ai-agent

Scalene

Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals
13,484 stars435 forksPythonUpdated 8/1/2026100% free · open source
What it does

Scalene is a Python profiler that uses AI to optimize CPU, GPU, and memory usage, providing detailed performance analysis and proposals for improvement.

When to use it
  • When you need to identify performance bottlenecks in your Python application
  • When you want to optimize CPU, GPU, and memory usage for better overall performance
  • When you need detailed, high-precision profiling for scientific computing or data-intensive workloads
Ready-to-paste prompt
python -m scalene --cpu-only --profile-gpu --output-file profiling_results.html your_script.py
Heads up: Scalene requires Python 3.6 or later to run, and may not work correctly with certain Python distributions, such as PyPy
Saves to your device
Use with Claude
New

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

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/scalene && curl -fsSL https://workflowstacks.com/api/skills/scalene/claude-skill -o ~/.claude/skills/scalene/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 Scalene works
Codeflow
Free to inspect

Scalene is a large Python project (~34k lines across 121 code files, plus 231 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit this month, Apache-2.0 license, has a test suite.

Size
Large codebase
~34k lines · 121 code files · ~5 h to skim
Setup
One-command install
Installs like a normal app. Reading the code is optional.
Runs on
Python
No API keys detected
Python 59%JavaScript 16%C++ 8%TypeScript 7%Lean 7%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    CLAUDE.md
    The instructions the AI actually follows
  3. 3
    scalene/__main__.py
    Where the program starts running
  4. 4
    pyproject.toml
    Dependencies and the commands it exposes
  5. 5
    scalene/__init__.py
    Inside scalene/ — the main logic begins here
What's in each folder
scalene/Core code — the actual logic101 files
src/Core code — the actual logic25 files
agents/Prompts, skills & agent definitions1 files
docs/Documentation21 files
formal/Folder32 files
benchmarks/Evaluations & benchmarks6 files
test/Tests — proof it works165 files
tests/Tests — proof it works147 files
READMEHas testsDocumentedCI checksApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
plasma-umass
Language
Python
Category
ai-agent
Published
12/17/2019

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.