Inference Logoinference shell

react components

drop in an agent.
ship it.

chat, generative UI, tool approvals. shadcn/ui compatible. connect to any inference shell agent.

browse componentsread the docs
pnpm dlx shadcn@latest registry add @inferencesh
agent

how can I help?

inference shell ui demo

blocks

everything your agent needs.

agent chat

full agent chat with state management, tool lifecycle, and generative UI. streaming, approvals, widgets — all wired to a runtime. 4 lines to ship.

explore →
agent

how can I help?

inference shell ui demo

generative widgets

30+ typed widgets your agent can render. forms, cards, charts, data displays. the agent returns JSON, the widget renderer handles the rest.

explore →

departure

SFO

san francisco
✈️

5h 45m

on time

arrival

JFK

new york

san francisco

partly cloudy

68°

⛅

H: 72° L: 58°

today's tasks
your order
item
brown sugar latte

large • oat milk • less ice

$6.50
item
taro milk tea

medium • regular sugar

$5.75
total

$13.32

tool invocation

pending, in-progress, completed, failed, awaiting approval. every tool state handled inline with collapsible details, approval UI, and widget results.

explore →
arguments:
{
  "query": "inference shell pricing"
}
result:
{"urls":["https://inference.sh/pricing"],"snippets":["pay per second, no minimums"]}
delete_file awaiting approval
arguments:
{
  "path": "/data/old-backup.tar.gz"
}
Q3 Revenue
generated bar chart with 3 data pointschart ready

chat primitives

container, messages, input, status indicators. composable building blocks for any chat UI. auto-resizing input, file upload, virtualized rendering for 1000+ messages.

explore →
agent

how can I help?

chat primitives demo

task output

streaming output, status indicators, tabbed views, auto-scrolling logs. display long-running agent task results with real-time updates.

explore →

markdown

high-performance markdown renderer with syntax-highlighted code blocks, tables, images, YouTube embeds, and zoomable images. optimized for token-by-token streaming.

explore →

getting started

build AI-powered apps with inference shell. the platform handles infrastructure, you write the logic.

typescript
const agent = new Agent({  tools: [searchWeb, analyzeData],})await agent.run("find recent papers on RLHF")

agents can use tools, render widgets, and stream responses in real-time.

featurestatus
streamingsupported
tool callssupported
widgets30+ types

why inference shell ui

not just chat bubbles.

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.

generative UI

agents render structured widgets — forms, cards, charts — not just text. typed with JSON schemas.

Next.js · Remix · SvelteKit · Hono · Express

b
belt
use belt to scaffold a full agent + UI project from your terminal.
inference shell ui vs Vercel AI SDKinference shell ui vs CopilotKit

faq

frequently asked questions

can't find what you're looking for? we're here to help.

contact us →

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.