About SelfMemory
SelfMemory is an open-source memory engine for storing and retrieving AI conversations and context across models. Memories can be added through MCP, an SDK, or a website, with organizational knowledge listed as a potential B2B use.
Key features
- 01Store and retrieve conversation memories across models
- 02Add memories through MCP, an SDK, or a website
- 03Designed for users and agents
- 04Intended for project and organizational context
Use cases
- 01Keep conversation context across different models
- 02Save and retrieve memories for agents
- 03Write content to memory through the SDK
- 04Bring project knowledge together for company AI systems
MCP support
SelfMemory supports adding memories through MCP. The README does not specify the tools or retrieval capabilities exposed to MCP clients.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.selfmemory.com/mcp/claude mcp add --transport http SelfMemory https://mcp.selfmemory.com/mcp/{"mcpServers":{"SelfMemory":{"type":"http","url":"https://mcp.selfmemory.com/mcp/"}}}Open in Cursor{"servers":{"SelfMemory":{"type":"http","url":"https://mcp.selfmemory.com/mcp/"}}}Open in VS Code{"mcpServers":{"SelfMemory":{"type":"http","url":"https://mcp.selfmemory.com/mcp/"}}}{"mcpServers":{"SelfMemory":{"serverUrl":"https://mcp.selfmemory.com/mcp/"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project README
SelfMemory
Store AI memories for you and your agents
It is a open-source universal memory engine where users can store and retrieve their AI conversations and context across different models. Users can add memories through MCP, SDK, or a website selfmemory.com Over time, this will evolve into a one-stop memory hub with note-taking and chatbot features. For B2B, it becomes a knowledge backbone, storing project context, organizational knowledge, documents, and data sources to power company-wide AI systems.
🚀 Quick Start
pip install selfmemory
from selfmemory import SelfMemory
memory = SelfMemory()
# Add memories
memory.add("Can you find the nearest BMW car showroom for me.", user_id="user")
# Search memories
results = memory.search("Can you find a car washing service near me?", user_id="user")
print(results)
📚 Full Documentation
Visit docs.selfmemory.com for complete documentation, guides, and examples.
Changelog: See CHANGELOG.md for a detailed list of changes and updates.
🤝 Contributing
We welcome contributions! CONTRIBUTING.md.
🔗 Links
- Discord: discord.com/invite/selfmemory
- Brand Assets (Logos, Slides, etc.): Storage Link
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.