mx-Liu123/AgentCommander

An open-source, graph-based workflow engine for Gemini/OpenCode/Claude Code/Qwen CLI. Automate ML experiments and scientific discovery.

29
/ 100
Experimental

This tool helps machine learning engineers and researchers accelerate scientific discovery by automating the iterative process of optimizing machine learning code. You provide an initial dataset or existing training code, and the system uses AI agents to generate, debug, and refine code, interpreting multimodal feedback like plots. The output is a highly optimized machine learning model or experiment, along with a detailed history of the evolution process.

Use this if you are an ML researcher or engineer spending too much time manually iterating and debugging machine learning models, and you want to automate the trial-and-error process of code optimization and experimental design.

Not ideal if you need a simple, one-off script execution or if your workflow does not involve iterative code refinement and complex experimental orchestration.

machine-learning-research scientific-discovery ml-experimentation code-optimization model-development
No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 13 / 25
Community 0 / 25

How are scores calculated?

Stars

23

Forks

Language

HTML

License

Apache-2.0

Last pushed

Feb 23, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/mx-Liu123/AgentCommander"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.