AI Devtools Radar

Mem0

Memory & contextmem0.ai4 published changes

2 sources under watch

Change timeline

apihigh

Mem0 Python SDK: delete_all() now paginates through vector store in batches of 1000

Accounts with more memories than a single page will now have all memories deleted correctly instead of silently leaving the remainder behind.

Evidence
+delete_all() now paginates through the vector store in batches of 1000 instead of listing once, so accounts with more memories than a single page (most vector stores default to ~100) had the remainder silently left behind

github.com

featurehigh

Mem0 Node SDK: Added Qdrant server-side BM25 keywordSearch()

Qdrant vector store now supports server-side BM25 keyword search (requires Qdrant >= 1.15.2) without requiring a client-side BM25 dependency.

Evidence
+Add Qdrant server-side BM25 keywordSearch() (requires Qdrant >= 1.15.2) plus payload filter indexes, so keyword search runs without a client-side BM25 dependency

github.com · also seen at 1 more source

featurehigh

Fix critical security issue preventing metadata from overwriting identity fields (user_id, agent_id, run_id, actor_id)

Prevents unauthorized tenant scope escalation attacks where malicious metadata could move memories to different tenants

Evidence
+Stop `update()` metadata from overwriting or injecting `user_id`, `agent_id`, `run_id`, or `actor_id`. These identity fields are immutable after creation, so passing them in `metadata` can no longer move a memory into a different tenant's scope (#6278)

github.com

api

OpenAIStructuredLLM now reads OPENAI_BASE_URL instead of OPENAI_API_BASE

Configuration now matches official OpenAI SDK and other OpenAI-compatible providers; users may need to update environment variables

Evidence
+Read `OPENAI_BASE_URL` (was `OPENAI_API_BASE`) in `OpenAIStructuredLLM`, matching the official OpenAI SDK's environment variable and the rest of the OpenAI-compatible providers (#6322)

github.com