Metal Sandbox: Isolated Execution and Command Scheduling for GPU Coding Agents on Apple Silicon
Metal Sandbox schedules GPU and development commands across isolated agent workspaces on interconnected Macs. Its reported throughput and wait-time gains come from controlled experiments and trace-based estimates with stated assumptions.
Metal Sandbox combines **restricted per-instance file access**, native command execution, and command scheduling across Macs. Parallel commands can run concurrently; serial commands share one execution slot per node, and eligible waiting commands can move to another Mac.
Builders running local GPU coding agents could consider command-level scheduling when GPU and tool time sit idle between model requests. The system also integrates with Harbor for task execution, verification, and rollout collection.
Metal Sandbox combines **restricted per-instance file access**, native command execution, and command scheduling across Macs. Parallel commands can run concurrently; serial commands share one execution slot per node, and eligible waiting commands can move to another Mac. Builders running local GPU coding agents could consider command-level scheduling when GPU and tool time sit idle between model requests. The system also integrates with Harbor for task execution, verification, and rollout collection. Controlled tests on **four Mac mini M4 nodes** reported 1.68×–2.05× command throughput under concentrated demand. Trace-based estimates reported 2.14× sustained throughput and, under unchanged phase durations, 18.8% less tool waiting and 22.3% shorter batches. The latter results rely on modeled assumptions, not live deployments.
This brings command scheduling and restricted file access to local GPU-agent infrastructure on Apple Silicon. Its four-node tests report higher throughput under concentrated demand, while the sustained-throughput and waiting-time gains are trace-based estimates. The results make a case for evaluating command-level scheduling in this setting without establishing live-deployment performance.