An OS-inspired memory layer for personalized AI agents that organizes user memory into short-, mid-, and long-term tiers and migrates entries between them via heat-based promotion/demotion. Four core modules: Storage, Updating, Retrieval, and Generation. Published as an EMNLP 2025 Oral.
- Storage
- Segmented-page storage with a heat-based updating mechanism that promotes/demotes memory across short / mid / long-term tiers; ChromaDB vector database supported as an alternative backend.
- Retrieval
- Retrieves relevant context from short-term history, mid-term segments, and long-term user profile/knowledge base; supports BGE-M3 and all-MiniLM-L6-v2 embeddings; configurable similarity_threshold and retrieval queue capacity.
- Self-host
- Self-host: moderate
- License
- Apache-2.0
- Pricing
- Open source (Apache-2.0), free to self-host · Free / OSS
- GitHub stars
- 1,551
- Last release
- 2025-07-18
- Last commit
- 2026-07-07
- First catalogued
- 2026-06-28
Strengths
- Peer-reviewed (EMNLP 2025 Oral); authors report a 49.11% F1 gain on LoCoMo (self-reported, not independently reproduced — route to harvest-benchmarks)
- OS-style tiered memory with heat-based promotion/demotion
- First-party MCP server (local-stdio) for Claude Desktop, Cline, and Cursor
- Python SDK on PyPI (memoryos-pro); Docker image available
- Permissive Apache-2.0 license
Watch out
- Name collides with the separate MemTensor MemOS project — they are different systems
- No versioned GitHub release since V1.2 (2025-07-18); repo does see periodic bug-fix commits (e.g. a thread-safety fix to the MCP/playground stores landed 2026-07-06/07) but maintenance cadence is research-project-paced, not release-driven
- Python SDK at v0.1.0 (single PyPI release as of 2025-07-09); API surface may change
Best for
- Personalized conversational agents needing tiered long-term user memory
- Claude Desktop / Cursor / Cline setups wanting plug-in memory via MCP
How it integrates
Benchmark results
No sourced results yet.
Sources
- Monthly card re-verification — GitHub API repo metadata: 1,536 stars, license Apache-2.0 confirmed, archived=false, last commit on the default branch 2026-07-07 (third-party)
- https://github.com/BAI-LAB/MemoryOS (vendor)
- https://arxiv.org/abs/2506.06326 (paper)
- MemoryOS-MCP server source and mcp.json config (vendor)
- memoryos-pro on PyPI (vendor)
- GitHub API — stars, pushed_at, archived status (vendor)
- GitHub commit history re-check — thread-safety fix propagated to memoryos-mcp and memoryos-playground (2026-07-06/07); no new versioned release since V1.2; repo not archived (third-party)
Last verified 2026-08-01 · updated by refresh-framework-cards