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

Anakin-Inc/anakin

Open-source web scraping API. Turn any website into clean markdown or structured JSON. Anti-detect browser, proxy auto-selection, self-hosted. One command: make up observed · 2026-08-28

github.com/Anakin-Inc/anakin · homepage · Go · AGPL-3.0 (copyleft) observed · 2026-08-28

Health v2 · maintenance only

73/100

  • Activity 98
  • Release rhythm 76
  • Longevity 12

Flags: young

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: 4
  • age_days: 169
  • days_rel: 163
  • days_push: 15
  • n_releases_24m: 2

Full methodology

Adoption not part of the score

2302 stars · 139 forks observed · 2026-08-28

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

AnakinScraper OSS is a self-hosted web scraping API written in Go that turns any website into LLM-ready markdown or structured JSON via a simple REST endpoint. It combines an anti-detect browser (Camoufox), ML-based smart proxy selection, and a fallback handler chain (HTTP fetch → browser → external API) to scrape sites that block bots.

Use cases

  • scrape websites into clean markdown for LLM and RAG pipelines
  • extract structured JSON data from web pages with AI
  • self-host a Firecrawl alternative with one docker command
  • scrape JavaScript-heavy sites that block headless browsers
  • crawl pages behind CAPTCHAs and bot detection
  • feed live web data into AI agents and chatbots
  • monitor website content changes with per-domain scraping configs
  • reduce paid scraping API costs with local-first handler fallback

When to choose

  • you need a self-hosted scraping API with no cloud dependency and a single Go binary
  • your targets use aggressive anti-bot measures requiring an anti-detect browser
  • you want LLM-ready markdown or AI-structured JSON output for RAG or agents
  • you want to minimize paid scraping API spend by only falling back to external services when local handlers fail
  • you need per-domain scraping strategies with failure detection and auto-retry

When to avoid

  • you only need simple static HTML fetching without anti-detection
  • you want a managed hosted service rather than running your own infrastructure
  • AGPL-3.0 licensing is incompatible with your product's distribution model
  • you need a pure Python or Node scraping framework with deep programmatic control like Scrapy or Crawlee

Facets

service · maturity active

web-scraping http-server api-framework rag nlp proxy crawlers web-development artificial-intelligence self-hosted apis self-hosted go windows cli anti-detect-browser camoufox playwright markdown-conversion structured-extraction handler-chain firecrawl-alternative llm-ready proxy-rotation crawler retrieval-augmented-generation data-engineering docker linux macos web-server

10 sources

Member repositories

RepositoryRoleHealth v2
Anakin-Inc/anakinmain73

For agents

markdown · JSON · MCP: product_card(name="Anakin-Inc/anakin")

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