BeClaude

VeloQ

New
68GitHub TrendingGeneralby lucifer1004

Agent-friendly GPU profile-query CLI

First seen 6/5/2026

Summary

VeloQ is an agent-friendly CLI tool that lets you query GPU profiles directly from your terminal.

  • It helps developers quickly find GPU specifications, compare performance metrics, and select the right hardware for their workloads without leaving the command line.

Install & Usage

1
Create the agents directory
mkdir -p .claude/agents
2
Save the agent file

Add the configuration to .claude/agents/veloq.md

3
Invoke with @agent-name
@veloq

Use Cases

Query GPU specs like memory, CUDA cores, and clock speeds for a specific model.
Compare performance benchmarks between two or more GPU models side by side.
Filter GPUs by minimum VRAM or TDP for a machine learning project.
List all available GPUs from a specific vendor or architecture generation.
Check the recommended GPU for a given deep learning framework version.
Export GPU profile data in JSON format for integration with other tools.

Usage Examples

1

/veloq query --model RTX 4090

2

/veloq compare --gpus A100,H100,B200

3

/veloq filter --min-vram 24GB --max-tdp 300W

View source on GitHub
agent

Security Audits

LicenseUnknownSourceWarnRepositoryPass

Frequently Asked Questions

What is VeloQ?

VeloQ is an agent-friendly CLI tool that lets you query GPU profiles directly from your terminal. It helps developers quickly find GPU specifications, compare performance metrics, and select the right hardware for their workloads without leaving the command line.

How to install VeloQ?

To install VeloQ: create the agents directory (mkdir -p .claude/agents), then add the config to .claude/agents/veloq.md. Finally, @veloq in Claude Code.

What is VeloQ best for?

VeloQ is a agent categorized under General. It is designed for: agent. Created by lucifer1004.

What can I use VeloQ for?

VeloQ is useful for: Query GPU specs like memory, CUDA cores, and clock speeds for a specific model.; Compare performance benchmarks between two or more GPU models side by side.; Filter GPUs by minimum VRAM or TDP for a machine learning project.; List all available GPUs from a specific vendor or architecture generation.; Check the recommended GPU for a given deep learning framework version.; Export GPU profile data in JSON format for integration with other tools..