Exa Search
API Key RequiredNeural search engine for finding high-quality content. Build AI agents that use Exa Searchwith Agno Builder's visual drag-and-drop interface — no code required to prototype.
What is the Exa Search tool?
The Exa Search tool is a built-in capability in the Agno framework that allows AI agents to neural search engine for finding high-quality content. When added to an agent in Agno Builder, the agent can autonomously decide when to invoke this tool based on the user's request.
This tool requires a EXA_API_KEY environment variable. Get your API key at dashboard.exa.ai.
How to use Exa Search in Agno Builder
- 1
Create an agent
Drag an Agent node onto the canvas in Agno Builder, or use one of the built-in templates.
- 2
Enable Exa Search
Click the agent, go to the Tools tab, and toggle on "Exa Search" from the search category.
- 3
Add your API key
Enter your EXA_API_KEY in the tool configuration. Your key stays in your browser and is never stored on our servers.
- 4
Test in chat
Open the chat panel and send a message. The agent will automatically use Exa Search when relevant.
- 5
Export Python code
Click File > Export Python to get clean, runnable code with the correct imports for Exa Search.
Python code example
This is the code Agno Builder exports when you use Exa Search:
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.exa import ExaTools
agent = Agent(
name="Exa Search Agent",
model=OpenAIChat(id="gpt-4o"),
tools=[ExaTools()],
instructions=["Use the exa search tool to help the user."],
markdown=True,
)
agent.print_response("Find high-quality articles about LLM tool use")Install with: pip install agno # + set EXA_API_KEY
Configuration options
| Option | Type | Default | Description |
|---|---|---|---|
| num_results | number | 5 | Number of results |
| text_length_limit | number | 1000 | Max text length per result |
| show_results | boolean | true | Show results in output |