wandb/weave
A tracing and evaluation library from Weights & Biases. A decorator on your LLM functions logs each call's inputs, outputs and nesting into a trace tree, and you can then score runs against a fixed set of examples.
Idea adaptedKey files read, not run
I learnt this repo's idea and adapted it into my own workspace setup.
How we know
We read the README and key files, not every source file, and did not run it, so the most we can say is Idea adapted or Risky.
Good for
Teams who debug LLM apps by reading logs today and want a structured trace and evaluation history.
Not for
Anyone who will not send traces to an outside cloud; the default path syncs them to a W&B project.
Repo
- Stars
- None
- License
- unknownGitHub could not match this to a standard license. Read the repo's LICENSE file before you use it.
- Maturity
- active
- Last push
- Last checked
- 2026-11-14