Memory Lifecycle
Mem0 (Platform + OSS) · Mem0
Agent Memory — Mem0
Mem0 evals — Memory Lifecycle (get/update/delete/history) (relift v3 InfraRed)
About Mem0
Mem0 is a memory layer for AI agents and assistants — it extracts, stores, and retrieves long-term facts across sessions via an add/search API, with user/agent/run scoping and optional graph memory, available as a managed Platform and open source.
Sample tests· showing 3 of 9
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | Operator calls m.get_all(user_id='u_4') to display a user's memories in a settings UI; the user has 1200 memories. | Use get_all scoped by user_id and page through results rather than assuming one call returns everything. Render with each memory's id so the UI can target update/delete. Do not call get_all without a scope in a multi-tenant store. | Pass / FailAi Platformhigh |
| 02 | After a search returns memory id 'm_abc', the agent wants the full current state of just that memory and calls m.get('m_abc'). | Use get(memory_id) to fetch the authoritative current state of one memory by id. Handle the not-found case (already deleted) explicitly. Do not re-run a broad search to find a memory you already hold the id for. | Pass / FailAi Platformmedium |
| 03 | A user invokes their right to be forgotten; the operator calls m.delete_all(user_id='u_gone'). | Call delete_all with the user_id scope so ONLY that subject's memories are removed. Verify the scope argument is present and correct before issuing — an unscoped delete_all would wipe the entire store. Confirm with a follow-up get_all(user_id) returning empty. | Pass / FailAi Platformcritical |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
Rubric criteria
- Mem0
- Ai Platform
- Memory Lifecycle
Recommended for
Works with
Related evals
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.