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

The following docs guide you through the basics of how to use Weave’s suite of tools.

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: 
pip install weave
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.