Skip to main content
W&B Weave is an observability and evaluation platform that helps you track, evaluate, and improve your agents and LLM applications. With Weave, you can:

​
Get started

Select your workload type and then use the following docs to guide you through the basics of how to use Weave’s suite of tools. For more information about the difference between workloads, see What is Weave?

Integrate Weave with an agent

Pick a built-in integration for your agent SDK or harness and start tracing sessions, turns, LLM calls, and tool calls in the Agents view.

Set up custom agent observability

Trace a custom multi-turn agent with the Weave SDK to capture sessions, LLM calls, and tool calls as OpenTelemetry spans.

View agent metrics in Weave UI

Trace a basic call to an LLM and review the inputs, outputs, and code in your W&B account.

​
Install Weave

W&B Weave provides Python and TypeScript libraries. To install the Weave library, run the following command:
To start using the Weave library, create a Weights & Biases (W&B) account and an API key at User Settings. The API key allows you to authenticate to your W&B account and start sending data to it.