Skip to content

feat: add fastCRW tool#363

Open
us wants to merge 1 commit into
agentstack-ai:mainfrom
us:feat/add-fastcrw
Open

feat: add fastCRW tool#363
us wants to merge 1 commit into
agentstack-ai:mainfrom
us:feat/add-fastcrw

Conversation

@us

@us us commented Jun 14, 2026

Copy link
Copy Markdown

What

Adds fastCRW as a web scrape/search provider, alongside the existing Firecrawl integration — additive only, Firecrawl untouched.

Why

fastCRW is a self-hostable, fully open-source (AGPL) web engine — single ~8MB Rust binary, ~6MB RAM.

Runs 100% locally with full capability. Anti-bot/stealth, BYO-proxy + rotation, and JS rendering (Cloudflare JS-challenge, SPA) all ship in the open core. Firecrawl's OSS self-host gates its stealth engine (fire-engine) behind a cloud-only flag, so its self-hosted instance falls back to plain fetch/Playwright and can't reliably reach protected or JS-heavy pages. fastCRW's open binary has no such gap.

Faster and higher-recall on Firecrawl's own benchmark dataset. Truth-recall 63.74% vs 56.04%; median latency p50 ~1.9s vs ~2.3s. One binary, no multi-service stack.

Search is SearXNG-backed with added reranking and multi-round retrieval for higher-quality results.

Key via CRW_API_KEY (free tier at https://fastcrw.com/dashboard); self-host base URL supported. Happy to adjust to your conventions — I maintain the integration and can provide free credits to evaluate.

Because fastCRW is Firecrawl-API-compatible, the integration diff is tiny and purely additive — that's why it mirrors the Firecrawl wiring with minimal code.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant