plexe-ai/plexe
✨ Build a machine learning model from a prompt
Orchestrates a 14-agent system across a 6-phase workflow to automatically select algorithms, engineer features, and tune hyperparameters from tabular data. Produces deployment-ready model packages (XGBoost, CatBoost, LightGBM, Keras, PyTorch) with zero plexe dependencies, and routes different agents to OpenAI, Anthropic, or other LiteLLM providers via YAML configuration. Includes PySpark support, Streamlit dashboards for experiment visualization, and extensible integrations for custom storage and deployment pipelines.
2,548 stars. Available on PyPI.
Stars
2,548
Forks
253
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 06, 2026
Commits (30d)
0
Dependencies
20
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/plexe-ai/plexe"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.