Ross ROSS = Recommend OSS · open-source software intelligence for agents

tinyfish-io/agentql

AgentQL is a suite of tools for connecting your AI to the web. Featuring a query language and Playwright integrations for interacting with elements and extracting data quickly, precisely, and at scale. Includes REST API, Python and JavaScript SDKs, browser debugger. observed · 2026-08-28

github.com/tinyfish-io/agentql · homepage · Python · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

70/100

  • Activity 99
  • Release rhythm 35
  • Longevity 66

Flags: no_releases

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 925
  • days_rel: n/a
  • days_push: 7
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

1451 stars · 166 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

AgentQL is a suite of tools for extracting structured data and automating workflows on live websites using an AI-powered natural language query language. It includes Python and JavaScript SDKs integrated with Playwright, a REST API, a CLI, and a browser-based debugger extension.

Use cases

  • extract structured data from web pages with natural language queries
  • scrape product names and prices from e-commerce sites
  • automate web interactions with Playwright instead of fragile XPath selectors
  • feed live web data to LLMs and AI agents
  • parse tables from PDFs
  • scrape pages behind authentication or with dynamic content
  • build resilient scrapers that survive UI changes

When to choose

  • you need structured data from dynamic or authenticated pages
  • CSS/XPath selectors break too often and you want self-healing queries
  • you're building web agents or RPA workflows with Playwright
  • you want the same query to work across similar sites

When to avoid

  • you need a fully free self-hosted solution - the query API requires an AgentQL API key with usage-based pricing
  • you only scrape static, well-structured pages where simple HTML parsing suffices
  • you need offline operation without cloud API calls

Facets

library · maturity active

web-scraping parser sdk agent-framework workflow-automation browser-extension cli web-development artificial-intelligence crawlers developer-tools python browser-extension cross-platform query-language playwright data-extraction web-automation rpa rest-api self-healing-selectors pdf-parsing ai-agents automation nodejs

8 sources

Member repositories

RepositoryRoleHealth v2
tinyfish-io/agentqlmain70

For agents

markdown · JSON · MCP: product_card(name="tinyfish-io/agentql")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem