

Hackathon: Building your own LLM Knowledge Wiki
ββπ§ AI-Memory Hackathon: Building your own Agent LLM Wiki π
β"Instead of just retrieving from raw documents at query time, the LLM incrementally builds and maintains a persistent wiki" - Karpathy
βRecently, 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.
βββπ $1,500+ Cash Pool
βMain Prizes
βπ₯ Prize: $800 cash
π₯ Prize: $500 cash
π₯ Prize: $200 cash
βRedis Prize:
βAirpods (one for each team member)
βRedis Hoodies (one for each team member)
β10k Redis cloud credits
βπ§° Build LLM Knowledge Wiki
βIn this hands-on hackathon, you will use Cogneeβs open-source memory engine to build your own LLM Knowledge Wiki
βYour wiki should do thee base operations:
βIngest
βQuery + Self-improve
βLint
βCheck how Karpathy explains it here: https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f
βπ₯ Show us what you got
βYou will have 3 minutes to stand out:
βPresent your idea and explain how you leverage agent self-improvement
βRun a live demo that showcases your agent in action
ββββ±οΈ Schedule
β12:00 PM β Doors open + Networking
β12:30 PM β Opening remarks + Redis & Cognee demos
β1:00 PM β Hacking begins
β4:30 PM β Project Submission Deadline - finalists selection
β5:00 PM β Finalist presentation & judging
β5:30 PM β Awards ceremony
β6:00 PM β Event wrap-up & doors close
ββTechnology & Venture Partners
βCognee
βRedis
βOpenAI
βPebblebed
βAbout Cognee
βCognee 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.
βAbout Redis
βRedis is a real-time context engine that unifies streaming and vector data to power intelligent applications and AI agents with instant awareness. It enables developers to process and serve dynamic context at sub-millisecond speed with enterprise-grade reliability, delivering highly responsive and personalized experiences at scale.
βAbout OpenAI
OpenAI is best known for driving the generative AI revolution through frontier models and practical consumer tools such as ChatGPT
βAbout Pebblebed
βPebblebed is a technical early stage VC founded by Pam Vagata (cofounder of OpenAI, ran AI for Stripe, inventor of FBLearner Flow); Keith Adams (founded Facebook AI Research, was chief architect at Slack, 20th engineer at VMWare) and Tammie Siew (former Sequoia Southeast Asia investor, former Sequoia & Notable Capital backed founder)