# tavily-ai/tavily-python

The Tavily Python SDK allows for easy interaction with the Tavily API, offering the full range of our search, extract, crawl, map, and research functionalities directly from your Python programs. Easily integrate smart search, content extraction, and research capabilities into your applications, harnessing Tavily's powerful features.

Repository: https://github.com/tavily-ai/tavily-python
Canonical: https://ross.abutalabs.com/products/tavily-python
Homepage: https://pypi.org/project/tavily-python/
Language: Python
License: MIT
License Family: permissive
Topics: agent, crawl, extract, map, python, search, tavily
Last push: 2026-08-24T15:47:47+00:00

## Health v2 (maintenance only)
Score: 72/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 78
- inputs: {"age_days": 1097, "days_push": 9, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1373, forks 177 (observed 2026-08-28T04:04:32.414018+00:00)

## What it is
The official Python SDK for the Tavily API, providing search, content extraction, crawling, site mapping, and research capabilities. It lets Python programs and AI agents integrate web search and retrieval with a simple client interface, including a rate-limited keyless mode for trying the service.

## Use cases
- add web search to an AI agent
- extract clean content from web pages in python
- crawl a website and map its urls
- build a RAG pipeline with live web results
- search the web from a python script
- give an LLM real-time internet access

## When to choose
- you want programmatic web search in Python for agents or RAG
- you need extraction, crawling, and mapping via one API client
- you want a quick keyless trial before committing to an API key

## When to avoid
- you need a self-hosted search engine rather than a hosted API
- your project is not Python-based and you don't want to call the REST API directly
- you require unlimited free usage without rate limits

## Facets
- artifact type: library
- maturity: active
- function: search-engine, http-client, web-scraping, rag
- domain: artificial-intelligence, developer-tools
- platform: python, cross-platform
- tags: web-search-api, sdk, content-extraction, crawler, api-client, llm-tools, search, ai-agents, retrieval-augmented-generation

## Member repositories
- tavily-ai/tavily-python (main) score 72

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:32.414018+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:40:43.765078+00:00, confidence not recorded.
  - readme: https://github.com/tavily-ai/tavily-python (fetched 2026-08-28T04:04:32.414018+00:00, sha 84b14c393feb)
  - homepage: https://pypi.org/project/tavily-python/ (fetched 2026-08-29T11:57:16.434468+00:00, sha 4b4e8fead74a)
  - registry_pypi: https://pypi.org/pypi/tavily-python/json (fetched 2026-08-29T11:57:16.443707+00:00, sha 105fb0fcb7d7)
- Data as of 2026-08-30T08:39:29.467469+00:00.