hanzo.ai/app/(marketing)/engine/page.tsx

'use client'

import { ArrowRight, Boxes, Cpu, Gauge, Layers, Server, Shield, Zap } from 'lucide-react'
import { ProductLanding } from '@/components/product/ProductLanding'
import { ProductFooter } from '@/components/products/ProductFooter'
import { useI18n } from '@hanzo/i18n/react'

/**
 * Hanzo Engine, through the ONE product kit.
 *
 * The largest cluster left: TWELVE pages — engine, gateway, guard, ingress,
 * jin, metrics, o11y, operator, sentinel, skills, telemetry, visor — at 85%+
 * identical className sets, each a hero, a six-card grid and a call to action
 * written out again. All twelve pass one typed props object to
 * `ProductLanding`. See LLM.md, "Tailwind is NOT gone".
 *
 * EVERY WORD IS THE ONE THAT WAS HERE. ProductFooter came out of the final
 * card's `max-w-3xl` wrapper, where it had been rendering narrower than on
 * every other product page.
 */

export default function HanzoEnginePage() {
  const { t } = useI18n()
  return (
    <>
      <ProductLanding
        badge={"hanzoai/engine"}
        badgeIcon={Cpu}
        title={"Hanzo Engine"}
        tagline={t("The inference engine, in one binary")}
        lede={t("Name a model on Hugging Face and it runs. Engine quantizes it for the hardware it finds, then serves an HTTP API and a web chat from the same process — text, vision, audio, speech, image and embeddings, without a second stack underneath.")}
        ctas={[
          { label: t("View on GitHub"), href: "https://github.com/hanzoai" },
        ]}
        what={{
          title: t("One process, laptop to GPU cluster"),
          sub: t("Chat, an API server, and a benchmark are three commands on the same binary. There is no Python interpreter under any of them."),
          pillars: [
            {
              icon: Zap,
              title: "run, serve, bench",
              body: t("One binary, three verbs. Chat with a model, put it behind an HTTP API, or measure it — the thing you benchmarked is the thing you shipped."),
            },
            {
              icon: Gauge,
              title: t("Built to serve, not just to run"),
              body: t("Paged attention and continuous batching keep the card busy across concurrent requests. A disk-first KV cache carries a session across a restart, so an agent that reuses a long prefix does not pay for it twice."),
            },
            {
              icon: Layers,
              title: t("More than text"),
              body: t("Vision, audio, speech, image and embeddings go through the same modality pipeline as generation, in the same process. A multimodal app is one deployment, not four."),
            },
            {
              icon: Boxes,
              title: t("It quantizes on the way in"),
              body: t("In-situ quantization of any Hugging Face model, plus GGUF from 2 to 8 bits, GPTQ, AWQ, HQQ, FP8 and bitsandbytes. Ask for a level and it takes a published prebuilt when one exists, or makes one when it doesn't."),
            },
            {
              icon: Server,
              title: t("The silicon you have"),
              body: t("CUDA with FlashAttention and multi-GPU tensor parallelism, Metal on Apple Silicon, or plain CPU. Same engine and same commands on each, and a doctor command that reports what it found."),
            },
            {
              icon: Shield,
              title: t("Tools, and a UI to watch them"),
              body: t("It can call MCP servers over a process, HTTP or a WebSocket. The built-in UI at /ui shows reasoning, code execution and plots inline, and edits branch a conversation with its own state. Pass --no-ui and it is a plain API server."),
            },
          ],
        }}
        finalCta={{
          title: t("Get started with Hanzo Engine"),
          buttons: [
            { label: t("View on GitHub"), href: "https://github.com/hanzoai" },
          ],
        }}
      />
      <ProductFooter slug={"engine"} name={"Engine"} />
    </>
  )
}