fleet-memory
Level CLocalRCLL — self-hosted shared memory for a team of AI agents. Rooms, hierarchical L0-L3 depth, MCP. The read path never invokes a language model. We publish the measured cost of one shared store versus ten private ones. Fork of vectorize-io/hindsight (MIT).
Installation
MCP client config (paste into mcp.json)
{
"mcpServers": {
"fleet-memory": {
"command": "npx",
"args": [
"fleet-memory-mcp"
]
}
}
}Agent install prompt
Copy and paste into Cursor / Claude / other agents to install this MCP for you
Please read this MCP repository and install it into my current environment:
https://github.com/Holetron-lab/fleet-memory
Known working client config (can write into mcp.json):
{
"mcpServers": {
"fleet-memory": {
"command": "npx",
"args": [
"fleet-memory-mcp"
]
}
}
}
Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.
Related servers
mempalaceThe best-benchmarked open-source AI memory system. And it's free.private-gptComplete API layer for private AI applications on local models: RAG, skills, toocodebase-memory-mcpLocal code intelligence for developers and AI agents. Connect code, docs and infcontext-modeFree, local plugin that keeps tool output out of your coding agent's context wincogneeCognee is the open-source AI memory platform for agents. Give your AI agents pergraphitiBuild Real-Time Knowledge Graphs for AI Agents