aitra-ai/aitra-meter

Desktop app for DeepSeek Harness with a live energy/carbon console: measure local GPU inference, estimate cloud APIs via published coefficients, alert on waste

Measure and optimize the energy consumption of your AI applications!

Kepler (Kubernetes-based Efficient Power Level Exporter) is a Prometheus exporter that measures energy consumption at the Kubernetes Pod and Node level. It reads hardware sensors, attributes power to containers, and gives per-workload visibility into where energy goes. Let's make every watt matter.

Benchmarking Intelligence Efficiency of LM Inference

GPU Profiler for AI agents

✈️ Kubernetes-native platform for deploying and managing AI inference across multiple providers

GenAI inference performance benchmarking tool

llm-d benchmark scripts and tooling

Track and predict the energy consumption and carbon footprint of training deep learning models.