instead of bloating. Selling point Detail Light one 18MB binary + one SQLite file is the whole footprint; 17MB idle, /extensions/interest-memory/ ) pi TS extension ( /.pi/agent/extensions/interest-memory/ ) Claude Code official plugin + MCP ( claude --plugin-dir bridge/claudecode ) Codex official plugin / hooks + MCP ( /.codex/hooks.json ) Reasonix official plugin + MCP ( reasonix plugin install bridge/reasonix --link ) De…

Category