Builders
Software, hardware, robotics, AI systems, developer tools, creative technology, and research prototypes are welcome.
For the first time, some of the collaborators aren't people, and they don't clock out when the sprint ends.
Persistent synthetic teammates are taking a new seat in engineering work—not as autocomplete, not as a search box, but as something closer to a colleague who remembers the project and shows up again tomorrow.
HarborHack is where developers explore what software development looks like when a persistent synthetic teammate becomes part of the team.
At HarborHack 2026, every team works alongside a persistent AI agent, to find out how that collaboration works in practice: where it helps, where it doesn't, and how much still depends on human judgment.
This isn't a contest to see who can generate the most code.
It's a weekend to practice leading a team that includes a synthetic collaborator, and to see up close how the software development team is changing.
Event at a Glance
Harbor Walk West · Room 211
Friday through Sunday
Friday • 5:30 PM EDT
1–4 humans + AI agent
until HarborHack begins.
Add to Calendar
What should I do next?
Software, hardware, robotics, AI systems, developer tools, creative technology, and research prototypes are welcome.
Humans remain responsible for product direction, judgment, architecture, approval, review, safety, final decisions, and the final presentation.
Teams may use Claude, Codex, Gemini, GPT-based tools, open-source agents, local models, and other specialist tools alongside their AI teammate.
The shift
Traditional Hackathons
AI Hackathons
HarborHack
Participant journey
Imagine This
Your team arrives with an idea and begins working with your AI agent as a coordination partner. The first milestone is not more output; it is shared clarity.
Then the weekend begins. The HarborHack agent experience will continue evolving before the event.
Learn the theme, challenges, who should attend, and what makes HarborHack different. Primary action: register.
Join the participant channel, verify GitHub access, install Git and tools, configure specialist AI tools, review Challenge 2 requirements, and read the rules and Code of Conduct.
Individuals may register before forming a team. Human team size is configuration-backed. The AI agent used by every team does not count toward the human limit.
Receive final instructions, confirm your team, select or create a repository, review the schedule, and begin working with your team’s AI agent.
Establish the problem, users, outcome, success criteria, constraints, challenge selection, and how your AI agent will participate.
Recommended loop: Understand → Plan → Decide → Build → Review → Validate → Integrate → Repeat.
Devpost is the official submission destination.
No prerecorded project video is required. Every eligible team presents live.
Retain the repository, documentation, backlog, engineering history, and mission where available. Stay connected with CharlestonHacks.
Schedule
Resources
Event day guide
Loading event phase…
Loading next milestone…
Submit
Devpost is the official submission system. Submit a functional prototype addressing one or both challenges. Projects may include software, hardware, AI systems, robotics, developer tools, creative technology, and research prototypes.
Include a project description, source repository access whenever possible, your AI collaboration story, Challenge 2 local model documentation if applicable, and live presentation readiness. No prerecorded project video is required. Every eligible team presents live.
Present live
No prerecorded video is required. Teams present live.
Recommended -minute structure with minutes of judge Q&A: Problem; Solution; Working demonstration; How your AI agent participated; Important decision or turning point; Failure, surprise, or course correction; What the team learned; What comes next.
Rules and Code of Conduct
Rules and Code of Conduct must be reviewed and finalized by HarborHack organizers and appropriate legal counsel before publication. Reporting contact: .
Eligibility, human team size, permitted pre-event preparation, requirement that core work occur during HarborHack, AI-tool transparency, open-source and license compliance, original-work expectations, Challenge 2 restrictions, judging eligibility, and organizer authority.
Safety, privacy, responsible data use, respectful conduct, harassment prohibition, reporting concerns, and consequences for violations.
FAQ
Eligibility is being finalized by organizers.
No. Individuals may register before forming a team.
No. The AI agent is used by every team but does not count toward the human team-size limit.
Yes. Every HarborHack team works alongside a persistent AI agent as part of the team.
Yes. They may be used as specialist tools alongside the team’s AI agent, and humans make final decisions.
AI inference must run locally on team-controlled hardware with no cloud-hosted foundation-model inference or commercial pay-per-token AI inference APIs. Final requirements will be confirmed by organizers.
Yes, but beginners should test a small fallback model before the event and ask mentors for guidance when mentor support is configured.
They may prepare tools, learning, and setup. Core project work must occur during HarborHack unless final rules state otherwise.
Provide an accessible source repository whenever possible. If public access is not possible, follow final organizer instructions for judge access.
No prerecorded project video is required.
Every eligible team presents live using the configured presentation and Q&A durations.
Bring a laptop, charger, headphones, development tools, Git access, and any hardware needed for your project or local inference.
Mentor support instructions are configuration-backed and currently coming soon.
Yes, if the project satisfies the requirements for both challenges.
Teams are encouraged to continue the project and retain repository, documentation, backlog, mission, and engineering history where available.