Vibe Coding Discovermemobase
View on GitHubUser Profile-Based Long-Term Memory for AI Chatbot Applications.
Memobase is a user-profile-based long-term memory service for LLM apps: insert chat blobs, it batch-extracts structured profiles plus a time-aware event timeline, then returns prompt-ready context in <100ms. Self-hosted on FastAPI/Postgres/Redis with Python, Node, Go SDKs and an MCP server.
Use Cases
Add long-term user memory to LLM chatbotsBuild AI companions that remember usersExtract and store structured user profiles from chatTrack time-aware user events for temporal questionsInject retrieved memories into prompts via context APIUser analytics and persona trackingPersonalized tutoring and assistant appsCompare with mem0/zep on LOCOMO memory benchmarksIntegrate memory through Python/Node/Go SDKs or MCP
Built With
- Language
- Python
- Frameworks
- FastAPI · PostgreSQL · Redis · Docker · MCP · Pydantic · httpx · OpenAI SDK · Ollama
Tags
long-term-memory · user-profile · llm-memory · chatbot · rag · retrieval · embeddings · personalization · temporal-memory · fastapi · postgres · redis · python-sdk · mcp · batch-processing · memory-layer