Multi-agent AI means several AI agents working together on a task. Multiplayer AI means several people and agents working together in one shared session. If you work alone with your own agents, multi-agent is the one you need, and the free, MIT-licensed Friday desktop app does it on your own computer.
What is the difference?
| Multi-agent AI | Multiplayer AI | |
|---|---|---|
| Who is involved | Several agents | Several people and one or more agents |
| The main question | How do agents split up and hand off work? | How do people and agents work on the same thing? |
| Typical problem | Agents lose context or overwrite each other | People cannot see or steer what an agent is doing |
| What you need | Roles, hand-offs, shared state | A shared session, shared context, clear control |
What is multi-agent AI?
Multi-agent AI splits a job between agents with different roles, such as a planner, a builder and a reviewer. The agents pass work to each other until the job is done. It can run with no person involved at all, though one person reading the result is the usual setup.
What is multiplayer AI?
Multiplayer AI puts several people in the same session as the agents, so they see the same context and can steer. It works with a single agent too. It needs a shared place for the session. The free app on your own computer has none: it listens on 127.0.0.1 only, so nobody else can open your session.
Which do you need?
Alone, multi-agent is the half that matters: several agents, one person reading the result. A set of agents with nobody watching is automation, and it is hard to trust, so keep review in the loop. Multiplayer only matters once several people need the same live session.
How does Friday handle multi-agent work?
Friday runs Claude Code, Codex, Cursor and 13 more coding tools (16 by name, plus any ACP agent) side by side on your own computer and your own plans. One agent splits a job into a task board, the others pick up tasks, and another agent checks each finished task before it counts as done.
- Agents message each other as they work, so you do not relay questions between them.
- When a tool runs out of usage mid-task, the task moves to another agent with a record of what the first did and changed.
- Each agent can work in its own git worktree, so two agents do not change the same files.
- You review each run’s changes line by line, with git built in.
Friday is open source (MIT) and needs no account. Install it with npx github:splashxmoon/friday or from GitHub; see the docs. Friday Team is the hosted version for several people in one session, now in beta: join the waitlist.