Semantic search for memories using vector similarity.
Requires READ permission on memory resources.
Documentation Index
Fetch the complete documentation index at: https://heyhumm.ai/docs/llms.txt
Use this file to discover all available pages before exploring further.
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Search query text
Filter by status (defaults to approved) Memory review status.
pending_review, approved, rejected Maximum number of results
1 <= x <= 50Minimum similarity score
0 <= x <= 1Successful Response
Types of memories that can be extracted.
procedural, factual, contextual Memory content as markdown text that you want Humm to store.
Confidence score from 0.0 to 1.0 indicating how trustworthy this memory is.
0 <= x <= 1Thread UUID where this memory was observed or extracted.
Organization UUID for the tenant that owns this memory. For POST /memories, this must also match the organization_id query parameter.
User UUID associated with the source thread or memory author.
Scope of memory applicability.
organization, user Memory review status.
pending_review, approved, rejected Reasoning for extraction
Optional tags