tavily-cli
CLI and agent tools for the Tavily API — search, extract, crawl, map, and research from the command line.
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- 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.
- Low install friction with a pure-Python wheel distribution.
License · maintenance · safety
MIT (permissive) — MIT license permits unrestricted use, modification, and distribution with minimal obligations—suitable for commercial and private projects.
last release 2026-07-31 (14 days) · last repo commit 2026-07-31 · 14 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 77,225 downloads/mo, #14,544 on PyPI
Alternatives
Verify before relying
pip install tavily-cli
tvly search "latest AI trends"
tvly extract https://example.com
tvly research "topic" --json- 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
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 on it.
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
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.
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.
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" --jsonVerify 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
| License | MIT permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 8 packagescertificlickhttpxpsutilrequestsrichtavily-pythonurllib3 |
| Maintenance | Actively maintained 14 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 77,225 / month, #14,544 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersLicense :: OSI Approved :: MIT LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Topic :: Scientific/Engineering :: Artificial Intelligence |
Evidence: tavily_cli-0.1.6-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 › “web search CLI tool”
- tavily-cliTavily CLI provides command-line and programmatic access to Tavily's…
- brave-search-python-clientA Python client library for the Brave Search API that supports web,…
- duckduckgo-mcpThis package is deprecated; install web-forager instead. It provides…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also tavily-python · langchain-tavily · Crawl4AI · pypistats · scrapegraph-py · firecrawl-py · crawlee · pairmux · readable-content · firecrawl