Enables AI agents to operate a persistent Linux sandbox in the cloud, running commands, managing files, using Git, and publishing artifacts through a Streamable HTTP MCP endpoint.
Enables AI agents to operate a real, private, local Docker-based computer with durable files, terminal access, web research, and a persistent browser or desktop. It supports multiple agent clients via MCP or OpenAPI, with live viewing and human takeover.
Enables AI agents to spin up real Linux desktops in Docker and drive them by reading windows, pages, and documents as text and acting with tools like opening apps, running menu commands, filling file dialogs, and exporting files. It exposes these capabilities uniformly over MCP, function calling, HTTP, CLI, and Python/TypeScript SDKs, with token-efficient diffs, code mode, and parallel or forked desktops.
Exposes a Linux host with shell, Python, and filesystem tools as MCP tools over HTTPS, enabling AI agents to execute commands and manage files remotely.
Enables AI agents to operate a complete Linux desktop through MCP, including applications, system windows, file managers, terminals, and browsers via AT-SPI element trees. It also provides noVNC access for humans to observe and take over the same desktop session.