Initializing
AI Lab
...
Write, run, and experiment with Python, JavaScript, HTML, C#, NumPy, Pandas, TensorFlow, PyTorch, scikit-learn — all in your browser. No setup. No install.
import numpy as np from sklearn.linear_model import LinearRegression import matplotlib.pyplot as plt # Generate sample data X = np.random.rand(100, 1) * 10 y = 2.5 * X.flatten() + np.random.randn(100) # Train model model = LinearRegression() model.fit(X, y) print(f"Score: {model.score(X,y):.4f}") # ✓ Score: 0.9823
Multi-language IDE with Python (Pyodide), JavaScript, HTML/CSS preview, and C# execution. Syntax highlighting, autocomplete, error hints.
Hands-on notebooks with TensorFlow.js, Pyodide scikit-learn, Keras examples, and interactive model training — all in-browser.
Integrated access to MLflow experiment tracking, Weights & Biases dashboards, and dataset management tools via embedded panels.
NumPy arrays, Pandas DataFrames, Matplotlib plots — run real data analysis right here. Upload CSVs, explore datasets, visualize results.
Track experiments, log metrics, compare models — all from within the lab.
Experiment tracking, model registry, reproducible runs.
Real-time training metrics, artifact logging, sweeps.
TensorFlow training visualizations and graph explorer.
Pre-trained models, datasets, and Spaces — direct access.
In-browser ML algorithms via Pyodide. Train, predict, score.
Deep learning in the browser — no Python, no server.
