Why I’m Building AgentFleet: From One Assistant to a Visible AI Team

#opensource #ai #productivity #showdev

Most AI tools still feel like hiring one very fast assistant.

That is useful, but it still breaks down for real work.

When I am working on something messy, I usually do not want one system to answer everything in a single thread. I want something closer to a team:

one part researching
one part planning
one part executing
clear checkpoints where the human steps in only when it matters

That idea is what pushed me to start building AgentFleet.

What I am trying to build

AgentFleet is an open-source multi-agent workspace where the workflow is visible.

Instead of hiding everything behind one chat box, I want the operator to be able to see:

which agent is doing what
where work is blocked
when coordination is happening
when a human decision is actually needed

My bet is that AI products become much more useful when they feel less like "one assistant" and more like "a visible team with roles and checkpoints."

Why the visible office metaphor

I know the obvious risk: a visual metaphor can help people understand a workflow, but it can also feel gimmicky.

I chose the office/team metaphor because I wanted the structure of the system to be legible at a glance. If there are researchers, planners, and executors, I want people to see that immediately instead of inferring it from hidden state.

I am still testing whether that tradeoff is actually worth it.

Current state

This is still early.

I am also in the middle of a rename from AgentsOffice / AgentOffice to AgentFleet, so some docs and screenshots still show the old name while I clean things up.

The repo is here:

https://github.com/DBell-workshop/AgentFleet