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

0xMassi/webclaw

Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API, and MCP server. observed · 2026-08-28

github.com/0xMassi/webclaw · homepage · Rust · AGPL-3.0 (copyleft) observed · 2026-08-28

Health v2 · maintenance only

77/100

  • Activity 99
  • Release rhythm 86
  • 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: 0.0
  • age_days: 176
  • days_rel: 17
  • days_push: 7
  • n_releases_24m: 61

Full methodology

Adoption not part of the score

2305 stars · 232 forks observed · 2026-08-28

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

webclaw is a Rust-based web extraction toolkit that turns any URL into clean, LLM-ready markdown, JSON, or token-optimized text, including bot-protected pages. It ships as three binaries sharing one engine: a CLI, an axum-based REST API server, and an MCP server with 14 tools for AI clients like Claude and Cursor.

Use cases

  • scrape a webpage into clean markdown for an LLM prompt
  • crawl an entire docs site and export every page as markdown
  • convert HTML to LLM-optimized text with 90% fewer tokens
  • extract structured JSON from a URL matching a schema
  • plug live web access into Claude Desktop or Cursor via MCP
  • monitor a webpage for changes with diffs
  • self-host a Firecrawl alternative for RAG ingestion

When to choose

  • you need LLM-ready web content instead of raw HTML boilerplate
  • you want a self-hostable, fast Rust alternative to Firecrawl or Jina
  • you need MCP integration so AI agents can read the live web
  • you scrape bot-protected sites and need TLS fingerprinting
  • you want CLI, REST API, and MCP access from one extraction engine

When to avoid

  • you need a fully managed scraping service and don't want to self-host or pay for the cloud API
  • you only need simple static HTML parsing in a language other than Rust
  • your use case requires heavy JavaScript rendering at scale beyond what the engine handles
  • you need a permissive license — the core is AGPL-3.0

Facets

cli-tool · maturity active

web-scraping parser rag mcp http-server cli search-engine web-development crawlers large-language-models developer-tools cli self-hosted cross-platform rust html-to-markdown firecrawl-alternative mcp-server llm-ready tls-fingerprinting rest-api web-crawler bot-protection-bypass ai-agents retrieval-augmented-generation natural-language-processing web-server

10 sources

Member repositories

RepositoryRoleHealth v2
0xMassi/webclawmain77

For agents

markdown · JSON · MCP: product_card(name="0xMassi/webclaw")

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