{"data":{"slug":"memtensor-memos","name":"MemOS","tagline":"Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse","github_url":"https://github.com/MemTensor/MemOS","owner":"MemTensor","repo":"MemOS","owner_avatar_url":"https://avatars.githubusercontent.com/u/210160027?v=4","primary_language":"TypeScript","stars":10758,"forks":994,"topics":["agent","agentic-ai","ai","ai-agents","chatgpt","claude","deepseek-harness","deepseek-harness-plugin","hermes","llm","long-term-memory","mcp","memory","memory-management","openclaw","rag","self-evolving","self-hosted","skills","token-savings"],"archived":false,"github_pushed_at":"2026-08-18T11:47:13+00:00","maintenance_label":"Very active","stars_delta_30d":497,"url":"https://www.graphcanon.com/tools/memtensor-memos","markdown_url":"https://www.graphcanon.com/tools/memtensor-memos.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/memtensor-memos","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=memtensor-memos","description":"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.","homepage_url":"https://memos.openmem.net","license":"Apache-2.0","open_issues":84,"watchers":45,"ai_summary":"MemOS is a self-evolving operating system designed for Long-Short Term Memory (LSTM) systems and AI agents. It supports ultra-persistent memory, hybrid retrieval technologies, and enables the reuse of skills across tasks to save tokens.","readme_excerpt":"## 🚀 Quick Start\n\nMemOS is built around four entry points. Pick the one that matches your scenario.\n\n\n|              | Cloud API               | Self-Host          | MemOS Cloud Plugin       | Local Plugin                                     |\n| ------------ | ----------------------- | ------------------ | ------------------------ | ------------------------------------------------ |\n| Best for     | Your app, fully managed | Teams on own infra | OpenClaw users, zero ops | DeepSeek Harness, Hermes, or OpenClaw; on-device |\n| Setup        | Get an API key          | docker compose up  | openclaw plugins install | npm install + agent-specific setup               |\n| Infra needed | None (hosted)           | Neo4j + Qdrant     | None (uses MemOS Cloud)  | None (local SQLite)                              |\n| Data lives   | MemOS Cloud             | Your servers       | MemOS Cloud              | Your machine                                     |\n\n---\n\n### 🖥️ Self-Host the MemOS Service\n\nYou want to run MemOS as a REST service on your own machine or cluster.\n\n**Option A — Docker (recommended):**\n\n```bash\ngit clone https://github.com/MemTensor/MemOS.git\ncd MemOS\ncp docker/.env.example .env          # fill in your API keys in .env\ncd docker\ndocker compose up                    # starts MemOS API + Neo4j + Qdrant\n```\n\nThe API is served at `http://localhost:8000`.\n\n**Option B — Run with uvicorn (without Docker):**\n\n```bash\ngit clone https://github.com/MemTensor/MemOS.git\ncd MemOS\ncp docker/.env.example .env          # fill in your API keys in .env\n\n---\n\n## ⚖️ License\n\nMemOS is licensed under the [Apache 2.0 License](./LICENSE).","github_created_at":"2025-07-06T09:51:27+00:00","created_at":"2026-07-07T17:37:13.114134+00:00","updated_at":"2026-08-18T12:01:00.629085+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"}],"tags":[{"slug":"agent","name":"agent"},{"slug":"agentic-ai","name":"agentic-ai"},{"slug":"llm","name":"llm"},{"slug":"long-term-memory","name":"long-term-memory"},{"slug":"memory-management","name":"memory-management"}],"trust":{"provenance":{"is_fork":false,"github_id":1014729376,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-18T12:00:59.556Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":21,"days_since_push":0,"last_release_at":"2026-08-16T05:43:54Z","stars_delta_30d":497,"open_issues_delta_30d":4},"security_summary":{"status":"findings","scanner":"mcp_manifest@v1","low_count":2,"high_count":0,"last_scan_at":"2026-07-11T11:09:04.424Z","medium_count":0,"scan_profile":"mcp_manifest","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-18T12:01:00.047Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-08-18T12:01:00.047Z","managed_saas":false},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-08-18T12:01:00.047Z"},"languages":{"value":["typescript","python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-18T12:01:00.047Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-08-18T12:01:00.047Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-18T12:01:00.047Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"unknown","summary":"Pricing details are not clearly specified in the repository data, but the self-hosted option provides flexibility at the expense of managing infrastructure costs."},"requirements":{"notes":["Self-hosting MemOS typically requires setting up Neo4j and Qdrant. The cloud API or OpenClaw Cloud Plugin options do not require these components."],"requires_docker":true},"constraints":{"pricing_model":"unknown","requires_docker":true},"when_to_use":["If you require ultra-persistent memory management within your application for long-term storage.","For applications where token savings are significant benefits; MemOS can offer up to 35.24% in savings.","When deploying applications on self-managed infrastructure, especially with the need for custom configurations using Docker or without relying on cloud services."],"when_not_to_use":["If you prefer fully managed solutions and have no preference over where your data is stored (hosted in MemOS Cloud).","When minimal setup overhead is a critical requirement since self-hosting MemOS necessitates Neo4j and Qdrant for optimal performance.","In scenarios preferring simpler on-device solutions as MemOS could be more complex to set up compared to other lightweight plugins or services."],"source":"enrich:decision_facts","observed_at":"2026-07-11T15:58:12.879Z"},"constraint_facets":{"pricing_model":"unknown","requires_docker":true},"decision_summary":[{"label":"Pricing","value":"unknown - Pricing details are not clearly specified in the repository data, but the self-hosted option provides flexibility at the expense of managing infrastructure costs."},{"label":"Requirements","value":"Requires Docker; Self-hosting MemOS typically requires setting up Neo4j and Qdrant. The cloud API or OpenClaw Cloud Plugin options do not require these components."},{"label":"Adopt for","value":"MemOS is a self-evolving operating system tailored for LSTM systems and AI agents, offering ultra-persistent memory, hybrid retrieval technologies, and skill reuse across tasks."},{"label":"License detail","value":"MemOS is available under the Apache-2.0 license, allowing you to use it freely with certain conditions."}]}}