get-available-resources

You can detect CPU, GPU, memory, and disk resources by running a Python script that outputs a .claude_resources.json file. This report includes OS details, hardware specifications, and tailored recommendations for parallel processing and memory strategies.

You should check available CPU and GPU memory at project initialization or before heavy analyses. Detecting system resources beforehand helps decide on parallelism, out-of-core memory strategies, and device acceleration to prevent resource-related failures during large-scale workflows.

Yes, resource detection works with NVIDIA, AMD, and Apple Silicon GPUs. The script reads hardware data across these environments, providing structured guidance on GPU usage and device acceleration suggestions for your specific hardware configuration.

Yes, you need psutil installed as a dependency to detect system resources. The Python script uses psutil to read CPU, memory, and disk data, which is then compiled into a .claude_resources.json file with actionable guidance for your computational tasks.

The best way to optimize parallel processing is to generate a resource report first. By detecting CPU cores, memory, and disk space, the tool provides strategic recommendations on parallelism levels and memory strategies tailored to your specific hardware capabilities.

A limitation of automated resource detection is that it provides a static snapshot of system resources at runtime. It may not reflect dynamic load changes or network bottlenecks, meaning recommendations for parallel processing and out-of-core strategies should be validated against real-time workload performance.