MemTensor/MemOS

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

11.9k stars · 1.1k forks · TypeScript

Healthy

Healthy: maintained by 22 people in the last 90 days, no known risks.

Why

No rule fired.

What would change this

Maintenance

Partial

Slowing

Human commits, 30 days
17
Human commits, 90 days
202
Human commits, 365 days
1.9k
Bot share of commits, 365 days
3%
Last commit
Sep 22, 2026 (23 days ago)
Last human commit
Sep 22, 2026 (23 days ago)
Authors, 90 days
22
Last release
Sep 23, 2026 (22 days ago)
Median PR merge time
3 hours

Responsiveness: of 26 recent issues, 100% got a maintainer reply. Median first response: under an hour.

Sources: Commits, Releases, Merged pull requests, Issues

People

Complete
Owner
Organization
Commits sampled
486 since Oct 14, 2025
Authors for half of commits
7
Authors for 80% of commits
15
Contributors
84

Top committers

The top committer changed during this period.

Sources: Commits, Contributors

Stars

Complete

Organic, confidence high

Stars per week, 2025-07-06 to 2026-10-11. 11 weeks overlap a burst.Peak 1.3k a week2025-07-062026-10-11
Bars show stars gained each week. Orange bars overlap a burst.

Bursts

Anyone can buy stars for any repo; bursts alone don't prove the owner did.

Sources: How star history is analyzed

Risk

Complete

Flags

No risk flags.

License

Now
Apache-2.0 (OSI-approved)
A year ago
Apache-2.0 (OSI-approved)

Packages

Package and advisory data: deps.dev and OSV.

Sources: GitHub: MemTensor/MemOS, deps.dev: PyPI MemoryOS

Badge

Add this to a README to show the current verdict:

[![RepoRadar](https://reporadar.ai/MemTensor/MemOS/badge.svg)](https://reporadar.ai/MemTensor/MemOS)

Earlier verdicts

Computed 7 hours ago · method 2026.10.2