AI-Memory Hackathon: Building your own Agent LLM Wiki 🚀
"Instead of just retrieving from raw documents at query time, the LLM incrementally builds and maintains a persistent wiki" - Karpathy
Recently, Karpathy popularised the idea of LLM Wiki. We decided to give it a go and try to extend on that idea and build one together with you.
🏆 1,200€ Cash Pool
Main Prizes:
🥇 Prize: 600€ cash🥈 Prize: 400€ cash🥉 Prize: 200€ cash
🧰 Build LLM Knowledge Wiki
In this hands-on hackathon, you will use Cognee’s open-source memory engine to build your own LLM Knowledge Wiki
Your wiki should do three base operations:
IngestQuery + Self-improveLint
Check how Karpathy explains it here: https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f
💥 Show us what you got
You will have 3 minutes to stand out:
Present your idea and explain how you leverage agent self-improvementRun a live demo that showcases your agent in action
⏱️ Schedule
17:00 PM — Doors open + Networking17:30 PM — Opening remarks + Redis & Cognee demos18:00 PM — Hacking begins8:30 PM — Project Submission Deadline - finalists selection9:00 PM — Finalist presentation & judging9:30 PM — Awards ceremony10:00 PM — Event wrap-up & doors close
Limited spots available. Can't make it? Please cancel your RSVP so we can offer your place to someone else.
About Cognee:
Cognee is an open-source AI memory engine that transforms unstructured data into persistent, queryable memory. It enables AI agents to store, retrieve, and reason over information across time, making it possible to build more reliable, adaptive, and stateful AI systems.
