Repository files navigation

Learn more ·Join Discord ·Demo

Mem0 (pronounced as "mem-zero") enhances AI assistants and agents with an intelligent memory layer, enabling personalized AI interactions. Mem0 remembers user preferences, adapts to individual needs, and continuously improves over time, making it ideal for customer support chatbots, AI assistants, and autonomous systems.

Core Capabilities:

• Multi-Level Memory: User, Session, and AI Agent memory retention with adaptive personalization
• Developer-Friendly: Simple API integration, cross-platform consistency, and hassle-free managed service

Applications:

• AI Assistants: Seamless conversations with context and personalization
• Learning & Support: Tailored content recommendations and context-aware customer assistance
• Healthcare & Companions: Patient history tracking and deeper relationship building
• Productivity & Gaming: Streamlined workflows and adaptive environments based on user behavior

Get started quickly withMem0 Platform - our fully managed solution that provides automatic updates, advanced analytics, enterprise security, and dedicated support.Create a free account to begin.

For complete control, you can self-host Mem0 using our open-source package. See theQuickstart guide below to set up your own instance.

Install the Mem0 package via pip:

pip install mem0ai

Install the Mem0 package via npm:

npm install mem0ai

Mem0 requires an LLM to function, withgpt-4o-mini from OpenAI as the default. However, it supports a variety of LLMs; for details, refer to ourSupported LLMs documentation.

First step is to instantiate the memory:

fromopenaiimportOpenAIfrommem0importMemoryopenai_client=OpenAI()memory=Memory()defchat_with_memories(message:str,user_id:str="default_user")->str:# Retrieve relevant memoriesrelevant_memories=memory.search(query=message,user_id=user_id,limit=3)memories_str="\n".join(f"-{entry['memory']}"forentryinrelevant_memories["results"])# Generate Assistant responsesystem_prompt=f"You are a helpful AI. Answer the question based on query and memories.\nUser Memories:\n{memories_str}"messages= [{"role":"system","content":system_prompt}, {"role":"user","content":message}]response=openai_client.chat.completions.create(model="gpt-4o-mini",messages=messages)assistant_response=response.choices[0].message.content# Create new memories from the conversationmessages.append({"role":"assistant","content":assistant_response})memory.add(messages,user_id=user_id)returnassistant_responsedefmain():print("Chat with AI (type 'exit' to quit)")whileTrue:user_input=input("You: ").strip()ifuser_input.lower()=='exit':print("Goodbye!")breakprint(f"AI:{chat_with_memories(user_input)}")if__name__=="__main__":main()

See the example forNode.js.

For more advanced usage and API documentation, visit ourdocumentation.

• Mem0 - ChatGPT with Memory: A personalized AI chat app powered by Mem0 that remembers your preferences, facts, and memories.

Try livedemo

• AI Companion: Experience personalized conversations with an AI that remembers your preferences and past interactions

• Enhance your AI interactions by storing memories across ChatGPT, Perplexity, and Claude using our browser extension. Getchrome extension.

• Customer support bot usingLanggraph and Mem0. Get the complete code fromhere

• Use Mem0 with CrewAI to get personalized results. Full examplehere

For detailed usage instructions and API reference, visit ourdocumentation. You'll find:

• Complete API reference
• Integration guides
• Advanced configuration options
• Best practices and examples
• More details about:
  • Open-source version
  • Hosted Mem0 Platform

Join our community for support and discussions. If you have any questions, feel free to reach out to us using one of the following methods:

• Join our Discord
• Follow us on Twitter
• Email founders

This project is licensed under the Apache 2.0 License - see theLICENSE file for details.