adaptive-agent-memory-research

Can an agent learn what is worth remembering?

A local-first, model-agnostic memory system that decides what to keep from the measured future usefulness of past experience — not from what looks similar to your query.

Give Claude Code persistent project memory in two minutes

The memory engine this research is built on is dependency-free, offline, and works today on your project. Point any MCP client at it:

Your agent now has eight tools — memory_status, memory_search, memory_context, memory_get, memory_timeline, memory_add, memory_supersede, memory_rebuild_index — writing to a single append-only memory/events.jsonl in your repository. No API key, no vector database, no daemon, no cloud account, no pip install.

Prefer no MCP client? Everything works from the CLI:

This is the research engine, not a finished product. It is used daily by this project on itself, which is the strongest thing we can honestly say about it. Bugs, rough edges, and honest reports of both are welcome — see #36 if setup fights you.

The problem

An agent's context window is a workspace, not a memory. Once a conversation is compacted, whatever was dropped is gone — including the thing that turns out to matter three weeks later.