MCP Mem0 General — AI skill for Claude Code
OpenAI just added memory across your chats across your openAI account.
How to install MCP Mem0 General
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open ryaker/mcp-mem0-general and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What MCP Mem0 General does
OpenAI just added memory across your chats across your openAI account. But wouldn't it be awesome to have general AI memory across all your interactions with any and all AI tools, IDEs, chatbots.... Now if it supports MCP you can with https://mem0.ai/ Give Claude desktop memory. Give cursor or windsurf memory across sessions or different projects.
Alternatives in AI
- Llmwiki — Open Source Implementation of Karpathy's LLM Wiki 1.5k ★
- Nocturne Memory — A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents 1.3k ★
- Browserwing — BrowserWing turns your browser actions into MCP commands Or Claude Skill, allowing AI agents to control browse 1.2k ★
README
Mem0 MCP Server
A Model Context Protocol (MCP) server for integrating AI assistants with Mem0.ai's persistent memory system.
Overview
This server provides MCP-compatible tools that let any compatible AI assistant access and manage persistent memories stored in Mem0. It acts as a bridge between AI models and the Mem0 memory system, enabling assistants to:
- Store and retrieve memories
- Search memories with semantic similarity
- Manage different memory types (episodic, semantic, procedural)
- Utilize short-term memory for conversation context
- Apply selective memory patterns
- Create knowledge graphs from memories
Project Structure
The project code is located within the `src/mcp_mem0_general/` directory.
Installation Methods
Method 1: DXT Extension (Recommended)
The easiest way to install this MCP server is using the DXT extension format in Claude Desktop.
**Download**: [`mem0-mcp-server-0.1.0.dxt`](releases/mem0-mcp-server-0.1.0.dxt)
For detailed DXT installation instructions, see [CLAUDE_DESKTOP_INSTALL.md](CLAUDE_DESKTOP_INSTALL.md).
Method 2: Direct Installation (Current)
This server can be run directly from GitHub using `uvx` without needing to clone the repository or install it locally.
Running the Server
Ensure you have `uv` installed (`pipx install uv` or `brew install uv`).
You can test the server directly in your terminal:
# Make sure MEM0_API_KEY is set in your environment
export MEM0_API_KEY="your-mem0-api-key-here"
# Run the server using uvx
uvx git+https://github.com/ryaker/mcp-mem0-general.git mcp-mem0-general
The server should start and log its initialization steps.
Method 3: Manual Configuration in Claude Desktop/Cursor
- Find
uvxPath: GUI applications like Claude Desktop often don't use the samePATHas your terminal. Find the full path to youruvxexecutable by running this in your terminal:
Copy the output path (e.g., `/Users/yourname/.lwhich uvx
Related Skills
Awareness SDK
Local-first AI agent memory — one command, 13+ IDEs, works offline. Persistent memory for Claude Code, Cursor,
Mem0 MCP Selfhosted
Self-hosted mem0 MCP server for Claude Code. Run a complete memory server against self-hosted Qdrant + Neo4j +
N2n Nexus
Local-first MCP coordination hub. One local daemon serves multiple AI assistants across IDEs — shared meetings
Agent Migrate
Move your whole AI coding-agent setup between harnesses in one command: Claude Code & Codex → pi, opencode, oh
ClikCode
The harness that logs in all your favorite AI coding providers, in the terminal and in VS Code. Chats you can
Turnbook
Local long-term memory for AI agents. Keeps every conversation word for word, costs nothing to save, and is sh
Related Agents
CLI Subagents Antigravity
Runs a task in Google Antigravity (agy, Gemini models) on the user's Google account (CLI Subagents; extra Goog
Device Driver
Executes interactions on a physical Android device via ui.sh over ADB. Always invoked via the device-driver sk
Codex Second Opinion
Get an independent opinion from OpenAI Codex (GPT-5) on a design decision, an approach, a tradeoff, or an unfa