Advanced Memory Operations

Run richer add/search/update/delete flows on the managed platform with metadata, rerankers, and per-request controls.

Make Platform Memory Operations Smarter

Prerequisites

• Platform workspace with API key
• Python 3.10+ and Node.js 18+

Need a refresher on the core concepts first? Review the Add Memory overview, then come back for the advanced flow.

Install and authenticate

Python

1. Install the SDK

   pip install mem0ai
   
2. Export your API key

   export MEM0_API_KEY="sk-platform-..."
   
3. Create an async client

   import os
   from mem0 import AsyncMemoryClient
   
   memory = AsyncMemoryClient(api_key=os.environ["MEM0_API_KEY"])
   

TypeScript

1. Install the OSS SDK

   npm install mem0ai
   
2. Load your API key

   export MEM0_API_KEY="sk-platform-..."
   
3. Instantiate the client

   import MemoryClient from 'mem0ai';
   
   const memory = new MemoryClient({ apiKey: process.env.MEM0_API_KEY! });
   

Add memories with metadata

Python

1. Record conversations with metadata

   conversation = [
       {"role": "user", "content": "I'm Morgan, planning a 3-week trip to Japan in May."},
       {"role": "assistant", "content": "Great! I'll track dietary notes and cities you mention."},
       {"role": "user", "content": "Please remember I avoid shellfish and prefer boutique hotels in Tokyo."},
   ]
   
   result = await memory.add(
       conversation,
       user_id="traveler-42",
       metadata={"trip": "japan-2025", "preferences": ["boutique", "no-shellfish"]},
       run_id="planning-call-1",
   )
   

TypeScript

1. Capture context-rich memories

   const conversation = [
     { role: "user", content: "I'm Morgan, planning a 3-week trip to Japan in May." },
     { role: "assistant", content: "Great! I'll track dietary notes and cities you mention." },
     { role: "user", content: "Please remember I avoid shellfish and love boutique hotels in Tokyo." },
   ];
   
   const result = await memory.add(conversation, {
     userId: "traveler-42",
     metadata: { trip: "japan-2025", preferences: ["boutique", "no-shellfish"] },
     runId: "planning-call-1",
   });
   

Successful calls return memories tagged with the metadata you passed. In the dashboard, verify the trip=japan-2025 tag exists on the new memory.

Retrieve and refine

Python

1. Filter by metadata + reranker

   matches = await memory.search(
       "Any food alerts?",
       filters={"user_id": "traveler-42", "metadata.trip": "japan-2025"},
       rerank=True,
   )
   
2. Update a memory inline

   await memory.update(
       memory_id=matches["results"][0]["id"],
       text="Morgan avoids shellfish and prefers boutique hotels in central Tokyo.",
   )
   

TypeScript

1. Search with metadata filters

   const matches = await memory.search("Any food alerts?", {
     filters: { user_id: "traveler-42", "metadata.trip": "japan-2025" },
     rerank: true,
   });
   
2. Apply an update

   await memory.update(matches.results[0].id, {
     text: "Morgan avoids shellfish and prefers boutique hotels in central Tokyo.",
   });
   

Clean up

Python

1. Delete scoped memories

   await memory.delete_all(user_id="traveler-42", run_id="planning-call-1")
   

TypeScript

1. Remove the run

   await memory.deleteAll({ userId: "traveler-42", runId: "planning-call-1" });
   

Quick recovery

• Empty results with filters: log filters values and confirm metadata keys match (case-sensitive).

Metadata keys become part of your filtering schema. Stick to lowercase snake_case (trip_id, preferences) to avoid collisions down the road.

Tune Metadata Filtering

Explore Reranker Search