mem0
Universal memory layer for AI Agents
Mem0 is an intelligent memory layer for AI agents and assistants that enables personalized, context-aware interactions by remembering user preferences, conversation history, and agent-generated facts across sessions. It offers multi-level memory (user, session, agent), hybrid search combining semantic, keyword, and entity retrieval, and temporal reasoning for time-aware queries. Developers can deploy Mem0 as a library for prototyping, self-hosted server for team infrastructure, or zero-ops cloud platform, and integrate it via Python/JavaScript SDKs or REST API. The repository includes reference skills (SDK knowledge) and pipeline skills (automated integration workflows) for AI coding assistants.
Key Features
Use Cases
- 01Building personalized AI assistants that remember user preferences and conversation context across sessions
- 02Enhancing customer support chatbots with memory of past tickets and user interaction history
- 03Creating healthcare AI that tracks patient preferences and medical history for tailored care recommendations
- 04Developing productivity tools with adaptive workflows based on individual user behavior patterns
- 05Automating Mem0 integration into existing codebases using AI coding assistants with pipeline skills
- 06Building gaming environments that adapt to player choices and preferences over time
Related Skills
View moresuperpowers
An agentic skills framework & software development methodology that works.
skills
Skills for Real Engineers. Straight from my .agents directory.
skills
Public repository for Agent Skills
ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
mem0 — FAQ
What is Mem0 and what does it do?+
Mem0 is a universal memory layer for AI agents that enables them to remember user preferences, conversation history, and context across sessions. It uses hybrid search (semantic, keyword, entity) and temporal reasoning to retrieve relevant memories and personalize AI interactions.
How do I install Mem0 for Python development?+
Install the library with 'pip install mem0ai' for basic use, or 'pip install mem0ai[nlp]' followed by 'python -m spacy download en_core_web_sm' for enhanced hybrid search with BM25 and entity extraction. For production use, sign up at app.mem0.ai or run the self-hosted Docker server.
Which AI clients and coding assistants work with Mem0 skills?+
Mem0 agent skills work with Claude Code, Codex, Cursor, Windsurf, OpenCode, OpenClaw, and any tool supporting the skills standard. The skills are added via 'npx skills add' commands and provide SDK knowledge or automated integration pipelines.
Do I need an API key to use Mem0?+
Yes, Mem0 requires an LLM (default: OpenAI's gpt-5-mini) and embedding model (default: text-embedding-3-small) to function, so you'll need an OpenAI API key or configure alternative supported LLMs. For the Mem0 Platform, you'll also need a Mem0 API key from app.mem0.ai.
Is Mem0 free and open source?+
Yes, Mem0 is open source under the Apache 2.0 license. The library and self-hosted server are free to use, while the managed cloud platform offers a zero-ops production option with advanced features and proprietary optimizations.
How do I add Mem0 skills to my AI coding assistant?+
Install reference skills with 'npx skills add https://github.com/mem0ai/mem0 --skill mem0' for SDK knowledge, or pipeline skills like 'npx skills add https://github.com/mem0ai/mem0 --skill mem0-integrate' for automated integration workflows. Then invoke them in your assistant with commands like '/mem0-integrate'.
How do I install mem0?+
Open the source repository on GitHub and follow its README. mem0 is a skill — MCP Agents Market links you directly to the official repo.
Is mem0 free?+
mem0 is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.