get-available-resources

You can detect CPU, GPU, memory, disk, and OS information by running a resource detection script at the start of computationally intensive tasks. This generates a .claude_resources.json file detailing available hardware and recommended parallelism strategies.

Yes, this resource detection tool supports backend hardware discovery across NVIDIA, AMD, and Apple Silicon GPUs. It identifies available GPU resources to recommend appropriate libraries like PyTorch MPS for optimized computational performance.

To decide between in-memory and out-of-core processing, run a system resource detection script to check available memory and disk space. The generated report provides memory strategy recommendations based on your hardware capacity.

The best way to plan hardware-aware workflows is to run a resource discovery script that outputs a structured schema with recommended parallelism strategies. It analyzes CPU, memory, and GPU data to suggest appropriate libraries like joblib or Dask.

Yes, you need the psutil Python dependency installed to run the system resource detection script. It relies on psutil to gather CPU, memory, and disk information required to generate the structured resource schema.

You should check available system resources before starting a simulation to optimize performance and cost. Detecting hardware constraints beforehand enables smarter workload planning, preventing memory overload and ensuring efficient parallel processing.