LiteLLM - Mem0

Usage

Python

import os
from mem0 import Memory

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

config = {
    "llm": {
        "provider": "litellm",
        "config": {
            "model": "gpt-5-mini",
            "temperature": 0.2,
            "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 thriller movies? They can be quite engaging."},\
    {"role": "user", "content": "I’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"})

TypeScript

import { Memory } from 'mem0ai/oss';

// Point Mem0 at your LiteLLM proxy. apiKey defaults to "sk-anything"
// (the proxy handles real auth); baseURL defaults to http://localhost:4000.
const config = {
  llm: {
    provider: 'litellm',
    config: {
      apiKey: process.env.LITELLM_API_KEY || 'sk-anything',
      baseURL: process.env.LITELLM_API_BASE || 'http://localhost:4000',
      model: 'gpt-5-mini',
    },
  },
};

const memory = new Memory(config);
const messages = [\
    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},\
    {"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},\
    {"role": "user", "content": "I’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."}\
];
await memory.add(messages, { userId: 'alice', metadata: { category: 'movies' } });

Config

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