AG2

AG2 is an open-source framework for building agents and multi-agent applications. It ships ExaToolkit, built on the Exa Python SDK: pass it to an agent and the model can search the web, find similar pages, read page contents, and get cited answers through Exa. Calls run on your own Exa API key.

Install

Install AG2 with your model provider’s extra and the Exa Python SDK. Swap openai for your provider, such as anthropic or gemini.

pip install "ag2[openai]" "exa-py>=2.12.1,<3"

Set EXA_API_KEY in your environment, or pass api_key to ExaToolkit.

Get your Exa API key

Create a key in the dashboard. New accounts start with free credits.

Add Exa to an agent

Passing the toolkit to an Agent registers all four Exa tools, and the model decides when to call them.

Python

import asyncio

from ag2 import Agent
from ag2.config import OpenAIConfig
from ag2.extensions.tools.search import ExaToolkit

agent = Agent(
    "researcher",
    config=OpenAIConfig(model="gpt-5-mini"),
    tools=[ExaToolkit()],
)

async def main():
    reply = await agent.ask("What changed in the latest stable Python release?")
    print(await reply.content())

asyncio.run(main())

Tool	What the model gets
`exa_search`	Exa search: ranked results with titles, URLs, and page text for a query
`exa_find_similar`	Pages similar to a URL the model already has
`exa_get_contents`	Full page contents for specific URLs
`exa_answer`	An answer to a question with cited sources

Configure the tools

num_results and max_characters on the constructor set defaults for exa_search and exa_find_similar. Each tool is also a factory method on the toolkit (search(), find_similar(), get_contents(), answer()), so you can give an agent only the tools it needs and bind filters per agent:

Python

toolkit = ExaToolkit(num_results=10, max_characters=2000)

agent = Agent(
    "researcher",
    config=OpenAIConfig(model="gpt-5-mini"),
    tools=[
        toolkit.search(
            category="research paper",
            include_domains=["arxiv.org"],
            start_published_date="2025-01-01",
        ),
        toolkit.answer(),
    ],
)

`search()` parameter	Use it to
`num_results`	Cap results per search
`max_characters`	Cap page text per result
`search_type`	Pick an Exa search type, such as `auto` or `deep`
`category`	Focus on a category: `company`, `research paper`, `news`, `pdf`, `personal site`, `financial report`, or `people`
`include_domains`, `exclude_domains`	Filter result domains
`start_published_date`, `end_published_date`	Filter by publish date
`start_crawl_date`, `end_crawl_date`	Filter by crawl date
`livecrawl`	Control fresh crawling: `never`, `fallback`, `always`, or `preferred`

find_similar() takes num_results, include_domains, exclude_domains, category, and exclude_source_domain. Every parameter also accepts an AG2 Variable, resolved from the agent’s context at call time.

Resources

AG2 Exa docs

AG2’s reference for ExaToolkit and its factory methods.

AG2 on GitHub

View the framework source and the ExaToolkit implementation.

Get Started

Search

Agent

Other APIs

SDKs

Integrations

Admin

Websets

Install

Get your Exa API key

Add Exa to an agent

Configure the tools

Resources

AG2 Exa docs

AG2 on GitHub

​Install

Get your Exa API key

​Add Exa to an agent

​Configure the tools

​Resources

AG2 Exa docs

AG2 on GitHub

Install

Add Exa to an agent

Configure the tools

Resources