Mem0 Platform Integration

Mem0 is a managed memory layer for AI applications. It stores, retrieves, and manages user memories via API — no infrastructure to deploy.

Step 1: Install and authenticate

Python:

pip install mem0ai
export MEM0_API_KEY="m0-your-api-key"

TypeScript/JavaScript:

npm install mem0ai
export MEM0_API_KEY="m0-your-api-key"

Get an API key at: https://app.mem0.ai/dashboard/api-keys

Step 2: Initialize the client

Python:

from mem0 import MemoryClient
client = MemoryClient(api_key="m0-xxx")

TypeScript:

import MemoryClient from 'mem0ai';
const client = new MemoryClient({ apiKey: 'm0-xxx' });

For async Python, use AsyncMemoryClient.

Step 3: Core operations

Every Mem0 integration follows the same pattern: retrieve → generate → store.

Add memories

messages = [
    {"role": "user", "content": "I'm a vegetarian and allergic to nuts."},
    {"role": "assistant", "content": "Got it! I'll remember that."}
]
client.add(messages, user_id="alice")

Search memories

results = client.search("dietary preferences", user_id="alice")
for mem in results.get("results", []):
    print(mem["memory"])

Get all memories

all_memories = client.get_all(user_id="alice")

Update a memory

client.update("memory-uuid", text="Updated: vegetarian, nut allergy, prefers organic")

Delete a memory

client.delete("memory-uuid")
client.delete_all(user_id="alice")  # delete all for a user

Common integration pattern

from mem0 import MemoryClient
from openai import OpenAI

mem0 = MemoryClient()
openai = OpenAI()

def chat(user_input: str, user_id: str) -> str:
    # 1. Retrieve relevant memories
    memories = mem0.search(user_input, user_id=user_id)
    context = "\n".join([m["memory"] for m in memories.get("results", [])])

    # 2. Generate response with memory context
    response = openai.chat.completions.create(
        model="gpt-4.1-nano-2025-04-14",
        messages=[
            {"role": "system", "content": f"User context:\n{context}"},
            {"role": "user", "content": user_input},
        ]
    )
    reply = response.choices[0].message.content

    # 3. Store interaction for future context
    mem0.add(
        [{"role": "user", "content": user_input}, {"role": "assistant", "content": reply}],
        user_id=user_id
    )
    return reply

Common edge cases

• Search returns empty: Memories process asynchronously. Wait 2-3s after add() before searching. Also verify user_id matches exactly (case-sensitive).
• AND filter with user_id + agent_id returns empty: Entities are stored separately. Use OR instead, or query separately.
• Duplicate memories: Don't mix infer=True (default) and infer=False for the same data. Stick to one mode.
• Wrong import: Always use from mem0 import MemoryClient (or AsyncMemoryClient for async). Do not use from mem0 import Memory.
• Immutable memories: Cannot be updated or deleted once created. Use client.history(memory_id) to track changes over time.

Live documentation search

For the latest docs beyond what's in the references, use the doc search tool:

python scripts/mem0_doc_search.py --query "topic"
python scripts/mem0_doc_search.py --page "/platform/features/graph-memory"
python scripts/mem0_doc_search.py --index

No API key needed — searches docs.mem0.ai directly.

References

Load these on demand for deeper detail: