Give your agents direct API access to any website.
Hermai discovers each site's internal endpoints and returns structured JSON directly — no browser, no HTML, no token waste.
Integrates with
Catalog
Trending this week
Health-driven rankings. Schemas auto-promoted by live telemetry — broken ones fall out, verified ones rise.
Trending this week
Most fetched by agents in the last 7 days
Crypto market prices, volume, and market cap (official API)
Search repositories by query with stars and language filters
Search products by keyword with price and rating filters
Full-text search Wikipedia articles (official API)
Search tracks, albums, and artists (official API)
Recently verified
Live-checked in the last hour
Crypto market prices, volume, and market cap (official API)
Full-text search Wikipedia articles (official API)
Search tracks, albums, and artists (official API)
Search repositories by query with stars and language filters
Search preprints by query, author, and category
Most fetched
All-time pull volume
Crypto market prices, volume, and market cap (official API)
Search repositories by query with stars and language filters
Search products by keyword with price and rating filters
Full-text search Wikipedia articles (official API)
Search tracks, albums, and artists (official API)
Browse
Explore by category
Eleven top-level categories following the intent taxonomy — the vocabulary agents use to describe what they want.
Travel
Flights, stays, trips
Commerce
Products and marketplaces
Food
Restaurants, menus, delivery
Media
Music, video, entertainment
Finance
Markets, crypto, equities
Real estate
Homes and rentals
Jobs
Roles and hiring
Communication
Social feeds and messaging
Productivity
Notes, calendar, tasks
Knowledge
Wikis, research, news
Developer
Code, packages, infra
How it works
Three commands to get any website's data.
Hermai publishes metadata — the full technical package (URLs, headers, params, selectors) is delivered to your machine when you pull it. You stay in control of execution.
Find a schema
Search the catalog by site or intent category. Each entry shows health, last verified time, and the fields you'll get back.
$ hermai search "hotel search" booking/hotels-search travel.accommodation.search verified · 1h airbnb/listings-search travel.accommodation.search verified · 2h kayak/flights-search travel.transportation.search verified · 3h
Pull and run
Fetch executes the schema on your machine. No hosted runtime in the loop — your CLI (or curl) talks to the site directly.
$ hermai fetch booking.com --action search \
--param destination="Tokyo" \
--param check_in=2026-05-01 \
--param guests=2Get structured JSON
Response comes back as clean JSON — the fields you saw on the catalog card, with real values. Ready for an LLM to reason over.
{
"hotels": [
{
"name": "Park Hyatt Tokyo",
"price_total": 842,
"currency": "USD",
"review_score": 9.2
}
]
}Benchmarks
Real sites. Real numbers.
Four sites where generic scrapers struggle, measured head-to-head against two tools agent builders actually reach for first: Firecrawl, the popular hosted scraper, and Claude Code's built-in WebFetch tool. Same network, cold fetch, single connection.
Search for-sale listings in a ZIP
41 listings · 50 fields each
~9 listings in noisy markdown
403 — PerimeterX wall
Fetch a product with its variants
Full product · 7 variants · SKUs
1 product, mixed with promo HTML
No inventory / no variant IDs
Fetch full quote for a ticker
Full quote · 50 fields
Quote, but mixed with ads
JS-rendered — empty payload
Fetch repo metadata
Repo metadata · 80 fields
README + UI chrome
Summary only, rounded counts
April 2026 · Oakland, CA · cold fetch, single connection