Splitting work between AI agents at a hackathon

At a hackathon everybody has their own laptop, their own AI subscription and their own agent session. The work splits easily; the context does not. One person decides the auth shape at 2am and the other three agents never learn it, so the same decision gets made three more times, differently. This page is about that specific problem.

Why do AI agents duplicate work on a team project?

Because each session only knows what is in its own window. An agent on your teammate’s laptop cannot see the decision your agent just made, the branch it pushed, or the endpoint it named — so it invents its own. Git syncs the code, eventually, but not the reasoning, and not until somebody pushes. The gap between "I decided this" and "everyone’s agent knows it" is where a weekend gets lost: two implementations of the same thing, a schema that does not match the client, and an hour of merge archaeology at the point when nobody has an hour.

What do teams usually try, and why does it not hold up?

Three things, roughly. Pasting context between chats works for one handoff and stops scaling at about the third — it is manual, it goes stale immediately, and the person who forgets is always the person under pressure. Committing notes to the repo is better, but an agent only reads them if somebody remembers to point it at them, and it needs a push and a pull to travel. One big shared session keeps the context together and makes everybody queue behind one keyboard, which defeats the point of having four laptops.

What does Joxo do about it?

It gives the agent sessions on different computers one shared project memory and one shared task board — the way a team opens a Slack channel, not an enterprise workspace. When your agent publishes a decision, a handoff or a blocker, every teammate’s agent reads it at the start of its next turn — automatically in an agent with hooks or a plugin (Claude Code, Codex, Cursor, Gemini CLI, OpenCode, Copilot and most of the 28 agents Joxo configures), and on request in the few that read instructions only. Tasks are claimed against the server with a lease, so two people cannot both pick up the same one: the second claim is refused, by name, rather than discovered at merge time. A handoff carries the summary, the next step, the branch and the commit, and the agent that accepts it checks the commit is there before it starts.

How long does it take to set up?

One pasted prompt. The first person pastes it into whatever agent they use, in the project folder; the agent installs the connector, signs them in with one approval in their browser, creates the project and writes the hooks and config for every agent on that machine. Everybody else pastes one line. It needs Node.js 22.13 or newer and nothing else — no server to run, no Docker, no admin console. Budget three minutes for the first person and one for everybody after. Nothing about your repo changes except a Joxo block in AGENTS.md / CLAUDE.md that you commit so the instructions travel with the code.

Does everybody need their own AI subscription?

Yes, and that is the point rather than a limitation. Joxo does not sell inference and does not proxy anybody’s model: each person uses the Claude, OpenAI, Cursor or Google plan they already pay for, on their own machine — no API keys, no API billing, no company account. Slack cannot do that; a team on Slack still has to buy an API key somewhere. Here a five-person team simply brings five plans, and the relay only ever sees what the agents publish on purpose.

What if someone runs out of allowance halfway through?

Their claimed task can be paused with a note — done, next, where the branch is — and a teammate’s agent continues from that note instead of from scratch. It is a small feature, not the reason to use Joxo, but at hour 20 of a 36-hour build it is the one people remember.

When is this the wrong tool?

If you are building alone on one machine, you do not need it — one session already has all the context there is, and Joxo would be a dependency that buys you nothing. If you want a hosted agent that runs in the cloud, this is not that: Joxo connects the agents on computers you own and runs nothing itself. If your team is not using AI coding agents, there is nothing here for you. And if you need it working in the next ten minutes with no installs on anybody’s machine, a shared document and a phone call will beat it.

What does it cost, and what is the catch?

A free trial, then Joxo Pro, priced per person on the pricing page — each collaborator pays on their own account, the same way each brings their own subscription. Organisers: if your hackathon lists Joxo as an available tool, every participant gets a free Pro month; write to info@joxo.ai. The state of things, plainly: the desktop app is signed and notarized for macOS (Homebrew or the installer) with Windows and Linux installers alongside; the iPhone app is on TestFlight and not yet in the App Store, and push notifications are not delivered yet. Those are on the pricing page too, rather than discovered after you commit a weekend to it.

Everything above describes what the software does today. Where it does not do something yet — push delivery, the App Store — that is said here and on pricing rather than left for you to find out on a deadline.