
Graphiti
Build personalized AI agents that learn from dynamic data
417 followers
Build personalized AI agents that learn from dynamic data
417 followers
Graphiti is Knowledge Graph-based memory for AI agents. Automatically build rich graphs from changing business data & chat histories. Enable your Python agent with fast access to relevant, accurate data, even as it evolves over time. Visit our GitHub repo!














I'm genuinely impressed. @Graphiti might solve the long lived issue we've just discussed with the team in application to agentical memory being "not human enough".
Graphiti
@vladzima Glad to hear it! We'd love to see how Graphiti could be of use to your dev team.
Langfuse
Congrats on the launch! We continue to see across @Langfuse users that memory is crucial for creating meaningful agents capable of engaging in long conversations and providing a personalized experience. Well done, Team Zep!
Graphiti
@marc_klingenGreatly appreciated! A lot of work to be done to get agentic personalization right.
Stripo.email
Excited to see this in action! AI remembering past interactions is key for personalization—Graphiti sounds like the missing piece. What’s next on your roadmap?
Graphiti
@marianna_tymchuk We just added custom ontologies and currently working on a few more features to to fully utilize them. We are also looking for community suggestions! You can find us at https://discord.gg/2JbGZQZT
Graphiti
@marianna_tymchuk Thanks! Right now we are working on a project that enables users to add a custom entity schema to increase the breadth and quality of data extraction, as well as enhance search capabilities.
Permit.io
Graphiti’s approach to evolving data feels like a breakthrough, especially for systems where user context shifts over time. It’s refreshing to see a framework that keeps AI “memory” accurate and current. Can’t wait to explore it for context-heavy chatbots!
Graphiti
@gemanor Thank you!
Huge potential here! AI-powered customer support, sales assistants, and chatbots could all benefit from better long-term memory. Wishing you all the success with Graphiti!
Graphiti
@samulskaya Thank you!
Looks really interesting! Curious to see how this can be implemented for the whole team on GitHub.
Graphiti
@boatbuilder Thanks! Zep builds on Graphiti's temporal knowledge graph by providing a complete memory management layer. It introduces concepts such as user and group graphs and handles the infrastructural overhead of running Graphiti in your stack.