What Graphiti does
Open source and originated by Zep. Graphiti turns conversations, business data, and documents into temporal Context Graphs — entities, relationships, and the timeline they live on. As facts change, Graphiti invalidates the old ones. Retrieval combines vector, full-text, and graph traversal in one call.
More accurate. Faster. Fewer tokens
Agent context and memory systems often trade one for another. Zep leads on all three.
- Retrieval latency
- 155 ms
- Context size
- 5,760 tokens
- Retrieval latency
- 162 ms
- Context size
- 4,408 tokens
What makes Graphiti different
Temporal by design
Every edge carries timestamps for when a fact became valid, when it stopped being valid, when Graphiti learned about it, and when it learned it was no longer true. Point-in-time queries follow from the data model.
Hybrid retrieval
Vector similarity, full-text search, and graph traversal in one ranked answer. No LLM-in-the-loop reranking, no orchestration layer to maintain.
Dynamic updates
New facts integrate immediately. Outdated facts are invalidated by temporal logic — preserved as history, removed from current state.
Pluggable backends
Runs on Neo4j, FalkorDB, and Amazon Neptune. Supports OpenAI, Azure OpenAI, Google Gemini, and Anthropic.
MCP Server
Connect Graphiti directly to Claude, Cursor, and other MCP-compatible clients. Give your tools graph-backed memory without changing your workflow.
Open source framework. Managed platform
Millions of governed Context Graphs, served in milliseconds, on top of Graphiti and Konig, Zep’s proprietary graph database service.
Graphiti
The framework.
One Context Graph per subject. The data model, the temporal logic, the hybrid retrieval API. Run it locally.
Zep
The Context Lake.
Millions of governed Context Graphs, served at sub-second latency. SOC 2, HIPAA, BYOC.
Contributing
We welcome contributions from the community. Bug fixes, documentation improvements, new features — your input makes Graphiti better.
- 01Report issues and suggest features on GitHub
- 02Improve documentation and examples
- 03Submit pull requests for bug fixes and features
- 04Answer questions on GitHub
Build with the community
Star the project
Help us reach more developers building the future of AI agents.
Read the docs
Comprehensive guides and examples.
