Enables AI agents to securely create, manage, and monitor local processes such as dev servers, docker-compose, and test watchers, including restarting, checking status, and retrieving logs via MCP, HTTP, or WebSocket messaging.
Enables agents to submit and manage persistent, dependency-aware task graphs with immutable artifacts, resource reservations, durable event streaming, and retryable process execution over MCP.
Enables AI agents to launch, monitor, and manage long-running terminal processes with real-time log capture and search functionality. It features automatic log rotation and graceful process termination to ensure system stability.
Enables AI agents and MCP clients to manage AutoDL GPU instances programmatically, including creating, listing, powering on/off, executing commands, transferring files, and enforcing automatic shutdown.
Enables durable agent session transfer between machines by serializing state, provisioning sandboxes, and metering costs via MCP tools over a Postgres-backed state machine.
