Connect any agent
to any user.
The Enterprise Agentic Frontend Stack. Build rich agentic applications that learn from every interaction. Self-hostable and built to scale with your org.
Trusted by the majority of the Fortune 500s and Global 50.
The company behind AG-UI, the Agent-User Interaction protocol.
First party integrations from the leading agent stacks.
Use cases & templates
Ready-made templates for many top use cases. Quick to start, fully customizable.
Company knowledge base
Ask anything your company knows
Which enterprise customers mentioned pricing this quarter? Summarize by segment.
thought · 3 steps
Scanning CRM notessearch_crm()
Querying revenue by segmentquery_warehouse()
Reading pricing threadsread_threads()
thought · 3 steps
12 accounts raised pricing — 9 mid-market, 3 enterprise.
Pricing mentions · by segment
mid-market9
enterprise3
chat threadsdata warehousetickets & crm
Who should we follow up with first? Draft the outreach.
thought · 1 step
Ranking accounts by signalrank_accounts()
thought · 1 step
These three — drafts ready to review.
Helios Manufacturing
Corva Logistics
Bluepine Health
A deep agent over everything your company knows — docs, conversations, dashboards, tickets — that anyone in the org can ask, analyze with, and draft from. It learns each person's context, and gets smarter for the whole company with every question.
Why CopilotKit.
One: your CopilotKit Agent doesn’t just talk about your product; it deeply interacts with it. Ask a question and get back a real chart or a real form, drawn in your own design, not a wall of text. It works in the app right beside your users, on the same live screen. Whatever it makes, stays made.
Two: it gets better the longer you own it, because it learns from how your users actually work. Most software starts depreciating the day you buy it. This one appreciates.
Three: every action is on the record, fully auditable, and your data stays yours. Fully self-hosted, or Cloud.
Four: choosing CopilotKit isn’t a bet on a vendor. Practically every agent framework and harness on the market already speaks our protocol, AG-UI. It’s the layer the ecosystem already runs on.
Loved by developers.
Build rich agentic applications for any surface.
// pre-built chat, styled with your CSS
<CopilotChat agentId="support"
className="acme-chat" />
// or swap any subcomponent via slots
<CopilotChat
messageView={AcmeMessages}
input={AcmeInput} />
// or fully headless
const { agent } = useAgent();
{ agent.messages.map((m) => (
<AcmeBubble key={m.id}> {m.content} </AcmeBubble>
)) }// Controlled generative UI
useComponent({
name: "showRefundStatus",
description: "Show a refund status card.",
parameters: z.object({
orderId: z.string(),
amount: z.number(),
method: z.string(),
}),
// your component, your design system
render: RefundStatusCard,
});
const RefundStatusCard = ({ orderId, amount }) => (
<Card>…</Card> // breakdown pie, your design system
);useHumanInTheLoop({
name: "chooseRefundMethod",
parameters: z.object({ orderId: z.string() }),
render: ({ respond }) => (
<RefundMethodChoice
options={["original card", "store credit"]}
allowCustomAnswer
onChoose={(answer) => respond?.(answer)}
/>
),
});useFrontendTool({
name: "selectOrder",
description: "Open an order in the dashboard.",
parameters: z.object({ orderId: z.string() }),
handler: async ({ orderId }) => {
openOrder(orderId); // your app code
return { status: "selected", orderId };
},
});const handler = createCopilotRuntimeHandler({
runtime,
hooks: {
onRequest: ({ request }) => {
const jwt = request.headers.get("authorization");
const user = verifyJwt(jwt);
if (!user)
throw new Response(null, { status: 401 });
// agent runs are tied to this user
},
},
});const { agent } = useAgent({ agentId: "support" });
// read the agent's shared state
agent.state.focus // "refunds"
// write it, the agent sees the change
agent.setState({ ...agent.state, focus: "returns" });Recent coverage and talks
From a Series A in TechCrunch to a hands-on course on DeepLearning.AI, CopilotKit is shaping the next wave of AI agent interfaces.

CopilotKit raises $27M to help devs deploy app-native AI agents
TechCrunch covers our Series A — scaling the open-source AG-UI protocol and helping developers embed AI agents directly inside their applications.
Read the article
Build Interactive Agents with Generative UI
CEO Atai Barkai teaches a hands-on short course on building fullstack agents that render rich, interactive UI on demand with CopilotKit and AG-UI.
Take the course
Generative UI for any agent, anywhere
Atai joins Google Cloud Tech to walk through A2UI, AG-UI, MCP Apps, and the protocols making in-app generative UI work across any agent.
Watch the talkAutomatic Learning
Your agents automatically get smarter, faster, and cheaper.
User interactions over time
How automatic learning works
Every interaction is captured.
In-chat & in-app.
What users do in your app: clicks, edits, and navigation outside the chat.
The back-and-forth with the agent, plus feedback signals: approvals, edits, retries.
Define learning containers for users, groups of users, or entire organizations.
Your agent automatically improves with every interaction.
Enterprise Ready. Future-proof your organization.
Self-host both the open-source SDK and the enterprise runtime. Nothing leaves your infrastructure. Or use our managed Cloud for added convenience.
AG-UI works with the stacks your teams use today, and whatever they adopt next.
No new data store to trust. Everything persists in the database you already run.
Use observed outcomes and human feedback to improve prompts, routing, workflows, and UI behavior while you own the learning loop.
Product analytics for agentic products.
Complete visibility into agent behavior, user interactions, and system performance. Integrate with your existing observability stack or use our built-in dashboard.
Real-Time Dashboard
Monitor agent performance, user engagement, and system health with live metrics and alerts.
Analytics & Trends
Track conversation patterns, user satisfaction, and agent effectiveness over time.
Data Lakehouse
SQL-queryable interaction data for deep analysis, compliance auditing, and training data extraction.
OTLP Observability
Bring your own observability stack with OTLP export to DataDog, NewRelic, or your preferred tools.
Built with teams shipping agentic products.
“The CopilotKit SDK has accelerated our development processes and enabled us to help our users accomplish their tasks more quickly and with more confidence.”
Mark Peterson, VP of Software Engineering
Docusign
“The AG-UI architecture lets us cleanly decouple our agent framework from the frontend, so we can evolve each independently. The pre-built component library saved us from rolling our own.”
Bryan Godwin, CTO
Evergreen Wealth
Start building
Enhance your applications
with powerful AI capabilities



