šŸ“¢ Announcing our research paper: Mem0 achieves 26% higher accuracy than OpenAI Memory, 91% lower latency, and 90% token savings! Read the paper to learn how we're revolutionizing AI agent memory.

You can use LLMs from Ollama to run Mem0 locally. These models support tool support.

ā€‹
Usage

import os
from mem0 import Memory

os.environ["OPENAI_API_KEY"] = "your-api-key" # for embedder

config = {
    "llm": {
        "provider": "ollama",
        "config": {
            "model": "mixtral:8x7b",
            "temperature": 0.1,
            "max_tokens": 2000,
        }
    }
}

m = Memory.from_config(config)
messages = [
    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
    {"role": "user", "content": "Iā€™m not a big fan of thriller movies but I love sci-fi movies."},
    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
]
m.add(messages, user_id="alice", metadata={"category": "movies"})

ā€‹
Config

All available parameters for the ollama config are present in Master List of All Params in Config.