Create and query dynamic knowledge graphs that adapt over time for AI agents.
From the README
pip install graphiti-core
- Build temporal knowledge graphs that evolve with every interaction — tracking what's true now and what was true before.
- Represent rich, structured context instead of flat document chunks or raw event streams.
- Query across time, meaning, and relationships with hybrid retrieval (semantic + keyword + graph traversal).
Excerpts from the project README on GitHub. Copyright and licensing remain with the respective authors.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeBuild Real-Time Knowledge Graphs for AI Agents
graphiti has 30.4k stars on GitHub. It has been forked 3.1k times. graphiti is written mainly in Python. It has been in active development since 2024. graphiti is available under the Apache-2.0 license. Its main topics are agents, graph, llms, rag.
What is graphiti?
Build Real-Time Knowledge Graphs for AI Agents
Is graphiti open source?
graphiti is an open-source project. It is released under the Apache-2.0 license.
Is graphiti free?
Yes. graphiti is free and open source — you can use, modify and self-host it.
What license does graphiti use?
graphiti is available under the Apache-2.0 license.
What language is graphiti written in?
graphiti is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/getzep-graphiti.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.