Product tour
Understand how Organizations, Apps, Agents, and runs fit together in mosoo.
mosoo is a managed workspace for building, running, publishing, and operating AI Agents. You configure an Agent once, test it in the console, then make it available through a Thread, an API endpoint, or an App deployment.
The product model
| Resource | What it owns |
|---|---|
| Organization | Your account-level container. The current product is a single-owner experience; team roles and invitations are not available. |
| App | The engineering and delivery boundary for Agents, files, configuration, usage, and one optional deployed site. A new account starts with a Default App. |
| Agent | A reusable worker with a type, runtime, model, instructions, Skills, MCP connections, and an Environment. |
| Thread | The durable conversation and work record for one Agent. Replies can resume work asynchronously. |
| Run | One execution inside a Thread. Runs produce events, logs, usage, and files. |
A typical workflow
- Open or create an App.
- Add a model Provider key.
- Create an Agent and choose its runtime.
- Configure its identity, instructions, Skills, MCP servers, and Environment.
- Test in Preview; inspect Logs, Cost, and Terminal when applicable.
- Publish the Agent.
- Start Threads in mosoo, enable API access, or bind the Agent to a deployed App.
- Monitor Runs, files, versions, and usage.
Most configuration belongs to the active App. Provider keys, MCP credentials, Skills, and Environments do not automatically cross App boundaries.