Semurg agent memory — MCP memory server for coding agents
Self-hosted memory for AI agents on your own hardware: a knowledge graph and vectors on one engine. Install it on Linux, then point your agent at it over MCP.
Open on GitHubWhat Semurg agent memory does
The node keeps notes and documents you hand to the agent. Each saved text is split into passages at sentence boundaries and linked to entities held in the graph, either already stored or sent alongside. The agent does the extracting itself by passing entities and relations in the same write call; the authors say that beats the node's own model running on CPU. Passages get vector embeddings when an embedding model is present on the machine.
Hardware first: x86_64 with AVX2 or newer, at least 2 CPU threads and 4 GB of RAM. Ubuntu 24.04 takes the installer; other x86_64 Linux distributions run in Docker. Nothing is published for Apple silicon, Windows or ARM, so from a Mac or a Windows box you reach a Linux node elsewhere. The data directory has to sit on a local ext4 or xfs volume, and the installer refuses to continue otherwise. Root is required, and a single node needs no licence key.
A scope is a namespace. Agents sharing a scope share facts; another scope stays private. In Claude the server is registered at user scope through claude mcp add-json and keeps only a reference to SEMURG_API_TOKEN. Other clients talk streamable HTTP to POST /v1/mcp with Authorization: Bearer <token> and an optional X-Semurg-Scope. The endpoint answers 401 without the token and 200 with it, so check that before trusting the setup.
What it helps with
- share one memory store across several agents
- attach entities and relations to text you save
- run vector search over notes without a hosted service
- keep each end user's memory apart inside one app
- confirm the MCP endpoint rejects requests without a token
Example prompts for the agent
- Save this note and send the entities and relations as facts in the same
memory_remembercall - Call
memory_statusfor scopedefaultand list the entity types it holds - Search memory for the deploy notes and quote the passage the answer came from
How to install Semurg agent memory
Install
The MCP registry has no launch command for it: see the repository README
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Semurg agent memory
How do I install Semurg agent memory in Claude Code?
Bring up the node on Linux with curl -fsSL https://one.semurg.io/install | sudo bash and copy the token from the final banner. Then run export SEMURG_API_TOKEN=<token> followed by `claude mcp add-json --scope user semurg '{"type":"http","url":"http://127.0.0.1:4000/v1/mcp","headers":{"Authorization":"Bearer ${SEMURG_API_TOKEN}","X-Semurg-Scope":"default"}}'`.
What does Semurg agent memory do?
It gives an agent long-term memory: text and facts go in, passages are tied to entities in the graph, and later calls search them. Everything runs through MCP over streamable HTTP.
Which machines can run the node?
Intel or AMD x86_64 with AVX2, 2 CPU threads and 4 GB of RAM at the minimum, on a local ext4 or xfs disk. The installer covers Ubuntu 24.04; elsewhere Docker is the route, and it needs root.
