getzep/graphiti
Build Real-Time Knowledge Graphs for AI Agents
Graphiti helps AI agent builders and developers give their AI agents a deep, evolving understanding of information, much like a human's memory. It takes in messy, real-world data and structured facts, then organizes them into a temporal context graph that tracks how information changes over time. The output is a highly structured, queryable knowledge base that agents can use to make more informed decisions.
23,665 stars. Actively maintained with 21 commits in the last 30 days.
Use this if you are developing AI agents and need them to retain and recall complex, time-sensitive information, beyond what simple document retrieval or chat history provides.
Not ideal if you need a fully managed, enterprise-grade platform with built-in user management, dashboards, and guaranteed performance for large-scale production deployments without building the surrounding infrastructure.
Stars
23,665
Forks
2,339
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
21
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/getzep/graphiti"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Recent Releases
Related tools
neo4j/neo4j-graphrag-python
Neo4j GraphRAG for Python
microsoft/graphrag
A modular graph-based Retrieval-Augmented Generation (RAG) system
Hawksight-AI/semantica
Semantica 🧠— A framework for building semantic layers, context graphs, and decision...
FalkorDB/GraphRAG-SDK
Build fast and accurate GenAI apps with GraphRAG SDK at scale.
gusye1234/nano-graphrag
A simple, easy-to-hack GraphRAG implementation