Grow your own Agent
Sero gives an AI coding agent its own desktop workspace. It can work with your project files, run commands, open previews, use a browser, and call tools while you inspect and steer the work as it runs.
Add your instructions, memory, skills, and plugins. The agent keeps useful context and gains new capabilities as you add them. That is what we mean by "grow your own Agent."
Sero is available as a public beta desktop release. It runs on your computer, not in a hosted cloud IDE. Sero is built on the open-source Pi coding agent.
Make it yours
A Sero profile holds your agent setup and instructions. Each workspace gives it project context. Memory keeps useful facts across sessions. Skills provide reusable instructions, while plugins add tools, apps, external services, and background jobs.
You choose the model and provider. You can inspect the agent's work, steer it while it runs, and use checkpoints when you need to undo a change.
Start using Sero
- Check Support Scope for the current platform and workspace runtime support contract.
- Follow Get Sero Running to install the packaged app, or use the source-build path if you are developing Sero.
- When you open or configure a workspace, use the default runtime if you are unsure. Read Choose a Workspace Runtime if you need container behavior or want to switch later.
- Set up your profile and providers with Profiles and Onboarding and Models and Providers.
Find your way around
After Sero opens, these pages explain the main surfaces:
- Workspace and Chat — the shell, sidebar, workspaces, sessions, and global chat panel.
- Explorer Workspace — files, editor previews, browser tabs, terminals, and source control.
- Agent Sessions and Context — composer controls, context, voice, steering, and queues.
- Plugins and Apps — bundled apps, installed plugins, widgets, and plugin concepts.
- Plugin Catalog — built-in and external/local plugins at a glance.
Reference and help
Use reference pages when you need a precise answer:
- Support Scope — canonical platform, runtime, and issue-reporting support facts.
- Troubleshooting — what to try when setup or a workspace fails.
- Environment Doctor — diagnostics, safe mode, output states, and redaction behavior.
- Security / Privacy — local state, credentials, logs, and remote-access cautions.
Before filing issues, redact tokens, auth files, private paths, and sensitive project details from logs, screenshots, and reproduction notes.