JacHacks SF is a one-day AI hackathon hosted by Jaseci Labs at Founders Inc. on July 26, $10,000+ in prizes, and a room full of builders shipping real projects in under 12 hours.

This is the third event in the JacHacks series. Our first two brought together 500+ hackers who shipped 150+ projects, and now we're bringing it to SF with sponsors including Google DeepMind, NVIDIA, Base44, Lovable, Koyal AI, and NSF.

What makes JacHacks different is it's built around Jac, an AI-native programming language designed for exactly the kind of agentic AI projects everyone's trying to build right now. You don't need to know Jac walking in. We run a workshop that takes you from zero to shipping in an hour. Total beginners, students, professionals, and founders are all welcome, and you don't need a team to sign up. Come solo and we'll match you at team formation.

Beyond the build, the day is stacked: a keynote from Prof. Jason Mars, a resume review + big tech recruiting workshop with Jeff Nguyen, and a YC application workshop with Mehul from Koyal AI (YC F25). Plus meals and snacks all day and merch for every builder.

About the challenge

Build something real in one day. Every project is eligible for track prizes. Judging is live and in person: 4-minute demos in parallel groups, with top teams doing a second-round demo before the closing ceremony. Working demos beat slide decks.

Get started

• Register on Luma — this is your official RSVP for the event. [https://luma.com/9x1573sw]
• Join the Discord — all announcements, schedule updates, and team matching happen there. Post questions in #ask-an-organizer.
• Get familiar with Jac — optional, but a head start never hurts. Check out jaseci.org and the open-source repo at github.com/jaseci-labs/jaseci. We'll teach you the rest at the workshop.
• Brainstorm ideas — thinking ahead is allowed and encouraged. Just remember all actual building happens during hacking hours (10:45 AM–7:15 PM).
• Register your team on Devpost — up to 4 people. No team? Come anyway, we'll match you at the event.

• Technical Execution
  Does the project work? Is the code clean, the architecture sound, and the demo stable? We're looking at overall engineering quality, from how well the pieces fit together to how gracefully it handles edge cases.
• Use of Jac and Jaseci
  How deeply does the project leverage what makes Jac unique? Projects that take full advantage of by llm(), walkers, graph-native data modeling, and single-file full-stack development will score significantly higher than those that use Jac superficially.
• Creativity and Innovation
  Is this a fresh idea? Does it approach a problem in a way we haven't seen before? We're not looking for another todo app. Show us something that makes us rethink what's possible with agentic AI.
• Presentation and Demo
  Was the 3-minute pitch clear, engaging, and well-structured? Could someone who knows nothing about your project walk away understanding what it does and why it matters?
• Impact and Novelty
  Does the idea matter? Is the approach fresh? We're looking for projects that solve a real problem in a way we haven't seen before. Specific, grounded, and genuinely interesting.
• Depth of Agentic Behavior
  Does your project actually behave like an agent? Show us real autonomous behavior: planning, memory, tool use, or multi-agent coordination. Wrapping an API call doesn't count.