Vibe Coding Discovergraphiti
View on GitHubBuild Real-Time Knowledge Graphs for AI Agents
Python framework for building temporal knowledge graphs that give AI agents time-aware memory. Ingests structured and unstructured episodes into Neo4j/FalkorDB and serves hybrid semantic+keyword+graph retrieval. Ships an MCP server.
Use Cases
Persistent long-term memory for AI agentsTracking facts that change over time with validity windowsGraphRAG alternative for dynamic, frequently updated dataBuilding enterprise/structured+unstructured knowledge graphsPoint-in-time historical queries over agent contextConversation and user-interaction memoryHybrid semantic + BM25 + graph traversal retrievalFeeding agent context via a bundled MCP serverCustom entity/edge ontology via Pydantic modelsIncremental real-time ingestion without batch recomputation
Built With
- Language
- Python
- Frameworks
- pydantic · neo4j · openai-sdk · falkordb · kuzu · amazon-neptune · opensearch · opentelemetry · langchain · langgraph · sentence-transformers · mcp
Tags
knowledge-graph · temporal-graph · agent-memory · graph-rag · hybrid-retrieval · neo4j · falkordb · embeddings · entity-resolution · provenance · ontology · incremental-ingestion · mcp-server · python · llm-memory · vector-search