EcoLogits

EcoLogits: Evaluating the Environmental Impacts of Generative AI - Published in JOSS (2025)

https://github.com/genai-impact/ecologits

Science Score: 98.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
    Found 4 DOI reference(s) in README and JOSS metadata
  • Academic publication links
    Links to: zenodo.org
  • Committers with academic emails
  • Institutional organization owner
  • JOSS paper metadata
    Published in Journal of Open Source Software

Keywords

genai generative-ai green-ai green-software llm llm-inference python sustainability sustainable-ai
Last synced: 4 months ago · JSON representation ·

Repository

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

Basic Info
  • Host: GitHub
  • Owner: genai-impact
  • License: mpl-2.0
  • Language: Python
  • Default Branch: main
  • Homepage: https://ecologits.ai/
  • Size: 6.78 MB
Statistics
  • Stars: 219
  • Watchers: 11
  • Forks: 22
  • Open Issues: 8
  • Releases: 27
Topics
genai generative-ai green-ai green-software llm llm-inference python sustainability sustainable-ai
Created almost 2 years ago · Last pushed 5 months ago
Metadata Files
Readme Contributing License Citation

README.md

EcoLogits

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

PyPI version PyPI downloads Python version Open In Colab DOI

EcoLogits was created and is actively maintained by the GenAI Impact non-profit.

Read the full documentation on ecologits.ai.

⚙️ Installation

shell pip install ecologits

For integration with a specific provider, use pip install ecologits[openai]. We are currently supporting the following providers: anthropic, cohere, google-genai, huggingface-hub, mistralai and openai. See the full list of providers.

🚀 Usage

```python from ecologits import EcoLogits from openai import OpenAI

Initialize EcoLogits

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

client = OpenAI(apikey="<OPENAIAPI_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") ```

See package documentation on EcoLogits

💚 Sponsors & benefactors

Resilio

Terra Cognita

Sopht

Avanade

Ministère de la Culture

💪 Contributing

To get started with setting up a development environment and making a contribution to EcoLogits, see Contributing to EcoLogits.

⚖️ License

This project is licensed under the terms of the Mozilla Public License Version 2.0 (MPL-2.0).

Owner

  • Name: GenAI Impact
  • Login: genai-impact
  • Kind: organization

JOSS Publication

EcoLogits: Evaluating the Environmental Impacts of Generative AI
Published
July 09, 2025
Volume 10, Issue 111, Page 7471
Authors
Samuel Rincé ORCID
GenAI Impact
Adrien Banse ORCID
GenAI Impact, ICTEAM, UCLouvain, Belgium
Editor
Fei Tao ORCID
Tags
Generative AI Environmental Impact Life Cycle Assessment

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"

GitHub Events

Total
  • Fork event: 13
  • Create event: 37
  • Commit comment event: 3
  • Release event: 9
  • Issues event: 41
  • Watch event: 119
  • Delete event: 22
  • Member event: 1
  • Issue comment event: 83
  • Push event: 197
  • Pull request review comment event: 51
  • Pull request review event: 52
  • Pull request event: 74
Last Year
  • Fork event: 13
  • Create event: 38
  • Commit comment event: 3
  • Release event: 9
  • Issues event: 41
  • Watch event: 119
  • Delete event: 22
  • Member event: 1
  • Issue comment event: 83
  • Push event: 197
  • Pull request review comment event: 51
  • Pull request review event: 52
  • Pull request event: 74

Committers

Last synced: 4 months ago

All Time
  • Total Commits: 653
  • Total Committers: 15
  • Avg Commits per committer: 43.533
  • Development Distribution Score (DDS): 0.366
Past Year
  • Commits: 260
  • Committers: 8
  • Avg Commits per committer: 32.5
  • Development Distribution Score (DDS): 0.423
Top Committers
Name Email Commits
Samuel Rince s@r****e 414
Adrien Banse a****e@u****e 156
luc l****n@t****m 32
Caroline Jean-Pierre 1****e 18
Nina P 2****v 7
vinh v****4@h****r 5
Jay DesLauriers 3****l 4
Luc BERTON l****n@g****m 4
sauraisg g****s@g****m 3
Clovis Varangot-Reille 1****i 2
Romain ROCHAS 4****m 2
Yoann Couble y****e@v****r 2
Luc l****c@t****r 2
DataForGood (Tech) 1****h 1
Thilo Michael u****o@g****m 1
Committer Domains (Top 20 + Academic)

Issues and Pull Requests

Last synced: 4 months ago

All Time
  • Total issues: 45
  • Total pull requests: 147
  • Average time to close issues: 29 days
  • Average time to close pull requests: 4 days
  • Total issue authors: 22
  • Total pull request authors: 13
  • Average comments per issue: 1.07
  • Average comments per pull request: 0.66
  • Merged pull requests: 125
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 28
  • Pull requests: 86
  • Average time to close issues: 7 days
  • Average time to close pull requests: 6 days
  • Issue authors: 18
  • Pull request authors: 9
  • Average comments per issue: 0.82
  • Average comments per pull request: 0.66
  • Merged pull requests: 66
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
  • adrienbanse (8)
  • samuelrince (8)
  • NP4567-dev (5)
  • ExploratoriumGPT (2)
  • gecBurton (2)
  • Zeitsperre (2)
  • Neyri (2)
  • cvarrei (2)
  • thilomichael (1)
  • ketsapiwiq (1)
  • benoit-cty (1)
  • paulgay (1)
  • jbjuin (1)
  • cleophas-dlg (1)
  • stephantul (1)
Pull Request Authors
  • samuelrince (63)
  • adrienbanse (47)
  • cjean-pierre (12)
  • LucBERTON (5)
  • NP4567-dev (5)
  • ycouble (3)
  • Zeitsperre (2)
  • C-BdB (2)
  • cvarrei (2)
  • thilomichael (2)
  • HsuChieh (2)
  • aqwvinh (1)
  • yipfram (1)
Top Labels
Issue Labels
bug (14) feature request (12) documentation (2) question (1)
Pull Request Labels
documentation (2)

Dependencies

.github/workflows/pre-commit.yaml actions
  • actions/cache v1 composite
  • actions/checkout v2 composite
  • actions/setup-python v2 composite
  • pre-commit/action v3.0.0 composite
poetry.lock pypi
  • cachetools 5.3.2
  • cfgv 3.4.0
  • chardet 5.2.0
  • colorama 0.4.6
  • distlib 0.3.8
  • exceptiongroup 1.2.0
  • filelock 3.13.1
  • identify 2.5.35
  • iniconfig 2.0.0
  • nodeenv 1.8.0
  • packaging 23.2
  • platformdirs 4.2.0
  • pluggy 1.4.0
  • pre-commit 2.21.0
  • pyproject-api 1.6.1
  • pytest 7.4.4
  • pyyaml 6.0.1
  • setuptools 69.1.0
  • tomli 2.0.1
  • tox 4.13.0
  • virtualenv 20.25.0
pyproject.toml pypi
  • pre-commit ^2.20.0 develop
  • pytest ^7.2.0 develop
  • tox ^4.4.8 develop
  • python >=3.8,<4