Inference Logoinference.sh

react components

AI-native react components.

chat, generative UI, tool approvals. drop in, connect to any inference.sh agent, ship.

get startedview components
app.tsxtsx
import { AgentChatProvider, Chat }
  from '@inference/ui'

<AgentChatProvider agent="my-agent">
  <Chat />
</AgentChatProvider>
rendered
generate a photo of an orange cat on a windowsill
Generated: orange tabby cat on windowsillgenerated with pruna/flux-dev in 7.9s
type a message...

full agent chat in 4 lines.

not just chat

30+ widgets your agent can render

Table
Chart
Form
Map
Card
Image
Dialog
Alert
Toggle
+21 more

agent decides what to render. components are typed with JSON schemas. structured output → rich UI.

streaming

real-time token streaming with useAgentChat(). no manual SSE parsing. state managed for you.

tool approvals

HITL gates render as UI. user clicks approve or reject inline. no modal interruptions.

embed anywhere

react natively. iframe for anything else. proxy adapters for next.js, remix, sveltekit, hono.

Next.jsRemixSvelteKitHonoExpress
npm i @inference/ui
b
belt
use belt to scaffold a full agent + UI project from your terminal.
inference.sh ui vs Vercel AI SDKinference.sh ui vs CopilotKit

frequently asked questions

no. it's a full generative UI system. your agent can render tables, charts, forms, cards, not just text. components are typed with JSON schemas.

ready to ship?

start with the hosted platform. deploy your own when you're ready.

start for freeview on github

we use cookies

we use cookies to ensure you get the best experience on our website. for more information on how we use cookies, please see our cookie policy.

by clicking "accept", you agree to our use of cookies.
learn more.