Skip to main content
Go to documentation:
⌘U
Weaviate Database

Develop AI applications using Weaviate's APIs and tools

Deploy

Deploy, configure, and maintain Weaviate Database

Query Agent

Run agentic search over your Weaviate Cloud collections

Weaviate Cloud

Manage and scale Weaviate in the cloud

Engram

Persistent memory for LLM agents and applications

Additional resources

Integrations
Contributor guide
Events & Workshops
Weaviate Academy

Need help?

Weaviate LogoAsk AI Assistant⌘K
Community Forum

Memories

A memory is a discrete piece of information stored in Engram. Each memory has:

FieldDescription
idUnique identifier for the memory
contentThe text of the memory (e.g. "The user prefers dark mode")
topicThe category it belongs to (e.g. UserKnowledge)
groupThe memory group that defines how it was processed
project_idThe project this memory belongs to
user_idThe user this memory is scoped to (if user-scoped)
propertiesCustom scope properties attached to the memory (e.g. {"conversation_id": "abc"} for conversation-scoped topics)
created_atWhen the memory was created (RFC 3339)
updated_atWhen the memory was last updated (RFC 3339)
scoreRelevance score (only present in search results)

Memories are automatically embedded as vectors, making them searchable by meaning.

Questions and feedback

If you have any questions or feedback, let us know in the user forum.

Was this page helpful?