{"id":"weave","name":"W&B Weave","maker":"Weights & Biases","url":"https://wandb.ai/site/weave","repo":"wandb/weave","docs":"https://docs.wandb.ai/weave","package":"pypi:weave","summary":"A toolkit from Weights & Biases for tracing, evaluating and monitoring LLM applications and agents.","details":"A Python and TypeScript library that records calls as traces after adding a decorator or a framework integration, and runs evaluations against datasets. Results show in the Weights & Biases web application, which needs an account. The library is open source under Apache 2.0.","open_source":true,"hosted":true,"speaks":["opentelemetry"],"verified":"2026-11-15","category":"observability","category_name":"Observability and evaluation","page":"https://modelmoot.com/tools/weave","reviewed":"2026-11-15","checked":{"at":"2026-11-15T16:10:15.342Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}