JacHacks is a virtual hackathon (May 15 - May19) where participants build real agentic AI applications using Jac, an AI-native programming language developed at the University of Michigan. Backed by NVIDIA and the NSF, this is a space for builders who want to go beyond the surface and create agents that actually do things.

Whether you're new to agentic AI or already deep in it, there's a track for you.

Get started

Registration is open now! The hackathon runs virtually from May 15-19, 2026. Once you're registered, join our discord to meet your fellow hackers, get resources, and stay up to date as we get closer to kickoff.

Pick a track, form a team, and start thinking about what you want to build. We'll handle the rest.

Details

  • Teams: 1–4 people
  • Skill Level: All levels welcome
  • Cost: Free
  • Format: Virtual
  • Perks: Networking, mentorship, gain valuable experience, learn new skills, and real job opportunities

Requirements

What to Build

Build an agentic AI application using Jac. Your project should demonstrate real agent behavior (planning, tool use, memory, multi-step reasoning, or any combination). We're looking for projects that show what's actually possible with AI-native tooling, not just a UI wrapped around an API call.

Pick a track that fits your idea and build toward it.

What to Submit

  • A working demo or prototype (deployed or runnable locally)
  • A 3-minute max demo video showing your project in action
  • Your source code in a public GitHub repository
  • A written description on Devpost covering what you built, how it works, what track you're submitting to, and what Jac/Jaseci features you used

Optional but encouraged: A brief write-up of what broke, what surprised you, and what you'd do next.

Hackathon Sponsors

Prizes

$4,200+ in prizes
+ other prizes
Agentic AI track - 1st place
$600 in cash
1 winner

Agentic AI track - 2nd place
$400 in cash
1 winner

Consumer Healthcare track - 1st place
$600 in cash
1 winner

Consumer Healthcare track - 2nd place
$400 in cash
1 winner

Fintech track - 1st place
$350 in cash
1 winner

Fintech track - 2nd place
$150 in cash
1 winner

Social Impact track - 1st place
$350 in cash
1 winner

Social Impact track - 2nd place
$150 in cash
1 winner

Best Use of Jac
$300 in cash
2 winners

Best Demo
$200 in cash
1 winner

Best LinkedIn Post
$100 in cash
1 winner

Best Startup Idea
3 winners

Fast-track interviews with PearVC

Best Use of Lovable
1 winner

2 months of Lovable pro for free

Best Use of Featherless.AI
$300 in cash
1 winner

$300 in Featherless Credits for overall winner

Devpost Achievements

Submitting to this hackathon could earn you:

Judges

Ponita Ty
Growth Engineer @ Jaseci Labs

Sacchit Mittal
Founding Engineer @ Soma

Noah Liu
Co-Founder @ WeKruit

Dhruv Bahl
SWE @ ATT

Shaurya Singh

Shaurya Singh
Wyn

Sanjay Mishra

Sanjay Mishra
Principle Software Engineer @ Fidelity

Vatsal Shah
Amplify

Aritra Saha

Aritra Saha
Co-Founder @ Vene

Jayanaka Dantanarayana
Jaseci

Lingjia Tang
Jaseci Labs

Jason Mars
Jaseci Labs

Kunj Raval

Sujal Dhakal
Co-Founder @ Vene

Nik Nandi
Co-Founder @ Vene

Judging Criteria

  • 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.

Questions? Email the hackathon manager

Tell your friends

Hackathon sponsors

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.