---
id: exa-py
version: "2.18.1"
license: MIT
license_treatment: permissive
maintenance: active
---

# exa-py — Python SDK for Exa API.

License: permissive · Maintenance: active · Downloads: 9.7M/mo

## What it is and what it does

Exa-py is the official Python SDK for Exa, a web search API designed for AI applications. It wraps HTTP calls to Exa's backend and provides a clean interface for searching the web, retrieving page contents, answering questions, and running autonomous agents. The package supports both synchronous and asynchronous workflows, streaming responses, and structured output schemas—allowing you to extract results in custom JSON formats rather than plain text.

The SDK is built on httpx and pydantic for HTTP and data validation, and integrates with openai for streaming compatibility. It's actively maintained and supports Python 3.9 through 3.14. Core use cases include semantic web search with filters, content extraction with highlights, multi-step agent runs with structured output, and real-time monitoring of entity data across the web.

Use it for:

- Search the web from an AI agent or LLM application and return structured results (e.g., company names, funding rounds) instead of raw links.
- Build a research tool that retrieves and highlights relevant passages from web pages matching a query.
- Run autonomous agents that discover people, companies, or products matching complex criteria and return results in a predefined JSON schema.
- Stream search results or answers to a user in real-time, similar to ChatGPT's streaming interface.
- Monitor a set of companies or entities for news and funding updates on a recurring cadence using Agent Monitors.
- Extract structured data from the web (e.g., engineering leaders at AI startups) without manual scraping or parsing.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

A Python SDK for the Exa web search API that enables AI applications to search the web, retrieve content, answer questions, and run autonomous agents with structured output support.

Yes. The package is actively maintained, has low install friction, carries a permissive MIT license, and integrates cleanly with common Python dependencies. Install it if you need to add web search or autonomous agent capabilities to an AI application. The main gotcha is that you must have an Exa API key and account; the SDK itself is straightforward to use.

## Install

pip install exa-py
uv add exa-py
poetry add exa-py

## Installing exa-py

Before you install: Low friction install with a pure-Python wheel. Active maintenance as of 2026-08-14. Depends on httpcore, httpx, openai, pydantic, python-dotenv, requests, and typing-extensions—all stable, widely-used packages.

License in practice: MIT license (permissive). You can use, modify, and distribute this package with minimal restrictions, including in commercial projects.

Quickstart:

pip install exa-py

from exa_py import Exa

exa = Exa(api_key="your-api-key")
results = exa.search("machine learning startups", contents={"highlights": True})

Requires Python 3.9 or later. Requires a valid Exa API key from https://dashboard.exa.ai.

Verify before relying:

- Whether the Exa API service itself has uptime guarantees or SLAs.
- Pricing model and cost implications of search, answer, and agent API calls.
- Rate limits and quota constraints for different API endpoints.
- Whether Agent Monitors and Agent Max features are production-ready or beta-only.

## Package facts

- License: MIT (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 9.7M/month (top 5,000 on PyPI)
- Known vulnerabilities: none known

## Tags

web search api for ai, python sdk web search, ai-powered search integration, structured web search results, autonomous agent search, semantic web search, ai agent framework, web-search-api, ai-agents, structured-output

[View on SkillFed](https://skillfed.io/packages/exa-py) · [View on PyPI](https://pypi.org/project/exa-py/)