ai-agent

Codecarbon

Name: Codecarbon
Author: mlco2

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

1,898 stars310 forksPythonUpdated 8/13/2026100% free · open source

What it does

Codecarbon tracks emissions from compute resources and recommends ways to reduce their environmental impact

When to use it

•When developing AI models that require significant computational resources
•When trying to reduce the carbon footprint of your data center or cloud infrastructure
•When needing to estimate and report the environmental impact of your AI projects

Ready-to-paste prompt

from codecarbon import EmissionsTracker; tracker = EmissionsTracker(); tracker.start(); # your compute-intensive code; tracker.stop(); emissions = tracker.calculate(); print(emissions)

Heads up: Make sure you have the `google-api-python-client` library installed, as codecarbon uses the Google Cloud API to estimate emissions, and also be aware that an API key from Google Cloud is required for some features

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/codecarbon && curl -fsSL https://workflowstacks.com/api/skills/codecarbon/claude-skill -o ~/.claude/skills/codecarbon/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Codecarbon works

Codeflow

Free to inspect

Codecarbon is a large Python project (~31k lines across 284 code files, plus 129 test files). Setup is light: installs like a normal app — add your API keys. Reading the code is optional. Last commit this month, MIT license, has a test suite.

Size

Large codebase

~31k lines · 284 code files · ~4 h to skim

Setup

One-command install

Installs like a normal app — add your API keys. Reading the code is optional.

Runs on

Python · Docker

Needs API keys (.env)

Python 78%TypeScript 21%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
AGENTS.md
The instructions the AI actually follows
3
carbonserver/main.py
Where the program starts running
4
pyproject.toml
Dependencies and the commands it exposes
5
.env.example
The API keys and settings you must provide

What's in each folder

codecarbon/Core code — the actual logic108 files

docs/Documentation63 files

examples/Examples you can copy53 files

webapp/Folder142 files

carbonserver/Folder139 files

deploy/Deployment / infrastructure18 files

benchmarks/Evaluations & benchmarks6 files

docker/Deployment / infrastructure6 files

READMEHas testsDocumentedCI checksDocker readyExamples includedMIT licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/codecarbon && curl -fsSL https://workflowstacks.com/api/skills/codecarbon/claude-skill -o ~/.claude/skills/codecarbon/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

mlco2

Language

Python