agentleFS
Sign inStart free
doobidoodoobidoo/mcp-memory-service/site/llms.txt

mcp-memory-service / site

llms.txt2.1k starsChanged 7 days agoApache-2.0View on GitHub

Open-source, self-hosted memory service for AI agents. It stores memories, finds them again by meaning (semantic search) and links them in a knowledge graph. Clients reach it over MCP (stdio or Remote MCP with OAuth 2.1), a REST API or a CLI. License: Apache 2.0. Install with pip install "mcp-memory-service[sqlite]" on Python 3.11 or newer. The default backend is SQLite-vec with a local ONNX embedding model; Cloudflare, hybrid sync and Milvus are optional backends. The service returns stored memories; it…

  • Installs packages

Trending

Steady talk.about the whole repository

Dec 2025: 0 mentionsJan 2026: 1 mentionFeb 2026: 0 mentionsMar 2026: 3 mentionsApr 2026: 1 mentionMay 2026: 9 mentionsJun 2026: 5 mentionsJul 2026: 6 mentionsAug 2026: 6 mentionsSep 2026: 3 mentionsOct 2026: 8 mentionsNov 2026: 6 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the doobidoo/mcp-memory-service repository that our weekly crawl found. There is no adoption data for this file yet.

Who's talking about doobidoo/mcp-memory-service

The biggest 5 of 53 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 53

Talked about on GitHub and Bluesky (53 times).

On GitHub · 50

45 more on GitHub

The file

Create a free account to mount
Files
llms.txt
# MCP Memory Service

> Open-source, self-hosted memory service for AI agents. It stores memories, finds them again by meaning (semantic search) and links them in a knowledge graph. Clients reach it over MCP (stdio or Remote MCP with OAuth 2.1), a REST API or a CLI. License: Apache 2.0.

Install with `pip install "mcp-memory-service[sqlite]"` on Python 3.11 or newer. The default backend is SQLite-vec with a local ONNX embedding model; Cloudflare, hybrid sync and Milvus are optional backends. The service returns stored memories; it is not a language model. Connecting it does not record conversations by itself: the client calls the store and recall tools.

## Site

- [Home](https://mcpmemory.services/): what the service is, how clients connect, comparison, questions
- [Live demo](https://mcpmemory.services/demo/): semantic search running in the browser with sqlite-vec and an ONNX model
- [Architecture diagram](https://mcpmemory.services/architecture/): the three ways into the service, with source references
- [Tutorial: persistent memory for claude.ai](https://mcpmemory.services/blog/remote-mcp-tutorial): Remote MCP with OAuth, step by step

## Documentation

- [README](https://github.com/doobidoo/mcp-memory-service/blob/main/README.md): overview, installation, supported clients
- [Setup guide](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/setup-guide.md): installation and client configuration
- [Integrations](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/integrations.md): supported clients and frameworks
- [Benchmarks](https://github.com/doobidoo/mcp-memory-service/blob/main/docs/BENCHMARKS.md): LongMemEval results, conditions and the commands to reproduce them
- [Wiki](https://github.com/doobidoo/mcp-memory-service/wiki): guides and troubleshooting

## Optional

- [Deployment landscape](https://mcpmemory.services/deployment/): where releases and the site are built and published
- [Source code](https://github.com/doobidoo/mcp-memory-service)
- [PyPI package](https://pypi.org/project/mcp-memory-service/)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free