Skip to content

mem0

vts-v3.0.7 scope: ts Feature

This release adds 2 notable features for engineering teams evaluating rollout.

Published 1mo AI Agents & Assistants
✓ 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

Summary

AI summary

Add LMStudio embedding provider, opt‑in explainable search scores, parallel entity boosts, normalized Redis similarity, and correct OpenAI float encodings.

Changes in this release

Feature Medium

Adds LMStudioEmbedding provider for local embeddings via LM Studio server.

Adds LMStudioEmbedding provider for local embeddings via LM Studio server.

Source: llm_adapter@2026-06-10

Confidence: high

 —
Feature Medium

Adds opt-in `explain: true` option to `Memory.search()` with scoreBreakdown.

Adds opt-in `explain: true` option to `Memory.search()` with scoreBreakdown.

Source: llm_adapter@2026-06-10

Confidence: high

 —
Performance Medium

Parallelizes entity boost searches in `Memory.search()` to reduce latency.

Parallelizes entity boost searches in `Memory.search()` to reduce latency.

Source: llm_adapter@2026-06-10

Confidence: high

 —
Bugfix Medium

Normalizes similarity scores to [0, 1] in Redis vector store adapter.

Normalizes similarity scores to [0, 1] in Redis vector store adapter.

Source: llm_adapter@2026-06-10

Confidence: high

 —
Bugfix Medium

Requests `encoding_format: "float"` from OpenAI embedder to fix vector dimension issues.

Requests `encoding_format: "float"` from OpenAI embedder to fix vector dimension issues.

Source: llm_adapter@2026-06-10

Confidence: high

 —
Full changelog

Mem0 Node SDK (v3.0.7)

New Features:

  • Embeddings: Add LMStudioEmbedding provider for local embeddings via the LM Studio server (#5377)
  • Memory: Add opt-in explain: true option to Memory.search(). When enabled, each result includes a scoreBreakdown object with semantic, keyword, entityBoost, and temporalBoost fields so callers can inspect and tune retrieval ranking (#5102)

Bug Fixes:

  • Memory: Parallelize entity boost searches in Memory.search(). All entity embed + store lookups now run concurrently instead of sequentially, eliminating multi-second latency on entity-rich queries with remote embedding providers (#5377)
  • Vector Stores: Normalize similarity scores to [0, 1] (higher = better) — fixed score inversion in the Redis vector store adapter (#5391)
  • Embeddings: Request encoding_format: "float" from the OpenAI embedder in both embed() and embedBatch(). Fixes incorrect vector dimensions when using OpenAI-compatible proxies that default to base64 encoding (#5170)
View diff on GitHub

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

Share on X Share on Bluesky

Track mem0

Get notified when new releases ship.

Sign up free

About mem0

Universal memory layer for AI Agents

All releases →

Related context

Beta — feedback welcome: [email protected]