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 agents to connect to remote MCP servers once, access their tools through a compact MCP endpoint, pair a CLI inside sandboxes, and create watches that turn command or tool output into pollable structured events.
Provides coding agents with a durable, revision-aware project workspace for semantic context, governed source changes, verification, task checkpoints, and observability through an MCP interface.
A durable MCP control plane for starting, observing, steering, continuing, cancelling, and handing off long-running coding agents, with bounded MCP calls and persistent worktrees.