mlco2/codecarbon

Track emissions from Compute and recommend ways to reduce their impact on the environment.

What it solves

CodeCarbon tracks and estimates the carbon emissions resulting from the electricity consumed by your local computing hardware during the execution of your code. It helps developers and researchers quantify the environmental impact of their software, particularly for compute-intensive tasks like training machine learning models.

How it works

The library estimates the electricity power consumption of the CPU, GPU, and RAM. It then applies the carbon intensity of the the region where the computing is performed to calculate the total CO2 emissions.

Who it’s for

It is designed for developers and researchers who want to monitor and reduce the carbon footprint of their local computing experiments and ML model training.

Highlights

  • Lightweight Python library: Offers a simple API to start and stop tracking emissions.
  • CLI support: Allows tracking of commands via the command line without modifying the source code.
  • Visualizations: Provides a dashboard and a local tool called carbonboard for analyzing emissions.
  • Hardware detection: Includes a detect command to identify local hardware components.
  • Regional carbon intensity: Accounts for the specific carbon footprint of the electricity grid in the user's region.

Related

  • Project
    saintslab/carbontracker

    A tool for tracking and predicting the energy consumption and carbon footprint of training deep learning models.

  • Project
    mlco2/ecologits

    EcoLogits is a Python library that estimates the electricity consumption and CO₂‑equivalent emissions of calls to generative‑AI APIs (OpenAI, Anthropic, Cohere, etc.). Install via `pip install ecologits` (add provider extras as needed), initialize with `EcoLogits.init`, and after a normal API call you can read `response.impacts.energy.value.mean` and `response.impacts.gwp.value.mean` for the estimated kWh and kg CO₂‑eq. It’s open‑source, part of the CodeCarbon non‑profit, and aims to help developers track and reduce the environmental impact of AI inference.

  • Project
    eduardolundgren/tracking.js

    A lightweight JavaScript library that brings computer vision algorithms like color tracking and face detection directly into the browser.

  • Dispatch
    Hugging Face Hub Carbon Emissions Tracking

    Hugging Face has introduced tools to track, report, and filter machine learning models based on their CO2 emissions to improve environmental transparency in AI.

  • Project
    pytorch/cpuinfo

    A cross-platform C/C++ library for detecting detailed CPU hardware information, such as instruction sets and cache topology, to enable performance optimizations.