Setup Install the Braintrust SDK and Agno, plus the Yahoo Finance tools used in the example below: ```bash theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}} pip install braintrust agno yfinance ``` Set your Braintrust and model provider API keys: ```bash title=".env" theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}} BRAINTRUST_API_KEY=your-api-key OPENAI_API_KEY=your-openai-key ``` Tracing Agno requires Agno 2.1.0 or later. Auto-instrumentation To trace Agno without modifying each agent call, call `init_logger()` and `auto_instrument()` once at startup. `auto_instrument()` patches Agno’s agent, team, model, workflow, and tool APIs along with every other supported library. ```python Python theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}} import braintrust from agno.agent import Agent from agno.models.openai import OpenAIChat from agno.tools.yfinance import YFinanceTools braintrust.init_logger(project="simple-agent-project") # Replace with your project name braintrust.auto_instrument() # Create and configure the agent agent = Agent( name="Stock Price Agent", model=OpenAIChat(id="gpt-5-mini"), tools=[YFinanceTools()], instructions="You are a stock price agent. Answer questions in the style of a stock analyst.", ) response = agent.run("What is the current price of AAPL?") print(response.content) ``` To patch Agno without enabling Braintrust’s other integrations, call `setup_agno()` instead. It initializes a logger for you when one isn’t already active. ```python Python theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}} from braintrust.wrappers.agno import setup_agno from agno.agent import Agent from agno.models.openai import OpenAIChat from agno.tools.yfinance import YFinanceTools # Initialize Braintrust tracing for Agno setup_agno(project_name="simple-agent-project") agent = Agent( name="Stock Price Agent", model=OpenAIChat(id="gpt-5-mini"), tools=[YFinanceTools()], instructions="You are a stock price agent. Answer questions in the style of a stock analyst.", ) response = agent.run("What is the current price of AAPL?") print(response.content) ``` Workflows Agno workflows are traced without extra configuration. The workflow run appears as a parent span, with nested agent and model calls underneath it: ```python Python theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}} import braintrust from agno.agent import Agent from agno.models.openai import OpenAIChat from agno.workflow import Workflow braintrust.init_logger(project="workflow-project") # Replace with your project name braintrust.auto_instrument() author_agent = Agent( name="Author Agent", model=OpenAIChat(id="gpt-5-mini"), instructions="Answer with only the author's name.", ) workflow = Workflow( name="Book lookup workflow", steps=[author_agent], ) response = workflow.run("Who wrote Charlotte's Web?") print(response.content) ``` What Braintrust traces Braintrust captures: * **Agent run spans** (`.run`, `.arun`, and their streaming variants), with the run input, agent and model metadata, output, and token usage. * **Team run spans** (`.run`, `.arun`, and their streaming variants), with the run input, team and model metadata, output, and token usage. * **Model call spans** (`.invoke`, `.response`, and their async and streaming variants), with the request messages, model and provider metadata, response, and token usage. * **Tool call spans** (`.execute` and `.aexecute`), with the tool arguments, function metadata, and result. * **Workflow run spans** (`.run`, its async and streaming variants, and nested workflow-step spans), with the workflow input, workflow metadata, output, and token usage. Resources * [Agno documentation](https://www.agno.com/) * [Trace LLM calls](/instrument/trace-llm-calls)