Utilyze: Open-Source GPU Monitor That Measures Real Compute Throughput, Not Just Kernel Activity
The standard GPU utilization metric used by nvidia-smi, nvtop, Weights & Biases, Amazon CloudWatch, Google Cloud Monitoring, and Azure Monitor is misleading. It reports the fraction of time any kernel is running, so a GPU can show 100% utilization while only using 1-10% of real compute capacity. Teams relying on this for capacity planning may think systems are saturated when they're actually underutilized.
Utilyze
SysTalize released Utilyze (utlz), an open-source (Apache 2.0) tool that measures GPU utilization differently. Instead of kernel activity, it samples hardware performance counters and reports compute and memory throughput relative to the hardware's theoretical limits. It also estimates an attainable utilization ceiling for a given workload.
Installation
curl -fsSL https://systalyze.com/utilyze/install.sh | bashUtilyze runs alongside any AI workload in real time with negligible overhead. In production deployments, it has revealed orders-of-magnitude performance headroom in systems that standard tools declared fully saturated.
Why This Matters
AI compute is scarce: H100 one-year rental contracts rose ~40% from October 2025 to March 2026, and lead times for GPUs stretch months. Wasted spend on unnecessary hardware and energy is massive. Accurate measurement is the prerequisite for optimization — every percentage point of real throughput recovered saves money and resources.
Check the GitHub repo: https://github.com/systalyze/utilyze
📖 Read the full source: HN LLM Tools
👀 See Also
GSD-Lite: A State Machine for Claude Code That Enforces TDD and Prevents Test Skipping
GSD-Lite is an open-source MCP server that adds a 12-state workflow machine to Claude Code, enforcing test-driven development with specific anti-rationalization prompts and separate agent contexts for execution, review, and debugging.
Depct tool collects runtime data to help Claude debug production issues
Depct is a tool that collects runtime instrumentation from Node.js apps, builds graphs from the data, and feeds it to Claude via AWS Bedrock to help debug intermittent production failures. It also generates architecture diagrams and dependency maps from runtime behavior.
Kreuzberg v4.7.0 adds code intelligence for 248 languages and improved markdown extraction
Kreuzberg v4.7.0, a Rust-core document intelligence library, now supports code extraction for 248 formats via tree-sitter and has significantly improved markdown quality with Structural F1 scores over 80% across 23 formats.
Ink: A Deployment Platform Where Claude AI Agents Are the Primary Users
Ink (ml.ink) is a deployment platform designed for AI agents like Claude, featuring one tool call deployment, auto-detection of frameworks, and integrated services including compute, databases, DNS, secrets, domains, metrics, and logs.