Skip to content

mem0

v2.0.3 Breaking

This release includes breaking changes for platform teams planning a safe upgrade.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agents ai ai-agents application chatbots chatgpt
+7 more
genai llm long-term-memory memory memory-management python state-management

Affected surfaces

auth breaking_upgrade

ReleasePort's take

Light signal
editorial:auto 8d

The PGVector adapter now supports rich filter operators in search(), keyword_search(), and list(). The /search endpoint no longer returns a 502 error when top‑level user_id, agent_id, or run_id are present; they are mapped to filters.

Why it matters: Adds robust filtering capabilities for Python SDK vector stores (PGVector) across all three search methods. Eliminates intermittent 502 failures in the /search API when those fields appear, improving reliability for SREs and developers.

Summary

AI summary

Fixed PGVector adapter to support rich filter operators and corrected /search endpoint handling of top‑level user/agent/run IDs.

Changes in this release

Deprecation Low

Top‑level user_id, agent_id, and run_id fields in /search are deprecated; use filters instead.

Top‑level user_id, agent_id, and run_id fields in /search are deprecated; use filters instead.

Source: llm_adapter@2026-05-26

Confidence: high

Bugfix Medium

PGVector adapter now supports rich filter operators in search(), keyword_search(), and list().

PGVector adapter now supports rich filter operators in search(), keyword_search(), and list().

Source: llm_adapter@2026-05-26

Confidence: high

Bugfix Medium

/search endpoint no longer returns 502 when top-level user_id, agent_id, or run_id are present; they are mapped to filters.

/search endpoint no longer returns 502 when top-level user_id, agent_id, or run_id are present; they are mapped to filters.

Source: llm_adapter@2026-05-26

Confidence: low

Full changelog

Mem0 Python SDK (v2.0.3)

Bug Fixes:

  • Vector Stores: PGVector adapter now supports rich filter operators (eq, ne, gt, gte, lt, lte, in, nin, contains, icontains, wildcard *, $or, $not) in search(), keyword_search(), and list(). Previously only exact-equality filters worked — operator dicts were silently stringified and returned zero results (#5263)

  • Server: Fixed /search endpoint returning 502 when user_id, agent_id, or run_id are sent as top-level request fields. The server now maps these into the filters dict before calling Memory.search(), matching the v3 API contract. Top-level entity ID fields are marked as deprecated in the OpenAPI schema and emit a warning log — clients should migrate to filters={"user_id": "..."} (#5263)

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track mem0

Get notified when new releases ship.

Sign up free

About mem0

Universal memory layer for AI Agents

All releases →

Beta — feedback welcome: [email protected]