exa-py
Python SDK for Exa API.
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.9 or later.
- Requires a valid Exa API key from https://dashboard.exa.ai.
- Low friction install with a pure-Python wheel.
License · maintenance · safety
MIT (permissive) — MIT license (permissive). You can use, modify, and distribute this package with minimal restrictions, including in commercial projects.
last release 2026-08-14 (0 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 9,661,073 downloads/mo, #1,511 on PyPI
Alternatives
Verify before relying
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})- 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.
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 on this page. Verify before relying on it.
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
exa-py on PyPI
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.
Requires Python 3.9 or later. Requires a valid Exa API key from https://dashboard.exa.ai.
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})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 the current Python release >=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 7 packageshttpcorehttpxopenaipydanticpython-dotenvrequeststyping-extensions |
| Maintenance | Actively maintained 0 days since the last release |
| First released | |
| Downloads | 9,661,073 / month, #1,511 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Programming Language :: Python :: 3.9 |
Evidence: exa_py-2.18.1-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “structured web search results”
- exa-pyA Python SDK for the Exa web search API that enables AI applications…
- serpapiOfficial Python client for SerpApi that queries multiple search…
- seltzSeltz is a Python SDK that provides web search and AI-powered answer…
Give your agent the search over MCP, or paste the wish link into any chat.
More WWW/HTTP packages
urllib3 is an HTTP client library that provides thread-safe connection pooling, SSL/TLS verification, multipart file uploads, request retries, compression support, and proxy handling for Python applications.
Requests is a Python HTTP library that simplifies sending HTTP/1.1 requests with automatic handling of headers, authentication, cookies, and response parsing.
h11 is a pure-Python HTTP/1.1 protocol implementation that handles parsing and serializing HTTP messages without any built-in I/O, letting you integrate it with any network layer you choose.
HTTPX is a fully featured HTTP client library for Python that provides both sync and async APIs, with support for HTTP/1.1 and HTTP/2, plus an integrated command-line client.
Install it if you are building new projects or modernizing existing ones that rely on HTTP.
A minimal low-level HTTP client library that sends HTTP requests with thread-safe and task-safe connection pooling, supporting HTTP/1.1, HTTP/2, proxies, and both sync and async interfaces.
aiohttp is an async HTTP client and server framework built on asyncio, supporting both WebSockets and middleware-based routing for building concurrent web applications.
Install it if you need async HTTP client or server capabilities in asyncio-based applications.
See also metaphor-python · seltz · langchain-exa · agent-framework-devui · npmai-agents · crewai · zai-sdk · rocketreach · gnews · pycdc