Stealth rendering, structured extraction, domain search, and multi-source research. Pay per request. No API keys.
Most AI agents can't run a browser. ClawFetch gives them eyes.
Puppeteer with anti-detection beats Cloudflare, CAPTCHAs, and JS-heavy SPAs that basic HTTP can't touch.
17 site-specific parsers: Twitter, GitHub, CoinGecko, NPM, PyPI, crates.io, Hacker News, YouTube, Wikipedia, Product Hunt, IMDb, Amazon, Crunchbase, SEC EDGAR, Zillow, Redfin, and news articles. Clean typed JSON, not messy HTML.
Check domain availability via WHOIS. Single names, bulk TLD checks, or keyword-based suggestions with auto-check.
Send a topic, get structured results from 5+ sources. One request replaces a dozen fetches.
Pre-warmed Puppeteer instances. No cold starts, sub-second for cached content, under 2s for fresh renders.
USDC on Base. No API keys, no accounts, no subscriptions. Standard X402 protocol โ any agent can pay.
JSON in, JSON out. Every response is token-efficient and structured for agent consumption.
Basic HTTP fetch โ clean text. Fast, no JS rendering. For static pages, APIs, and simple content.
curl -X POST https://api.clawfetch.ai/fetch \
-H "Content-Type: application/json" \
-d '{"url": "https://docs.example.com", "maxChars": 5000}'
Full Puppeteer render with stealth. Handles Cloudflare, bot detection, and JS-heavy SPAs. Optional CSS selector wait.
curl -X POST https://api.clawfetch.ai/render \
-H "Content-Type: application/json" \
-d '{"url": "https://app.uniswap.org", "waitFor": ".swap-page"}'
Structured extraction via site-specific parsers. Returns typed fields โ not raw text.
curl -X POST https://api.clawfetch.ai/extract \
-H "Content-Type: application/json" \
-d '{"url": "https://github.com/openclaw/openclaw"}'
{
"type": "github",
"name": "openclaw",
"stars": "2.4k",
"forks": "312",
"language": "TypeScript",
"topics": ["ai", "agents"]
}
Check domain availability via WHOIS. Pass a name + TLD list, or an explicit domain array. Returns registrar, expiry, and creation dates for taken domains.
curl -X POST https://api.clawfetch.ai/domains/check \
-H "Content-Type: application/json" \
-d '{"name": "myproject", "tlds": ["com", "ai", "io", "dev"]}'
{
"checked": 4,
"available": 2,
"taken": 2,
"results": [
{"domain": "myproject.com", "available": false, "registrar": "GoDaddy", "expiryDate": "2027-03-15"},
{"domain": "myproject.ai", "available": true},
{"domain": "myproject.io", "available": true},
{"domain": "myproject.dev", "available": false, "registrar": "Google LLC"}
]
}
Generate domain name ideas from keywords, then check availability. Combines words with common prefixes (get, try, my) and suffixes (hq, app, hub, ai).
curl -X POST https://api.clawfetch.ai/domains/suggest \
-H "Content-Type: application/json" \
-d '{"keywords": ["agent", "fetch"], "tlds": ["com", "ai"], "maxCheck": 20}'
{
"keywords": ["agent", "fetch"],
"generated": 72,
"checked": 20,
"available": ["getagentfetch.ai", "fetchagent.ai", "agentfetchhq.com"]
}
Multi-source topic research. Searches the web, fetches top results, returns structured summaries from 5+ sources in one call.
curl -X POST https://api.clawfetch.ai/research \
-H "Content-Type: application/json" \
-d '{"query": "Casper Network DeFi", "maxResults": 5}'
Service status, browser pool stats, cache stats, and available extractors. Always free.
List all structured extractors with supported domains and output fields.
twitter x.com, twitter.com โ author, text, likes, reposts, views, media
coingecko coingecko.com โ name, price, marketCap, volume, rank
github github.com โ name, stars, forks, language, readme
news any article (public) โ title, author, date, body, source
npm npmjs.com โ name, version, downloads, dependencies
pypi pypi.org โ name, version, author, license, requires_python
crates crates.io โ name, version, downloads, features
hackernews news.ycombinator.com โ title, author, score, comments, url
youtube youtube.com, youtu.be โ title, channel, duration, views
wikipedia wikipedia.org โ title, summary, sections, references
producthunt producthunt.com โ name, tagline, votes, topics, makers
edgar sec.gov โ name, cik, ticker, filings, financials
imdb imdb.com โ title, rating, cast, plot, genres, runtime
amazon amazon.com โ title, price, rating, reviews, features
crunchbase crunchbase.com โ name, funding, founders, categories
zillow zillow.com โ address, price, zestimate, beds, baths, sqft
redfin redfin.com โ address, price, estimate, beds, baths, sqft
Raw HTML + GPT costs $0.03โ$0.38 per extraction. ClawFetch does it for $0.003. Deterministic, no hallucinations.
$167
per 1,000 extractions
Fetch HTML (~50k tokens) โ send to LLM โ parse response โ hope it doesn't hallucinate fields
$3
per 1,000 extractions
One API call โ deterministic typed JSON โ same output every time โ we fix breakage, not you
Same URL โ same structured JSON. No hallucinated fields, no varying formats. Test once, trust always.
Every field comes from the actual page โ parsed, not generated. No LLM in the extraction loop means no invented data, ever.
17 extractors return strictly typed schemas. Prices are numbers, dates are dates, lists are lists. Your agent gets clean data it can act on without guessing.
No accounts. No subscriptions. No minimums. Just USDC on Base.
Standard X402 โ the HTTP 402 status code, finally used as intended.
npm install @x402/fetch @x402/evm โ wrap your fetch with automatic payment handling.
The SDK signs a gasless EIP-3009 authorization. No ETH needed โ just USDC in your wallet on Base.
The facilitator verifies the signature, settles on-chain, and you get your response. One round-trip.
0x67439832C52C92B5ba8DE28a202E72D09CCEB42f
0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913
Drop this SKILL.md into your agent's skills directory. Works with OpenClaw, Claude Code, Codex, and any agent that supports the Agent Skills format.
---
name: clawfetch
description: Web intelligence API for AI agents. Stealth rendering, 17 structured
extractors (Twitter, GitHub, CoinGecko, NPM, PyPI, crates.io, Hacker News,
YouTube, Wikipedia, Product Hunt, IMDb, Amazon, Crunchbase, SEC EDGAR, Zillow,
Redfin, news), domain search, and multi-source research. Gasless USDC payments
on Base via standard X402 protocol.
metadata:
author: jean-clawd
version: "2.0"
website: https://clawfetch.ai
twitter: "@ClawFetchAI"
compatibility: Requires HTTP client, ethers.js or viem for signing, USDC on Base.
---
# ClawFetch.ai โ Web Intelligence for AI Agents
Base URL: `https://api.clawfetch.ai`
## Quick Start
### 1. Create a Base Wallet
```javascript
import { ethers } from 'ethers';
const wallet = ethers.Wallet.createRandom();
console.log('Address:', wallet.address);
console.log('Private Key:', wallet.privateKey);
// Save the private key securely!
```
### 2. Get USDC on Base
Ask your human to send USDC to your wallet on the Base network.
Even $0.50 covers hundreds of API calls. **No ETH needed** โ X402 is gasless!
### 3. Install the X402 Client SDK
```bash
npm install @x402/fetch @x402/evm ethers
```
### 4. Make Requests (Payment is Automatic)
```javascript
import { wrapFetchWithPayment } from '@x402/fetch';
import { ExactEvmScheme } from '@x402/evm/exact/client';
import { toClientEvmSigner } from '@x402/evm';
import { privateKeyToAccount } from 'viem/accounts';
import { createPublicClient, http } from 'viem';
import { base } from 'viem/chains';
const account = privateKeyToAccount(process.env.EVM_PRIVATE_KEY);
const publicClient = createPublicClient({ chain: base, transport: http() });
const signer = toClientEvmSigner(account, publicClient);
const fetchWithPay = wrapFetchWithPayment(fetch, [new ExactEvmScheme(signer)]);
// Now use it like normal fetch โ payments happen automatically!
const res = await fetchWithPay('https://api.clawfetch.ai/render', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ url: 'https://example.com' }),
});
const data = await res.json();
```
## Endpoints & Pricing
| Endpoint | Price | Description |
|-----------------------|--------|--------------------------------|
| POST /fetch | 0.1ยข | Basic HTTP โ clean text |
| POST /render | 0.2ยข | JS rendering with stealth |
| POST /extract | 0.3ยข | Structured JSON extraction |
| POST /domains/check | 0.2ยข | Domain availability via WHOIS |
| POST /domains/suggest | 0.2ยข | Generate + check domain names |
| POST /research | 1ยข | Multi-source topic research |
| GET /extractors | 0.1ยข | List available extractors |
| GET /health | Free | Service status |
## Payment (X402 Protocol โ Gasless)
Standard X402 with EIP-3009 (TransferWithAuthorization):
- Network: Base mainnet (eip155:8453)
- Token: USDC (0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913)
- Wallet: 0x67439832C52C92B5ba8DE28a202E72D09CCEB42f
- **No ETH needed** โ the facilitator handles gas
The SDK handles everything: detect 402 โ sign authorization โ retry โ get data.
## Available Extractors (17)
- **twitter** โ x.com โ author, text, likes, reposts, views, media
- **coingecko** โ coingecko.com โ name, price, marketCap, volume, rank
- **github** โ github.com โ name, stars, forks, language, readme
- **news** โ any public article โ title, author, date, body, source
- **npm** โ npmjs.com โ name, version, downloads, dependencies
- **pypi** โ pypi.org โ name, version, author, license, requires_python
- **crates** โ crates.io โ name, version, downloads, features
- **hackernews** โ news.ycombinator.com โ title, author, score, comments, url
- **youtube** โ youtube.com, youtu.be โ title, channel, duration, views
- **wikipedia** โ wikipedia.org โ title, summary, sections, references
- **producthunt** โ producthunt.com โ name, tagline, votes, topics, makers
- **edgar** โ sec.gov โ company profile, CIK, filings, XBRL financials
- **imdb** โ imdb.com โ title, rating, cast, plot, genres, runtime
- **amazon** โ amazon.com โ title, price, rating, reviews, features, BSR
- **crunchbase** โ crunchbase.com โ name, funding, founders, categories
- **zillow** โ zillow.com โ address, price, Zestimate, beds, baths, sqft
- **redfin** โ redfin.com โ address, price, estimate, beds, baths, sqft
## Cost Estimates
$1 USDC gets you: 1,000 fetches, 500 renders, 333 extractions, or 100 researches.