Experience memory for LLM agents that act, built up one measured step at a time: no memory, examples, random bank, retrieval by state. Controls and per-task gain/loss after every rung. ALFWorld first.
Power your agent
Install from the publisher. Not a PlugMCP endpoint.
Host a copy with our keys and logs.
No packaged release in the registry yet. Follow the repository README.
Remote URL or a command on your machine? How the two installs differ
Run on PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
LaunchOverview
Experience memory for LLM agents that act, built up one measured step at a time: no memory, examples, random bank, retrieval by state. Controls and per-task gain/loss after every rung. ALFWorld first. Lend a GPU: run a 2-hour cell (#179). No GPU? Many CPU tasks under the milestone. Directions: docs/research-map.
Tools
No tool list yet. Remote servers get one after the first health check.
FAQ
Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.
No required environment variable is listed on this record.
Adaptive Agent Memory Research runs locally over stdio.
Last checked 2026-11-16. Experience memory for LLM agents that act, built up one measured step at a time: no memory, examples, random bank, retrieval by state. Controls and per-task gain/loss after every rung. ALFWorld first. Lend a GPU: run a 2-hour cell (#179). No GPU? Many CPU tasks under the milestone. Directions: docs/research-map.
From the publisher
README is not crawled yet. Open the repository
Experience memory for LLM agents that act, built up one measured step at a time: no memory, examples, random bank, retrieval by state. Controls and per-task gain/loss after every rung. ALFWorld first. Lend a GPU: run a 2-hour cell (#179). No GPU? Many CPU tasks under the milestone. Directions: docs/research-map.