Shared laptop clusters for larger models

Hyperspace shipped Pods in v5.19, and the repo now shows v5.19+ support plus pod commands in the CLI.

Pods turn a small group of laptops and desktops into one peer-to-peer AI cluster, so models that do not fit on a single machine can be split across the mesh. Hyperspace says that includes Qwen 3.5 32B and GLM-5 Turbo, with layers sharded across available devices and inference piped through the network instead of a central server. There is no manual VRAM planning in that flow. Everyone installs the CLI, someone creates a pod, and the setup uses an OpenAI-compatible API endpoint so requests can keep one drop-in shape while the work is spread out underneath.

Pod state is replicated across members with Raft consensus, including membership, API keys, and a shared cloud budget. Hyperspace is pitching it at teams already spending $500 to $2,000 a month on API calls, with the idea that daily coding, research, and drafting work can run on hardware they already own. Cloud still stays in the loop for jobs that need a frontier model, but local prompts are supposed to cost only the machines' electricity.