tavily-cli

What it is and what it does

Tavily CLI is a command-line interface and Python agent toolkit for the Tavily search and research API. It wraps the tavily-python SDK with a user-friendly CLI that supports both interactive REPL mode and non-interactive scripting, making it suitable for both human operators and AI agents. The tool provides web search with LLM-optimized ranking, content extraction from URLs, website crawling with depth and breadth control, URL discovery, and AI-powered research with citations.

The package is designed for flexibility: humans get rich-formatted terminal output with colors and tables, while agents receive structured JSON. Most commands support filtering by domain, date range, and path patterns. Search and extract work without authentication up to a fair-use limit; other operations require a Tavily API key set via login, environment variable, or OAuth. The tool handles both synchronous operations and async research tasks with polling.

Use it for:

• Run web searches from the command line with domain and date filtering for research or data gathering
• Extract clean markdown content from URLs for RAG pipelines or document processing workflows
• Crawl documentation sites or knowledge bases with depth control and semantic filtering
• Integrate structured search and research into AI agent workflows via JSON output and stdin input
• Discover and map all URLs on a website without extracting content for site audits or indexing

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Tavily CLI provides command-line and programmatic access to Tavily's web search, content extraction, website crawling, and AI-powered research APIs, with both interactive REPL and structured JSON output modes.

Yes. Tavily CLI is actively maintained, has no known vulnerabilities, and offers low install friction. It's a solid choice if you need programmatic or command-line access to Tavily's search and research APIs. The MIT license is permissive, and the tool supports both interactive and agent-friendly modes. Start with keyless search or extract to evaluate before committing to an API key.

Install

tavily-cli on PyPI

pip install tavily-cli

uv add tavily-cli

poetry add tavily-cli

Installing tavily-cli

Before you install

Low install friction with a pure-Python wheel distribution. Active maintenance with a recent release (14 days old) and current repository activity. Eight runtime dependencies are all standard, well-maintained libraries.

License in practice

MIT license permits unrestricted use, modification, and distribution with minimal obligations—suitable for commercial and private projects.

Quickstart

pip install tavily-cli
tvly search "latest AI trends"
tvly extract https://example.com
tvly research "topic" --json

Requires Python 3.10 or later. Most commands (crawl, map, research) require a Tavily API key; search and extract work without one up to a fair-use rate limit.

Verify before relying

• Whether the fair-use rate limit for keyless search and extract is sufficient for typical development workflows
• Performance characteristics and timeout behavior for large-scale crawls or deep research tasks
• Exact API response latency and reliability guarantees not detailed in the excerpt

Package facts

Evidence: tavily_cli-0.1.6-py3-none-any.whl

Keywords: agents, ai, crawl, extract, llm, rag, research, tavily, web-search

Tags

More Artificial Intelligence packages