Reference

Feedback API

Rate a memory's usefulness after you retrieve and use it. Positive feedback increases a memory's importance score over time; negative feedback decreases it. This signal feeds into the scheduled importance recalculation job and helps Neuroloom surface the most relevant memories first.

See Session Lifecycle for how feedback integrates with the broader memory health cycle.

Base URL and Authentication

https://api.neuroloom.dev

All requests require an API key:

Authorization: Token $MEMORIES_API_TOKEN

Rate a Memory

POST /api/v1/memories/{memory_id}/feedback

Record whether a memory was useful after you retrieved and acted on it. Call this after using (or deciding not to use) a retrieved memory to provide an explicit quality signal.

memory_rate(
  memory_id="mem-a1b2c3d4e5f6g7h8",
  useful=true,
  context="This pattern resolved the N+1 query issue in the sessions router. The selectinload hint was exactly what was needed."
)

The context field is optional but valuable — it gives the importance recalculation job a human-readable explanation for why the memory was helpful.

import httpx, os

response = httpx.post(
    "https://api.neuroloom.dev/api/v1/memories/mem-a1b2c3d4e5f6g7h8/feedback",
    headers={"Authorization": f"Token {os.environ['MEMORIES_API_TOKEN']}"},
    json={
        "useful": True,
        "context": "This pattern resolved the N+1 query issue in the sessions router.",
        "session_id": "sess-abc123",
    },
)
assert response.status_code == 201

curl -X POST "https://api.neuroloom.dev/api/v1/memories/mem-a1b2c3d4e5f6g7h8/feedback" \
  -H "Authorization: Token $MEMORIES_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "useful": true,
    "context": "This pattern resolved the N+1 query issue in the sessions router.",
    "session_id": "sess-abc123"
  }'

Path parameters

Parameter	Type	Description
`memory_id`	string	The `memory_id` of the memory to provide feedback on (e.g. `mem-a1b2c3d4e5f6g7h8`).

Request body

Field	Type	Required	Default	Description
`useful`	boolean	Yes	—	`true` if the memory was helpful in context, `false` if it was not.
`context`	string	No	`null`	Explanation of why the memory was or was not useful. Stored alongside the feedback record.
`session_id`	string	No	`null`	Session ID linking the feedback to a specific work session. Must belong to the same workspace — cross-workspace session IDs are silently ignored.

Response — 201 Created, the memory object the feedback was applied to.

{
  "id": "550e8400-e29b-41d4-a716-446655440000",
  "memory_id": "mem-a1b2c3d4e5f6g7h8",
  "title": "Use selectinload for SQLAlchemy relationship loading",
  "importance_score": 0.9,
  "feedback_positive_count": 6,
  "feedback_negative_count": 1,
  ...
}

feedback_positive_count and feedback_negative_count reflect the updated totals after this submission.

How Feedback Affects Importance

Feedback is not applied to importance_score immediately. It is incorporated during the scheduled importance recalculation job that runs periodically across the workspace. After the job runs, memories with net positive feedback will have a higher importance_score and appear earlier in search results.

The recalculation formula weights:

feedback_positive_count — increases importance
feedback_negative_count — decreases importance
access_count and retrieval_count — recency and frequency of use
Original confidence_score — baseline trust in the memory

Note

You can view the current feedback_positive_count and feedback_negative_count on any memory by calling GET /api/v1/memories/{memory_id}. These totals update immediately after feedback is submitted, even before the recalculation job runs.

When to Submit Feedback

Submit positive feedback when a retrieved memory directly helped you complete a task or make a decision. Submit negative feedback when a retrieved memory was outdated, incorrect, or irrelevant to the context it appeared in.

The MCP memory_rate tool is designed for use at the end of a task, after you have evaluated whether the retrieved context was genuinely useful. If you used memory_search or memory_get_detail to retrieve a memory, call memory_rate once you know whether it helped.

Error Responses

Status	When
`401 Unauthorized`	Missing or invalid `Authorization` header.
`404 Not Found`	The `memory_id` does not exist in the authenticated workspace.
`422 Unprocessable Entity`	`useful` field missing or not a boolean.

{ "detail": "Memory 'mem-notexist' not found." }

Memory Lifecycle — how feedback signals feed into importance score recalculation
What is a Memory — importance score fields and their meaning

Ready to get started?

Start building with Neuroloom for free.

Start Building Free