EcoLogits

Tracks the energy consumption and environmental impacts of using generative AI models through APIs.
https://github.com/mlco2/ecologits

Category: Consumption
Sub Category: Computation and Communication

Keywords

genai generative-ai green-ai green-software llm llm-inference python sustainability sustainable-ai

Last synced: about 5 hours ago
JSON representation

Repository metadata

🌱 EcoLogits tracks the energy consumption and environmental footprint of using generative AI models through APIs.

• Host: GitHub
• URL: https://github.com/mlco2/ecologits
• Owner: mlco2
• License: mpl-2.0
• Created: 2024-02-02T16:25:32.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2026-03-02T19:54:09.000Z (15 days ago)
• Last Synced: 2026-03-08T06:50:50.541Z (9 days ago)
• Topics: genai, generative-ai, green-ai, green-software, llm, llm-inference, python, sustainability, sustainable-ai
• Language: Python
• Homepage: https://ecologits.ai/
• Size: 10.9 MB
• Stars: 263
• Watchers: 12
• Forks: 26
• Open Issues: 10
• Releases: 31
• Metadata Files:
  • Readme: README.md
  • Contributing: docs/contributing.md
  • License: LICENSE
  • Citation: CITATION.cff

README.md

pip install ecologits

from ecologits import EcoLogits
from openai import OpenAI

# Initialize EcoLogits
EcoLogits.init(providers=["openai"])

client = OpenAI(api_key="<OPENAI_API_KEY>")

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "user", "content": "Tell me a funny joke!"}
    ]
)

# Get estimated environmental impacts of the inference
print(f"Energy consumption: {response.impacts.energy.value.mean} kWh")
print(f"GHG emissions: {response.impacts.gwp.value.mean} kgCO2eq")

Citation (CITATION.cff)

cff-version: "1.2.0"
authors:
- family-names: Rincé
  given-names: Samuel
  orcid: "https://orcid.org/0009-0000-0739-6114"
- family-names: Banse
  given-names: Adrien
  orcid: "https://orcid.org/0000-0002-4456-6618"
doi: 10.5281/zenodo.15601289
message: If you use this software, please cite our article in the
  Journal of Open Source Software.
preferred-citation:
  authors:
  - family-names: Rincé
    given-names: Samuel
    orcid: "https://orcid.org/0009-0000-0739-6114"
  - family-names: Banse
    given-names: Adrien
    orcid: "https://orcid.org/0000-0002-4456-6618"
  date-published: 2025-07-09
  doi: 10.21105/joss.07471
  issn: 2475-9066
  issue: 111
  journal: Journal of Open Source Software
  publisher:
    name: Open Journals
  start: 7471
  title: "EcoLogits: Evaluating the Environmental Impacts of Generative
    AI"
  type: article
  url: "https://joss.theoj.org/papers/10.21105/joss.07471"
  volume: 10
title: "EcoLogits: Evaluating the Environmental Impacts of Generative
  AI"

Owner metadata

• Name: CodeCarbon
• Login: mlco2
• Email:
• Kind: organization
• Description:
• Website: https://codecarbon.io
• Location:
• Twitter:
• Company:
• Icon url: https://avatars.githubusercontent.com/u/54071934?v=4
• Repositories: 7
• Last ynced at: 2025-11-12T05:34:26.578Z
• Profile URL: https://github.com/mlco2

GitHub Events

Total

• Delete event: 5
• Member event: 2
• Pull request event: 5
• Fork event: 1
• Discussion event: 1
• Watch event: 4
• Issue comment event: 3
• Push event: 17
• Create event: 2

Last Year

• Delete event: 5
• Member event: 2
• Pull request event: 5
• Fork event: 1
• Discussion event: 1
• Watch event: 4
• Issue comment event: 3
• Push event: 17
• Create event: 2

Committers metadata

Last synced: 2 days ago

Committer domains:

• test.fr: 1
• valraiso.fr: 1
• test.com: 1
• uclouvain.be: 1
• rince.me: 1

Issue and Pull Request metadata

Last synced: 3 days ago

Dependencies

Score: 8.442685139241176