pmb

Repo for anyone who wants to look under the hood: https://github.com/oleksiijko/pmb

How it works: - Storage uses one SQLite database file, plus a local LanceDB index of vectors. No need for a server, cloud services, or any API keys. - Retrieval is a hybrid approach using BM25 (rank-bm25) and vector-based search (sentence-transformers) combined with a co-occurrence graph of entities, using reciprocal rank fusion. The idea is to find the right memory, not the closest one. - It plugs into the agent's lifecycle via MCP: before the agent responds, relevant memories are added to its input; after each turn, decisions and new learnings are automatically recorded. No need to manually remember "remember this". - It maintains a dictionary for each project which builds itself based on your memories, which improves recall performance for the project-specific vocabulary. - It can run fully offline, pointing to a locally installed Olla

PMB is a local-first memory system for AI coding agents, running on MCP and storing data with SQLite and LanceDB. It preserves project context, decisions, and preferences across sessions and tools. I created it because coding agents frequently lose valuable context between sessions, especially on long projects. So, I'd love feedback from those who use coding agents regularly. What do you think should be auto-remembered versus what should always need explicit confirmation?