Keep Memories Accurate with Update

Mem0’s update operation lets you fix or enrich an existing memory without deleting it. When a user changes their preference or clarifies a fact, use update to keep the knowledge base fresh.

Key terms

• memory_id: Unique identifier returned by add or search results.
• text: New content that replaces the stored memory value. In the Python OSS SDK, data is a deprecated alias for text.
• metadata: Optional key-value pairs you update alongside the text.
• timestamp: Unix epoch (int/float) or ISO 8601 string to override the memory’s timestamp.
• batch_update: Platform API that edits multiple memories in a single request.
• immutable: Flagged memories that must be deleted and re-added instead of updated.

How the update flow works

1. Locate the memory
   Use search or dashboard inspection to capture the memory_id you want to change.

2. Submit the update
   Call update (or batch_update) with new text and optional metadata. Mem0 overwrites the stored value and adjusts indexes.

3. Verify
   Check the response or re-run search to ensure the revised memory appears with the new content.

Single memory update (Platform)

Python

from mem0 import MemoryClient

client = MemoryClient(api_key="your-api-key")

memory_id = "your_memory_id"
client.update(
    memory_id=memory_id,
    text="Updated memory content about the user",
    metadata={"category": "profile-update"},
    timestamp="2025-01-15T12:00:00Z"
)

JavaScript

import MemoryClient from 'mem0ai';

const client = new MemoryClient({ apiKey: "your-api-key" });
const memory_id = "your_memory_id";

await client.update(memory_id, {
  text: "Updated memory content about the user",
  metadata: { category: "profile-update" },
  timestamp: "2025-01-15T12:00:00Z"
});

Expect a confirmation message and the updated memory to appear in the dashboard almost instantly.

Batch update (Platform)

Update up to 1000 memories in one call.

Python

from mem0 import MemoryClient

client = MemoryClient(api_key="your-api-key")

update_memories = [
    {"memory_id": "id1", "text": "Watches football"},
    {"memory_id": "id2", "text": "Likes to travel"}
]

response = client.batch_update(update_memories)
print(response)

JavaScript

import MemoryClient from 'mem0ai';

const client = new MemoryClient({ apiKey: "your-api-key" });

const updateMemories = [
  { memoryId: "id1", text: "Watches football" },
  { memoryId: "id2", text: "Likes to travel" }
];

client.batchUpdate(updateMemories)
  .then(response => console.log('Batch update response:', response))
  .catch(error => console.error(error));

Update with Mem0 OSS

Python

from mem0 import Memory

memory = Memory()

# Replace the content
memory.update(
    memory_id="mem_123",
    text="Alex now prefers decaf coffee",
)

# Update content plus metadata and an expiration date (None clears it)
memory.update(
    memory_id="mem_123",
    text="Alex now prefers decaf coffee",
    metadata={"category": "preferences"},
    expiration_date="2030-01-31",
)

JavaScript

import { Memory } from "mem0ai/oss";

const memory = new Memory();

// Replace the content
await memory.update("mem_123", { text: "Alex now prefers decaf coffee" });

// Update content plus metadata and an expiration date (null clears it)
await memory.update("mem_123", {
  text: "Alex now prefers decaf coffee",
  metadata: { category: "preferences" },
  expirationDate: "2030-01-31",
});

// Update metadata only, leaving the stored text untouched
await memory.update("mem_123", { metadata: { category: "preferences" } });

In both OSS SDKs the content is optional: pass only metadata and/or an expiration date to update those while keeping the existing content. At least one of the three must be provided, otherwise the call raises.

data is a deprecated alias for text in both OSS SDKs (data= in Python, { data: ... } in JavaScript). It still works but logs a warning; prefer text. In JavaScript, passing a bare string is shorthand for { text }, so update(memoryId, "new text") also still works.

Tips

• Update both text and metadata together to keep filters accurate.
• Batch updates are ideal after large imports or when syncing CRM corrections.
• Immutable memories must be deleted and re-added instead of updated.
• Pair updates with feedback signals (thumbs up/down) to self-heal memories automatically.

MCP Alternative: With Mem0 MCP, AI agents can update their own memories when users correct information.

Managed vs OSS differences

Put it into practice

• Review the Update Memory API reference for request/response details.
• Combine updates with Feedback Mechanism to automate corrections.

See it live

• Support Inbox with Mem0 uses updates to refine customer profiles.
• AI Tutor with Mem0 demonstrates user preference corrections mid-course.