Loading subscription status...
💡 Description
Graphiti is a framework for creating and querying knowledge graphs with temporal awareness, designed specifically for AI agents operating in dynamic environments. Unlike traditional Retrieval-Augmented Generation (RAG) methods, Graphiti continuously integrates user interactions, structured and unstructured business data, and external information into a coherent and queryable graph. The framework supports incremental data updates, efficient retrieval, and accurate historical queries without requiring a complete recalculation of the graph, making it ideal for developing interactive and contextual AI applications.
📝 JSON Entries
{
"mcpServers": [
{
"graphiti": {
"env": {
"NEO4J_URI": "bolt://localhost:7687",
"MODEL_NAME": "gpt-4.1-mini",
"NEO4J_USER": "neo4j",
"NEO4J_PASSWORD": "password",
"OPENAI_API_KEY": "sk-XXXXXXXX"
},
"args": [
"run",
"--isolated",
"--directory",
"/Users/<user>/dev/zep/graphiti/mcp_server",
"--project",
".",
"graphiti_mcp_server.py",
"--transport",
"stdio"
],
"command": "/Users/<user>/.local/bin/uv"
}
}
]
}🛠️ Tools
add_episodesearch_nodessearch_factsdelete_entity_edgedelete_episodeget_entity_edgeget_episodesclear_graphget_status
⚡ Features
- Episode management: add, retrieve, and delete episodes (text, messages, or JSON data)
- Entity management: search and manage entity nodes and relationships in the knowledge graph
- Search capabilities: Seek facts (edges) and node summaries using semantic and hybrid search
- Group management: Organize and manage related data groups with group_id filtering
- Graph maintenance: Clean the graph and rebuild indices