OptMem

OptMem gives an AI agent permanent memory in about 426 tokens of prompt and a small script. It's a Python CLI, wake, note, and recall, backed by an append-only log with a binary-tree cache for fast compressed retrieval. The compact prompt teaches the agent how to use it, and the storage design does the heavy lifting underneath.

The clever part is the architecture, not the surface. Fixed-width, append-only records let it find a memory in a single disk seek even as the log grows, so recall stays fast without a database or a vector store. It's from Victor Taelin, whose work on HVM, Kind, and Bend gives the systems thinking real credibility.

Free and open source, for solo builders and teams experimenting with agent memory.

The catch is that it's minimalist by design. This is a small, sharp memory CLI plus an integration prompt, not a full memory framework with retrieval strategies and knobs. The value here is the idea and the storage architecture, plug it in for what it is. If you need a rich, configurable memory layer, you'll outgrow it, but as a lean, fast primitive it's a genuinely smart piece of work.