feat: add fastCRW search provider#253
Open
us wants to merge 1 commit into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Adds fastCRW as a search provider (
FastCrwSearchStrategy), alongside Firecrawl.Registered in the web-search provider factory.
Why
fastCRW is a faster, more open alternative to Firecrawl for web scraping and search — and it runs 100% locally with no cloud dependency.
Runs fully locally, nothing gated: fastCRW is a single ~8MB Rust binary (AGPL). Anti-bot/stealth bypass, BYO-proxy + rotation, and JS/SPA rendering all ship in the open core. Firecrawl's OSS self-host gates its stealth engine (
fire-engine) behind a cloud-only flag, so a self-hosted Firecrawl instance falls back to plain fetch/Playwright and can't reliably reach protected or JS-heavy sites. fastCRW's self-host can.Higher recall, lower latency — on Firecrawl's own benchmark dataset: truth-recall 63.74% vs 56.04%; median latency (p50) ~1.9s vs ~2.3s. Single binary, ~6MB RAM at idle.
Search backed by SearXNG — with a quality layer on top: crw is not an alternative to SearXNG, it is built on top of it. SearXNG is the metasearch aggregator underneath; crw adds query expansion (multi-variant rewrite), content-aware reranking (re-scoring by fetched content instead of SearXNG's content-blind ordering), and category routing (research queries fan out to arxiv / semantic scholar / google scholar, code queries to GitHub). The result is SearXNG's breadth plus a measurable accuracy layer — all open-source (AGPL) and self-hostable with configurable engines.
The integration is a small additive diff (Firecrawl untouched) specifically because fastCRW is Firecrawl-API-compatible — drop-in, same shape.
Key via
CRW_API_KEY(free tier at https://fastcrw.com/dashboard); self-host base URL supported. I maintain fastCRW and can provide free credits — happy to adjust to your conventions.