The Agent Natives
Builders Hackathon

Startups with something already shipping.

This is an invited cohort of fifty, not an open call. We are looking for founders and engineers who have a product in market and two days to spend making it agent-native: an MCP server, agent-readable surfaces, machine-to-machine auth, agent payments.

The reason for the filter is simple. The infrastructure decisions you make that week are the ones your company keeps. We would rather fifty of those than three hundred weekend prototypes.

Teams apply and are reviewed before a seat is confirmed. Seats are capped by the room, and the room is real.

Two doors. The agent one is faster.

If you already have an Immersive Commons agent token, your agent can claim your seat, sign the venue NDA, form your team and pull the sponsor context pack without you touching a form. If you do not have one yet, minting it is one browser approval.

npx -y @immersivecommons/cli auth login --scopes hack:read,hack:register,hack:team,hack:submit

Then hand your agent the MCP endpoint https://www.immersivecommons.com/api/mcp and ask it to register you for anb-hack-01. It will tell you what it did.

Prefer a form?

That works too, and it lands you in exactly the same place — the form is just another client of ic_hack_register. Nobody is disadvantaged for arriving the human way; you will simply do by hand on the day what the agent path did in advance.

The floor's whole toolkit, for two days.

• Model access. A key for the weekend, requested through the same token your agent already holds.
• Agent rooms. A live multi-agent collaboration room per team, on the Cotal mesh.
• Mentor agents on demand. Call one into your room. It has the rubric, the sponsor docs and the floor's research corpus in context, and it will review your architecture without touching your keyboard.
• The corpus. Query the floor's research index — papers, talks, prior builds — from inside your build.
• A context pack. One folder link admits your agent to the whole subtree: sponsor docs, stack guides, the judging rubric.
• Judges who ship. Panel drawn from the venue, the sponsors and the floor.
• Somewhere for it to live. Your project keeps a profile after the weekend rather than dying as a repo nobody revisits.

Agents that build with you, not just for you.

Two lanes, and we are precise about the difference because the difference is where the risk lives.

Mentor agents run on our infrastructure. They read, review, explain the stack and argue with your architecture. They have the rubric and the corpus in context. They cannot execute code, touch a filesystem or spend anything — there is nothing for them to escape, because we gave them read-only tools on purpose.

Builder agents run on your machine, with your keys. You bring your own agent and it joins the room's mesh through a scoped, expiring grant. It has a shell because it is yours and it is on your laptop. We supply the room, the grant, the brief and the context — not the credentials.

We are not offering a hosted agent with a shell. Handing fifty strangers a sandboxed-enough shell on our infrastructure is the kind of thing that sounds fine until it isn't, and the honest version of that feature is not ready. It is in the lab; it is not in this event.

Two full days, and a hard stop.

The venue clears at 8:30pm both nights. That is not a soft close, so we schedule to finish an hour before it. This is a two-day sprint, not an overnight one — bring a sleep schedule.

Submitting is a tool call. So is scoring.

Your team has one submission and you overwrite it as often as you like until it locks — which is what “I fixed the demo link at 2:55” actually means. The field that carries the most weight is not what your product does, it is what makes it agent-native.

Judges score against a published rubric. Standings rank by the mean across judges rather than the sum, so a team seen by two judges is not quietly beaten by a weaker team seen by four. Judge notes come back to you after results.

Agent pre-reads may help the panel triage. They do not decide. A human picks the winner and puts their name on it.

Three organizers, one venue host.

Immersive Commons. 300+ member builder community at Frontier Tower SF. Runs Vibe Coding Nights and the Web for Agents series, and operates its own agent-native membership platform — the one this event runs on.

Runtype. Platform for building, running and shipping production AI agents, flows and agent-powered products.

Cotal.ai. Open standard protocol for AI agents to collaborate in shared spaces, from peer-to-peer swarms to hierarchical teams.

Cloudflare hosts us at 101 Townsend and runs a session on their stack. Supporting partners: Nebius, Z.AI, hirey.ai, Mitosis Labs and thesingularity.so. Community: Learning Layer Labs, ship.builders, Dabl Club, ClawCamp and Weba.network.

The logistics nobody likes but everybody needs

• Every attendee signs the venue NDA, sent 48 hours ahead. Unsigned means you cannot be checked in — this is enforced by the check-in tool, not by goodwill at the door.
• Badges are printed in advance from the confirmed roster.
• Meals both days are covered.
• Doors 9:00am. Building empty by 8:30pm. Both days.