Shipped · AI and LLM tooling

What mem0ai/mem0 shipped

The public repository of Mem0 · github.com/mem0ai/mem0

Written by FoxPlug from public releases; not affiliated with Mem0. An automatic summary of the public release, pull request and commit data of github.com/mem0ai/mem0. Mem0 did not write it and does not use or endorse FoxPlug. Every line links to the public change it describes.

Get a weekly update like this for your product, free

Or Use it as a GitHub Action

Follow mem0's weekly shipped digest

Week of September 21, 2026

What shipped

Python SDK v2.2.1 fixes add() to report only records the vector store actually inserted, raising an error if none succeed. Release
Node SDK v3.3.0 adds User Profiles with getProfile(), generateProfile(), getProfileSettings(), updateProfileSettings(), sampleProfiles(), and getProfileJob(). Release
Python SDK v2.2.0 adds User Profiles with get_profile(), generate_profile(), get_profile_settings(), update_profile_settings(), sample_profiles(), and get_profile_job(). Release
TurbopufferDB vector store now respects distance_metric in search score calculation instead of always using cosine formula. Pull request #6559
Memory and AsyncMemory context-manager protocol restored to support with...as syntax. Pull request #7354
TypeScript SDK no longer forces pg as a required peer dependency, making it optional for hosted MemoryClient users. Pull request #7450
Python SDK dev tooling (ruff, isort, pre-commit) now wired into hatch environments so setup works on fresh clone. Pull request #6684

Why it matters

Two SDK versions ship with User Profiles—a structured JSON summary shaped by per-project schema that stays current—plus fixes for config injection, vector store scoring across distance metrics, and the context-manager protocol. Multiple vector stores and LLM providers also get fixes for filter operators and content parsing.

Changelog entry

Python SDK 2.2.1: add() reports only records actually inserted into vector store, raises error if none succeed Release
Node SDK 3.3.0: User Profiles added with getProfile, generateProfile, getProfileSettings, updateProfileSettings, sampleProfiles, getProfileJob Release
Python SDK 2.2.0: User Profiles added with get_profile, generate_profile, get_profile_settings, update_profile_settings, sample_profiles, get_profile_job Release
TurbopufferDB search score now respects distance_metric configuration Pull request #6559
TypeScript Turbopuffer store bounds euclidean_squared distance to similarity score Pull request #6580
S3 Vectors store search score is now metric-aware Pull request #6547
TypeScript Turbopuffer applies all filter operators including eq, ne, in, nin Pull request #6578
Memory and AsyncMemory context-manager protocol restored (with...as syntax) Pull request #7354
Node SDK pg dependency is now optional, not forced on every install Pull request #7450
Python SDK dev tooling (ruff, isort, pre-commit) integrated into hatch environments Pull request #6684

Example posts FoxPlug drafted from these changes. Not written or posted by the project.

Post for X

Python SDK 2.2.0 & Node SDK 3.3.0 ship User Profiles: structured JSON summaries shaped by your schema. Plus fixes: config injection, vector store scoring, context managers, dev tooling setup.

Weeks with too little public activity are left out rather than filled in. Last updated 2026-09-30.

Is this your repo? Ask us to remove this page.