SchemasSolutionsPlaygroundPricingDocsBlog
GitHubStarLog inStart free

Blog

Notes from building Hermai AI.

Launch posts, spec drafts, engineering writeups, and trust rationale.

FeaturedProductMay 15, 2026·5 min read

Most AI agents are using the slowest possible API

Browser automation made agents useful on the web, but it is also the highest-latency, highest-token way to reach data that already exists as JSON.

by Hermai AI Team

ProductApr 7, 2026·4 min read

Introducing Hermai AI: the open catalog of website APIs

Models have HuggingFace. Agents do not have anything equivalent for the websites they need to reach. Here is why we are building one.

by Hermai AI Team

EngineeringApr 5, 2026·5 min read

Schema format v0.1: what goes in, what stays private

Every schema has a public card and a private package. This is where we draw the line and why the line matters.

by Hermai AI Team

OperationsMar 28, 2026·6 min read

Catalog and runtime: how we think about legal posture

The short version: the public catalog should publish facts about schemas, while execution happens through explicit local or authenticated hosted paths.

by Hermai AI Team

Subscribe via RSS · or follow us on X / GitHub

The open catalog of website APIs.

Catalog

  • Browse schemas
  • Website APIs for AI agents
  • Government
  • Submit a schema
  • Playground
  • Changelog

Developers

  • Docs
  • Quickstart
  • FAQ
  • Blog
  • Hermai vs Firecrawl
  • Hermai vs Apify
  • Hermai vs Jina Reader
  • Hermai vs ScrapingBee
  • Hermai vs Diffbot
  • Roadmap

Community

  • GitHub
  • Discord
  • X / Twitter

© 2026 Hermai AI

PrivacyTermsTrustTakedownContact