WeaveHacks 4: Multi-Agent Orchestration Hackathon with Weights & Biases

WeaveHacks is back, revamped (With OpenAI, Cursor, Redis, and CopilotKit) On June 6th - 7th 2026, come to the Weights & Biases SF office (no online component, sorry) to have the most fun building self-improving agents you'll have this year. This time, we're growing the team: orchestrating pipelines and wrangling swarms. Agent capabilities have advanced a lot over the last year — even by their own doing. This can mean better memory systems, new forms of RL and fine-tuning, new ways of dynamic tool creation, self improving loops like Ralph, GasTown etc. Agents that run while we go play with robot dogs--let's build agents that work together while we're away. We bring: A killer office with ultrawide monitors and standing desks Great food & drinks (breakfast, lunch and dinner) Expert judges A robot dog that yells at you Exciting new wandb tools for agents Whimsy You bring: Your ideas A readiness to actually show up & crank out code Good vibes Will you make an arena for agent training? A research team? A productivity colony? An agent bazaar for agent discover and hiring? A debate club? Civilization sim? A recursive self-improvement loop? How have you been thinking about wrangling the flood of agents? Whatever it is, no more excuses. This is your sign to build. If you don't know, WeaveHacks is our AI Agent Hackathon series. Our first one was last year in which over 200 builders came from across the country to network, build, and deploy agents. Due to popular demand, we are continuing the series. Here is a peek at what to expect, from our 3rd WeaveHacks event: https://x.com/wandb/status/2019207262221529596?s=20 EXPECT: 🎁 $15k+ in prizes 🐕🤖🤖 Unitree g2 pro robot dog Tons of food, snacks, drinks A handful of excellent sponsors, who will have onsite assistance for integrating their tools. Only a few though - no hours-long presentations at the start. We're here to hack. Expert judges who can offer specific feedback Partner prizes to be announced SCHEDULE: SATURDAY JUNE 6 9:00 AM: Doors open & breakfast 10:30 AM: Kickoff & initial presentation 11:15 AM: Hacking starts! 6:30 PM: Dinner SUNDAY JUNE 7 9:00 AM: Doors open, breakfast snacks 12:30 PM: Lunch 1:30 PM: Submissions due, judging begins 2:00 PM: Project presentations 3:30 PM: Finalist presentations 4:00 PM: CoreWeave Ventures office hours (tentative) 4:30 PM: Awards ceremony SPONSORS: Your host: Weights & Biases! We build Weave, the smoothest LLM tracing & observability platform. 2 lines of code to instantly understand what your agent is doing. https://wandb.me/use-weave Cursor. Built to make you extraordinarily productive, Cursor is the best way to code with AI. 👉 https://cursor.com/ Redis. The real-time data platform powering the fastest AI applications. Build agents with vector search, caching, and blazing-fast memory systems. https://redis.io/ CopilotKit. The agentic frontend stack & the company behind the AG-UI protocol. This protocol has been adopted by Google, Microsoft, AWS, LangChain & more, making it the easiest path for bringing AI functionality (like Generative UI) to full stack applications. copilotkit.ai JUDGES: Dominik Kundel | OpenAI Emmanuel Turlay | Weights & Biases by CoreWeave Nina Olding | Weights & Biases by CoreWeave Paige Bailey | Google DeepMind Redis TBA Aditya Thakur | Salesforce Atharva Gundawar | Markov Robotics. Previous WeaveHacks winner. Savir Dillikar | Previous WeaveHacks winner. Vibhakar Mohta | Nuro. Previous WeaveHacks winner. Bassim Eledath | Asurion. Previous WeaveHacks winner. APPLYING TO PARTICIPATE Apply on Luma! Participants in our past hackathons get an instant acceptance. Beyond that, we prioritize hackers who have some kind of project they've built that they can point to (it doesn't need to be polished at all). Github or Devpost links are fine. No specific experience is required. Note that we will likely hit max capacity on registrations before the event, so apply early, and mark yourself as going / not going as soon as you know (so you're not taking a slot from someone else). Come ready to build agents 🙂