Agents

Agents are AI coding sessions launched and managed from inside Solo. They run alongside your project commands and terminals, can be connected to MCP tools, and can use Solo context to inspect processes, coordinate work, and hand off progress.

What are agents?

Agents in Solo are AI coding tools that you configure in Settings → Agents and launch inside a project. Unlike regular commands that mostly stream output, agents are conversational…

Setting up agent tools

Before you can launch agents from Solo, you need to tell it which tools are available. You do this in Settings → Agents.

Agent installation health

Solo checks whether each agent tool's CLI is actually installed and working, and shows the result in Settings → Agents. Health decides which agents are offered for launch and expla…

Launching agents in a project

Agents always launch inside a project context. Terminal-backed CLI agents open in that project's directory, giving them access to your code and files. If your version of Solo inclu…

Auto-summarization

Solo can generate a compact summary after recent activity in an agent or terminal. This gives you a quick way to catch up without re-reading the full output.

Agent idle detection

Solo tracks agent state so you can tell which agents are working, idle, waiting for permission, or blocked by an error.

Closing an agent removes it from the sidebar and ends its process if it's still running. This is different from stopping a regular command — agents don't leave behind an empty "slo…

Are you an agent? Read this doc via API: /api/v1/docs/agents