Memory systems
MemOS
Memory operating system with graph-structured long-term memory
Open source
★ 12,343 on GitHub · +3 today · last commit Nov 9, 2026
What it is
Our note
Skill reuse; claims 43.70% lift vs OpenAI Memory, 35.24% token savings (self_reported)
At a glance
- Vendor
- MemTensor
- Business model
- Open source
- License
- Apache-2.0
GitHub activity
This product has a public repository, so we read it nightly from the GitHub API. Stars measure developer attention, not quality or market share.
“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.” (repository description)
- Stars
- 12,343
- Change since last reading
- +3
- Forks
- 1,117
- Open issues
- 165
- Last commit
- Nov 9, 2026 (0 days ago)
- License (GitHub)
- Apache-2.0
Links and sources
- Official sitememos.openmem.net
- GitHub repositorygithub.com/MemTensor/MemOS
Added nov 8, 2026. Vendor facts come from the vendor’s own pages; benchmark claims are self-reported unless we say otherwise.