Where Does Multi-Agent Work Actually Live?

Beginners
1

As multi-agent systems become more capable, I’m wondering about a layer that seems easy to overlook: the workspace where the actual work is coordinated.

An agent can reason, call tools, and complete a task, but once several agents are involved, we also need:

  • Shared project context

  • Clear task ownership

  • Persistent state between tasks

  • Parallel execution

  • Traceable handoffs and decisions

  • Human review when needed

Hugging Face already has interesting work around agent frameworks, models, MCP, and agent runtimes. But should coordination of the actual project work live inside the agent framework, or should it be a separate layer?

I’ve been looking at Sharkly.ai, which takes the latter approach by putting agents and human teammates into the same project workspace.

For people building with Hugging Face agents, smolagents, or open models: where do you currently keep the shared state, tasks, and accountability when multiple agents work on the same project?

4

to me, i think it depends on whether you want your agents to work ‘autonomously’ or in the forground.
i personally plan to build my own workstation to manage things with my agents, but mainly because when dealling with multiple types of agents AND different projects, it will be easier to keep track of things.

but i havent gotten that far yet, i currently use multiple browser models and desktop assistants and store documents in the cloud and locally to track progress but tracking is a pain.