Explore/framework/MemOS
M

MemTensor/MemOSActive

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

frameworkTypeScriptApache-2.0
GitHubCompare
Refreshed 2h ago
OverviewActivity52wAlternativesDocs
Stars11.9k
Forks1.1k
HF Downloads—30d
Last commit4d ago
Refreshed2h ago
Project healthActiveLast commit 4d ago.
Production readinessMVP-readySuitable for non-critical production use.
Risk notesApache-2.0Verify license before production use.
AgentHub Score
87 / 100
Composite score from 6 signals. How we score →
Active project
87Score
Growth
98A+
Activity
90A
Documentation
70C+
Maturity
94A+
Community
95A+
Production
58C
GitHub stars · 79 days observed11.9k +4.80% / 30d
snapshots
Repository activity · 79 days observedReal snapshots from pushed_at
inactivepushed
2026-07-262026-10-14
Practical assessment
Should you use it?

✓ Best for

  • Multi-agent orchestration
  • Production agentic workflows
  • Stateful long-running tasks

◎ Strengths

  • Stable API
  • Active release cadence
  • Strong GitHub community

✕ Not ideal for

  • Simple single-step automation
  • Teams without Python/ML expertise

⚠ Watch-outs

  • Breaking changes between minor versions
  • Ecosystem lock-in if tightly coupled
Technical details
What's inside
LanguageTypeScript
LicenseApache-2.0
Sourcegithub
Open source✗ No
Commercial use—
Docs—
Demo—
Paper—

AgentHub Score

87
Score 87/100
Top performer

Alternatives

E
ECC
279.0k · framework
95
R
rea
229.6k · framework
95
P
ponytail
163.3k · framework
95
C
cc-switch
144.2k · framework
95
Compare all →

Recent activity

Latest commit 4d ago4d ago
Indexed by AgentHub crawler2h ago
Monitor for new releasesongoing