crw
Ochiq manbalardanRust tilida yozilgan tez va yengil Firecrawl/Tavily muqobili. AI agentlar uchun veb-skreper, kroler va qidiruv API hamda MCP server. Firecrawl bilan mos API (/scrape, /crawl, /search). 1K URL sinovlarida Tavilydan 2,3 baravar, Firecrawldan 1,5 baravar tez. 6 MB RAM, yagona ikkilik fayl. Oʻz serveringizda joylashtiring yoki ma
Mashina tarjimasi · Asl matnni koʻrsatish
Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary. Self-host or use ma
Sharh
- ai
- ai-agents
- crawler
- data-extraction
- docker
- firecrawl-alternative
- html-to-markdown
- llm
- markdown
- mcp
Oʻrnatish
Buyruqlar faqat koʻrsatiladi, marketpleys ularni bajarmaydi. Rasmiy hujjatlar bilan solishtiring.- Rasmiy saytOchiq manbalardankatalog metamaʼlumotlaridanfastcrw.com/ ↗
- Rasmiy reliz fayllariOchiq manbalardanoxirgi rasmiy relizdangithub.com/fastcrw/crw/releases/tag/v0.39.1 ↗
- Manbadan yigʻishOchiq manbalardankatalog metamaʼlumotlaridan
Manbadan yigʻish: tekshirilgan yigʻish retsepti yoʻq — repozitoriy koʻrsatmalariga amal qiling.
github.com/fastcrw/crw ↗
Moslik
«Nomaʼlum» dalil topilmaganini bildiradi, mahsulot mos emasligini emas.| Platforma | Holat | Arxitektura | Dalil | Ishonchlilik |
|---|---|---|---|---|
| Claude (web & desktop) | Nomaʼlum | — | — | — |
| Claude Code | Nomaʼlum | — | — | — |
| Cursor | Nomaʼlum | — | — | — |
| VS Code | Nomaʼlum | — | — | — |
| Windsurf | Nomaʼlum | — | — | — |
| ChatGPT | Nomaʼlum | — | — | — |
| Windows | Mos | arm64 | v0.39.1 relizidagi rasmiy yigʻma: crw-mcp-win32-arm64.zip | 0.70 |
| Mos | x86_64 | v0.39.1 relizidagi rasmiy yigʻma: crw-mcp-win32-x64.zip | 0.70 | |
| macOS | Mos | arm64 | v0.39.1 relizidagi rasmiy yigʻma: crw-darwin-arm64.tar.gz | 0.70 |
| Mos | x86_64 | v0.39.1 relizidagi rasmiy yigʻma: crw-darwin-x64.tar.gz | 0.70 | |
| Linux | Mos | arm64 | v0.39.1 relizidagi rasmiy yigʻma: crw-linux-arm64.tar.gz | 0.70 |
| Mos | x86_64 | v0.39.1 relizidagi rasmiy yigʻma: crw-linux-x64.tar.gz | 0.70 |
Relizlar
tekshirilgan: 29-okt, 20260.39.1 versiyasi fayllari
| Fayl | Platforma | Hajm | SHA-256 | Rasmiy manbadan yuklab olish |
|---|---|---|---|---|
| crw-darwin-arm64.tar.gz | macos · arm64 · tarball | 11,8 MB | 1db251678dc8… | Rasmiy manba ↗ |
| crw-darwin-x64.tar.gz | macos · x86_64 · tarball | 13 MB | 17cb7b10fc7d… | Rasmiy manba ↗ |
| crw-linux-arm64.tar.gz | linux · arm64 · tarball | 12,1 MB | 02c24e898c49… | Rasmiy manba ↗ |
| crw-linux-x64.tar.gz | linux · x86_64 · tarball | 13,5 MB | 0263c8b68365… | Rasmiy manba ↗ |
| crw-mcp-darwin-arm64.tar.gz | macos · arm64 · tarball | 8,9 MB | ba49dda76366… | Rasmiy manba ↗ |
| crw-mcp-darwin-x64.tar.gz | macos · x86_64 · tarball | 9,7 MB | bb9936799a3a… | Rasmiy manba ↗ |
| crw-mcp-linux-arm64.tar.gz | linux · arm64 · tarball | 9,1 MB | 73b2ba350ff2… | Rasmiy manba ↗ |
| crw-mcp-linux-x64.tar.gz | linux · x86_64 · tarball | 10,2 MB | 928f47a0ebce… | Rasmiy manba ↗ |
| crw-mcp-win32-arm64.zip | windows · arm64 · zip | 9,6 MB | aebad7895b6a… | Rasmiy manba ↗ |
| crw-mcp-win32-x64.zip | windows · x86_64 · zip | 10,3 MB | ddd50c277126… | Rasmiy manba ↗ |
| crw-server-darwin-arm64.tar.gz | macos · arm64 · tarball | 9,8 MB | fb857698d1ab… | Rasmiy manba ↗ |
| crw-server-darwin-x64.tar.gz | macos · x86_64 · tarball | 10,7 MB | 86d255bfbcc9… | Rasmiy manba ↗ |
| crw-server-linux-arm64.tar.gz | linux · arm64 · tarball | 10 MB | 22aade33d968… | Rasmiy manba ↗ |
| crw-server-linux-x64.tar.gz | linux · x86_64 · tarball | 11,2 MB | 1a821838d709… | Rasmiy manba ↗ |
| crw-server-win32-arm64.zip | windows · arm64 · zip | 10,7 MB | feea9909a04c… | Rasmiy manba ↗ |
| crw-server-win32-x64.zip | windows · x86_64 · zip | 11,4 MB | 77a4bff3b1d7… | Rasmiy manba ↗ |
| crw-win32-arm64.zip | windows · arm64 · zip | 13 MB | eaf5f93266bc… | Rasmiy manba ↗ |
| crw-win32-x64.zip | windows · x86_64 · zip | 14 MB | a6d997a34f04… | Rasmiy manba ↗ |
| SHA256SUMS | nazorat summalari | 1,6 KB | a03bbbb0bbde… | Rasmiy manba ↗ |
| release-audit-0.39.1.md | boshqa | 190 B | 9144ea73b6f0… | Rasmiy manba ↗ |
| SHA256SUMS.sigstore.json | imzo | 9,8 KB | 7ef2092a3de9… | Rasmiy manba ↗ |
Relizlar tarixi
- v0.39.021-okt, 2026Rasmiy manba ↗
- v0.38.020-okt, 2026Rasmiy manba ↗
- v0.37.230-sen, 2026Rasmiy manba ↗
- v0.37.130-sen, 2026Rasmiy manba ↗
- v0.37.029-sen, 2026Rasmiy manba ↗
- v0.36.019-sen, 2026Rasmiy manba ↗
- v0.35.110-sen, 2026Rasmiy manba ↗
Sifat profili
algoritm quality-v1.0 · baholangan 15-okt, 2026Baho tarkibi
Litsenziya
AGPL-3.0Bu katalog siyosati holati, yuridik xulosa emas.
Manbalar
Sharhlar
Hali sharhlar yoʻq.
Muqobillar
README
fastcrw/crw dan · litsenziya AGPL-3.0 · yuklangan 29-okt, 2026One-command install
curl -fsSL https://fastcrw.com/install | sh
Runs local and free, no account needed. To use the Cloud, paste your key into the same command and it installs the binary, connects the key, and registers the MCP server with the AI coding tools you already have:
curl -fsSL https://fastcrw.com/install | CRW_API_KEY=crw_live_... sh
crw search "rust tutorials"
Claude Code, Cursor, Codex, Gemini CLI, OpenCode and Windsurf are picked up
automatically when they are already set up; nothing else is touched, and your
key stays in ~/.config/crw/config.toml rather than being copied into each
tool. Add CRW_NO_AGENTS=1 to skip that step, or run crw setup on its own to
choose interactively.
1000 free credits, no credit card. Managed proxies, JS rendering and search, with nothing to run or keep up to date. Get my free key →
macOS and Linux, Intel and ARM. More install options →
What it does
| Operation | Outcome |
|---|---|
| Scrape | One URL to markdown, HTML, links, screenshots, or schema JSON |
| Crawl | Follow a bounded site crawl and collect its pages |
| Map | Discover URLs without scraping every page |
| Search | Search the web and optionally scrape selected results |
| Extract | Produce structured fields from one or many URLs |
Why fastCRW
On Firecrawl's own public 1,000-URL dataset, fastCRW recovered more truth than Crawl4AI and Firecrawl, matched the fastest median latency, and idled at ~14 MB RAM.
On a different benchmark entirely, answer accuracy rather than scrape recall, fastCRW answers 90.0% of the 600 AA-Omniscience questions correctly. Every product listed on the Artificial Analysis Search Index sits below it.
Choose how you use it
CLI
crw https://example.com # scrape, works right after install
crw search "rust async runtime" # search, after `crw setup`
Python SDK
Using Cloud? Get an API key, then export it once:
export CRW_API_KEY="crw_live_..."
pip install crw
from crw import CrwClient
client = CrwClient()
page = client.scrape("https://example.com", formats=["markdown"])
print(page["markdown"])
npm install crw-sdk
import { CrwClient } from "crw-sdk";
const client = new CrwClient();
const page = await client.scrape("https://example.com", {
formats: ["markdown"],
});
console.log(page.markdown);
Local mode and more SDK examples → · REST API →
MCP for AI agents
npx -y crw-mcp@latest install
Installs the CRW skill and MCP server in your detected AI tools. crw setup can
also do this step, so either path is enough.
Manual setup →
Choose where it runs
| Managed API | Local / self-hosted | |
|---|---|---|
| Best for | Zero infrastructure and managed scaling | Data control, private networks, or custom infrastructure |
| Start | Create an API key, then crw setup | Install and run crw <URL> |
| Operations | Managed proxies, billing, and hosted capabilities | You choose renderers, search, auth, proxies, and capacity |
Capabilities and response shapes can differ by deployment:
/v1/capabilities · response shapes
Learn more
Contributing
The workspace requires Rust 1.85 or newer:
git clone https://github.com/fastcrw/crw
cd crw
make check-fast
Contributors
crw is better because of these people. Thank you, all of you:
Engine and MCP server: AGPL-3.0. Python and TypeScript SDKs: MIT. Embedding license: hello@fastcrw.com.
Star History
Please respect website policies. Crawl and map follow robots.txt by default.