Vibe Coding DiscoverMemOS
View on GitHubSelf-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.
Memory OS for LLMs and AI agents: unified add/retrieve/edit/delete of long-term and multi-modal memory as an inspectable graph, with hybrid retrieval (vector + FTS5), async ingestion, skill evolution, and plugins for OpenClaw, Hermes and DeepSeek Harness.
Use Cases
give AI agents persistent long-term memorypersonalized assistants that recall user preferencescustomer support recalling past tickets and historymulti-agent shared or isolated memorymanage multiple knowledge bases as memory cubesreuse crystallized skills across tasksreduce token usage via hybrid memory retrievalon-device memory for OpenClaw/Hermes/DeepSeek Harness agents
Built With
- Language
- TypeScript
- Frameworks
- FastAPI · SQLAlchemy · FastMCP · OpenAI SDK · Ollama · Transformers · scikit-learn · Neo4j · Qdrant · SQLite · Docker · uvicorn
Tags
long-term-memory · agent-memory · memory-os · hybrid-retrieval · rag · mcp · self-evolving · skill-evolution · vector-database · knowledge-base · multi-agent · token-savings · context-management · local-first · sqlite · neo4j