# vifreefly/kimuraframework

Write web scrapers in Ruby using a clean, AI-assisted DSL. Kimurai uses AI to figure out where the data lives, then caches the selectors and scrapes with pure Ruby. Get the intelligence of an LLM without the per-request latency or token costs.

Repository: https://github.com/vifreefly/kimuraframework
Canonical: https://ross.abutalabs.com/products/kimuraframework
Homepage: https://kimur.ai/framework
Language: Ruby
License: MIT
License Family: permissive
Topics: kimurai, scraper, crawler, scrapy, headless-chrome, antidetect-browser, ruby, web-scraping, camoufox
Last push: 2026-01-27T17:39:38+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 64, release rhythm 35, longevity 100
- inputs: {"age_days": 2932, "days_push": 218, "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 1102, forks 162 (observed 2026-08-28T04:03:35.858744+00:00)

## What it is
Kimuraframework (Kimurai) is a Ruby web scraping framework with an AI-assisted DSL: an LLM generates XPath selectors from a schema on first run, caches them, and subsequent scrapes run as fast pure-Ruby extraction. It also supports classic manual selectors with headless antidetect Chrome/Firefox, Capybara-style interaction, and parallel crawling.

## Use cases
- scrape structured data from websites without writing selectors
- crawl paginated search results into JSON
- extract data from JavaScript-rendered pages with headless Chrome
- build Ruby spiders with delays and parallel crawling
- use an LLM once to generate reusable extraction rules
- scrape sites behind anti-bot protection with an antidetect browser

## When to choose
- you write scrapers in Ruby and want a Scrapy-like framework
- you want AI-generated selectors without per-request LLM costs
- you need JS rendering or anti-bot evasion built in
- you want to mix manual XPath with AI extraction in one codebase

## When to avoid
- you need a Python or Node scraping stack
- you want fully selector-free LLM extraction on every request
- your project requires a battle-tested framework with a large community
- you cannot send page HTML to an external LLM provider

## Facets
- artifact type: framework
- maturity: active
- function: web-scraping, parser, llm-inference, http-client, browser-extension
- domain: web-development, crawlers, large-language-models
- platform: ruby
- tags: scraping-framework, ai-assisted-extraction, headless-browser, antidetect-browser, capybara, xpath, crawler, selector-caching, vibe-scraping, automation, data-engineering, linux, macos, docker

## Member repositories
- vifreefly/kimuraframework (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:35.858744+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 2026-08-30T06:45:39.886556+00:00, confidence not recorded.
  - readme: https://github.com/vifreefly/kimuraframework (fetched 2026-08-28T04:03:35.858744+00:00, sha 7dbccd80fc25)
  - homepage: https://kimur.ai/framework (fetched 2026-08-29T12:48:33.828740+00:00, sha 38ca5510ee44)
  - site_page: https://kimur.ai/ (fetched 2026-08-29T12:48:33.838734+00:00, sha 4c2d123c081d)
- Data as of 2026-08-30T08:39:29.467469+00:00.