getzep/graphiti

Project overview

Graphiti autonomously builds and queries temporal context graphs that track how facts change over time, supporting incremental updates without complete graph recomputation. It targets developers who need to manage frequently changing data through code, requiring external LLM and graph database dependencies.

Project type

MCP · AI Agent · RAG

Use cases

Knowledge Q&A · Automation

Deployment

Refer to project documentation

License

Apache-2.0

Best for

• Developers and AI engineers who need to build temporal knowledge graphs from changing data using a Python framework or REST API.

Key capabilities

• Autonomously builds context graphs from unstructured and structured data, handling changing relationships while preserving full temporal history.
• Provides a Model Context Protocol server implementation allowing AI assistants to interact with context graph capabilities through the MCP protocol.
• Provides a FastAPI-based API service for interacting with the API.
• Supports developer-defined entity and edge types upfront via Pydantic models, or lets structure emerge from data.

Limitations and risks

• Using LLM services without Structured Output support may result in incorrect output schemas and ingestion failures.
• High concurrency ingestion pipelines may cause LLM provider 429 rate limit errors.

Getting started

• Setup requires provisioning external dependencies including an LLM API and a graph database. The path to first success involves installing the core package, setting up a graph database such as Neo4j or FalkorDB via Docker, setting the OpenAI API Key environment variable, and initializing the graph by adding episodes.

Evidence and sources

• GitHub project description: Build Real-Time Knowledge Graphs for AI Agents
• GitHub repository metadata: {"primary_language":"Python"}
• README: Traditional RAG approaches often rely on batch processing and static data summarization, making them inefficient for frequently changing data.
• README: Graphiti continuously integrates user interactions, structured and unstructured enterprise data, and external information into a coherent, queryable graph.
• README: Graphiti is the open-source temporal context graph engine at the core of Zep's context infrastructure for AI agents.

Reviewed at: 2026-07-16T12:17:39Z