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.

⭐ 12,203 stars on GitHub · 🍴 1,100 forks · 📜 License: apache-2.0 · 💻 Language: TypeScript

What is MemOS?

A self-hosted notes & knowledge management tool. Your data lives on your server — no vendor lock-in, no risk of provider shutdown.

Main components

• Unified Memory API: A single API to add, retrieve, edit, and delete memory—structured as a graph, inspectable and editable by design, not a black-box embedding store.
• Multi-Modal Memory: Natively supports text, images, tool traces, and personas, retrieved and reasoned together in one memory system.
• Multi-Cube Knowledge Base Management: Manage multiple knowledge bases as composable memory cubes, enabling isolation, controlled sharing, and dynamic composition across users, projects, and agents.
• Asynchronous Ingestion via MemScheduler: Run memory operations asynchronously with millisecond-level latency for production stability under high concurrency.
• Memory Feedback & Correction: Refine memory with natural-language feedback—correcting, supplementing, or replacing existing memories over time.

The biggest strength is no vendor lock-in — markdown/JSON data, easy to migrate between tools.

Best for researchers, devs, product people — anyone wanting a portable second brain across devices.

Topics: the project is tagged with popular topics:

• 🏷️ agent
• 🏷️ agentic-ai
• 🏷️ ai
• 🏷️ ai-agents
• 🏷️ chatgpt
• 🏷️ claude
• 🏷️ deepseek-harness
• 🏷️ dsh-plugin
• 🏷️ hermes
• 🏷️ llm

📸 Screenshots

Quick install

See the README for detailed install instructions. Most projects support Docker — if the repo has a Dockerfile, use:

git clone https://github.com/MemTensor/MemOS.git
cd MemOS
docker build -t MemOS .
docker run -d -p 8080:8080 MemOS

Minimum system requirements

⚡ Deploy fast on VSIS

Use the VSIS VPS Standard 4GB RAM / 2 vCPU / 50GB SSD (~150k/tháng) plan from VSIS.NET — high-speed VN-based VPS, 24/7 support, ideal for running MemOS smoothly.

🎯 Benefits:

• One-command docker compose up -d deploy in 2 minutes
• Dedicated IPv4, root access, unmetered domestic bandwidth
• Daily snapshot backup
• Free install assistance from the VSIS team

👉 See matching VPS plans at vsis.net

Resources

• 🔗 GitHub: MemTensor/MemOS
• 🌐 Homepage: https://memos.openmem.net
• 📚 Official docs: see README in the repo
• 💬 Community: GitHub Issues + Discussions

Article compiled from GitHub data on 31/10/2026. Star/fork counts may have changed — see live numbers via the GitHub link.