Self-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path.
RCLL gives a whole fleet of AI agents one memory store. Every fact is scoped by room, typed by hall and tiered by layer, so a recall asks for exactly the slice it needs. · What is wrong with it · It runs with nothing outside the box · The read path never calls a model · Friday, then Monday
npm:fleet-memory-mcp
| Type | MCP server |
| Section | MCP servers |
| Pricing | free |
| Platform | Command line |
| Systems | cli, api |
| Hosting | local |
| Install | mcp |
| Protocols | mcp |
| Site language | en |
| GitHub | Holetron-lab/fleet-memory |
| Launched | 2026-08-28 |