Weights & Biases
FreemiumObservability & Evals
Experiment tracking and LLM tracing for ML teams.
What it’s for
W&B is the industry standard for tracking ML experiments, and its Weave module extends that to LLM apps with tracing, prompt experiments and evals. One dashboard for datasets, runs, metrics, prompts and costs.
How to use it
pip install wandb, run weave.init('project'), and decorate functions with @weave.op() to trace every call. Review traces, compare prompts and build eval datasets in the hosted UI.
Pricing
Free tier for individuals. Team, business and enterprise plans are paid.