Understand the project
Practical overview
When it fits
Use Graphiti when an AI application must combine changing conversations, profiles or other structured and unstructured data while retaining historical context and source provenance.
Who it is for
- Developers building AI agents with evolving context.
- Teams creating agent memory or retrieval-augmented generation systems.
- Python developers who want a self-managed knowledge-graph framework.
Documented uses
- Store time-sensitive entities and relationships for agent memory.
- Track how facts and relationships change over time.
- Retrieve context using semantic, keyword and graph-traversal methods.
- Build knowledge-graph-backed RAG applications with historical context.
- Trace derived facts back to the raw episodes that produced them.
Before you choose
Requirements & limits
The repository is public, active in the supplied status data, and licensed under Apache-2.0. The documented deployment model for Graphiti is self-hosted.
- Temporal validity windows distinguish current facts from superseded ones.
- Episodes preserve the source stream behind derived entities and relationships.
- Incremental updates avoid requiring complete graph recomputation.
- Hybrid retrieval combines semantic search, keyword search and graph traversal.
- Graphiti requires developers to provide the surrounding application, tools and third-party graph database.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Evidence and transparency
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 30 September 2026
- Original website title
- getzep/graphiti · Official homepage title · retained in its source language
Related options
Zep — The repository documentation describes Zep as a managed context-graph service built around Graphiti's open-source framework, while Graphiti is the self-managed framework for buildi
Explore project →