docs(website): refresh llms.txt for post-publish reality

apps/website/content/docs/ag-ui/getting-started/installation.mdx

@@ -0,0 +1,97 @@
+# Installation
+
+## Prerequisites
+
+- Angular 20 or later
+- Node.js 22+
+- An AG-UI-compatible backend running locally or remotely (CrewAI, Mastra, Microsoft Agent Framework, AG2, Pydantic AI, AWS Strands, CopilotKit runtime, or your own subclass of `AbstractAgent`)
+
+## Install packages
+
+```bash
+npm install @ngaf/chat @ngaf/ag-ui
+```
+
+`@ngaf/chat` provides the chat UI primitives. `@ngaf/ag-ui` provides the adapter that wires an AG-UI backend into the `Agent` contract those primitives consume.
+
+## Configure the provider
+
+In your app config:
+
+```ts
+import { ApplicationConfig } from '@angular/core';
+import { provideAgUiAgent } from '@ngaf/ag-ui';
+
+export const appConfig: ApplicationConfig = {
+  providers: [
+    provideAgUiAgent({
+      url: 'http://localhost:3000/agent',  // your AG-UI backend
+    }),
+  ],
+};
+```
+
+`provideAgUiAgent` accepts:
+
+| Option | Type | Description |
+|---|---|---|
+| `url` | `string` | **Required.** AG-UI backend HTTP/SSE endpoint. |
+| `agentId` | `string` | Optional. Identifies a specific agent on the backend. |
+| `threadId` | `string` | Optional. Resume an existing conversation thread. |
+| `headers` | `Record<string, string>` | Optional. Custom request headers (auth, tracing). |
+
+## Use in a component
+
+```ts
+import { Component, inject } from '@angular/core';
+import { ChatComponent } from '@ngaf/chat';
+import { AG_UI_AGENT } from '@ngaf/ag-ui';
+
+@Component({
+  selector: 'app-streaming',
+  standalone: true,
+  imports: [ChatComponent],
+  template: `<chat [agent]="agent" />`,
+})
+export class StreamingComponent {
+  protected readonly agent = inject(AG_UI_AGENT);
+}
+```
+
+## No backend yet?
+
+Use the `FakeAgent` for offline demos:
+
+```ts
+import { provideFakeAgUiAgent } from '@ngaf/ag-ui';
+
+export const appConfig: ApplicationConfig = {
+  providers: [
+    provideFakeAgUiAgent({
+      tokens: ['Hello', ' from', ' a', ' fake', ' agent.'],
+      delayMs: 60,
+    }),
+  ],
+};
+```
+
+`FakeAgent` extends `AbstractAgent` and emits a canned `RUN_STARTED → TEXT_MESSAGE_START → TEXT_MESSAGE_CONTENT × N → TEXT_MESSAGE_END → RUN_FINISHED` sequence. Drop-in replacement for `provideAgUiAgent({ url })` while you're prototyping.
+
+## Custom transport
+
+If you have a backend that speaks AG-UI but not over HTTP, subclass `AbstractAgent` directly and feed it to `toAgent`:
+
+```ts
+import { AbstractAgent, type RunAgentInput, type BaseEvent } from '@ag-ui/client';
+import { Observable } from 'rxjs';
+import { toAgent } from '@ngaf/ag-ui';
+
+class MyCustomAgent extends AbstractAgent {
+  protected run(input: RunAgentInput): Observable<BaseEvent> {
+    // Your custom transport (WebSocket, in-process worker, etc.)
+    // emits BaseEvent events.
+  }
+}
+
+const agent = toAgent(new MyCustomAgent());
+```

apps/website/content/docs/ag-ui/getting-started/introduction.mdx

@@ -0,0 +1,52 @@
+# Introduction
+
+`@ngaf/ag-ui` is the runtime adapter that wraps an [AG-UI](https://github.com/ag-ui-protocol/ag-ui) `AbstractAgent` into the runtime-neutral `Agent` contract from `@ngaf/chat`. The chat UI primitives consume the Agent contract; the AG-UI adapter translates between the contract and the AG-UI event protocol.
+
+<Callout type="info" title="What is AG-UI?">
+AG-UI is the open agent-to-UI protocol from the CopilotKit ecosystem. It standardizes how agent runtimes stream events (messages, tool calls, state updates) to a frontend. Used by **CrewAI**, **Mastra**, **Microsoft Agent Framework**, **AG2**, **Pydantic AI**, **AWS Strands**, and the **CopilotKit runtime**. One adapter unlocks all of them.
+</Callout>
+
+## How it fits
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│  @ngaf/chat  (UI primitives — runtime-neutral)              │
+│  <chat>, <chat-messages>, <chat-input>, <chat-debug>, …     │
+└─────────────────────────┬───────────────────────────────────┘
+                          │ Agent contract (signals + events$)
+                          │
+              ┌───────────┴───────────┐
+              ▼                       ▼
+   @ngaf/langgraph              @ngaf/ag-ui
+   (toAgent: AgentRef→Agent)    (toAgent: AbstractAgent→Agent)
+              │                       │
+              ▼                       ▼
+   LangGraph Platform           Any AG-UI backend
+                                (CrewAI, Mastra, MS AF,
+                                 CopilotKit runtime, …)
+```
+
+## What you get
+
+- **`toAgent(source: AbstractAgent): Agent`** — wraps any `AbstractAgent` subclass (custom transports, mocks).
+- **`provideAgUiAgent({ url })`** — DI convenience that instantiates `HttpAgent` under the hood for the common SSE/HTTP case.
+- **`FakeAgent`** — in-process `AbstractAgent` subclass that emits canned streaming events for offline demos and tests.
+
+## What's covered
+
+Scope of the first release:
+- `messages` (streaming token deltas via `TEXT_MESSAGE_*` events)
+- `status` / `isLoading` / `error` (lifecycle via `RUN_STARTED/FINISHED/ERROR`)
+- `toolCalls` (streaming tool calls via `TOOL_CALL_*` events)
+- `state` (snapshots and JSON-Patch deltas)
+- `events$` (custom events; discriminates `state_update`)
+
+Out of scope for now (use `@ngaf/langgraph` if you need these):
+- Interrupts
+- Subagents
+- History / time-travel
+
+## Next steps
+
+- [Quick Start](/docs/ag-ui/getting-started/quickstart) — bind `<chat>` to an AG-UI backend in 5 minutes.
+- [Installation](/docs/ag-ui/getting-started/installation) — npm install + provider setup.

apps/website/content/docs/ag-ui/getting-started/quickstart.mdx

@@ -0,0 +1,71 @@
+# Quick Start
+
+Bind `<chat>` from `@ngaf/chat` to an AG-UI backend in 5 minutes.
+
+<Callout type="info" title="Prerequisites">
+Angular 20+ project with Node.js 22+. If you need setup help, see the [Installation](/docs/ag-ui/getting-started/installation) guide.
+</Callout>
+
+<Steps>
+<Step title="Install the packages">
+
+```bash
+npm install @ngaf/chat @ngaf/ag-ui
+```
+
+</Step>
+<Step title="Configure the provider">
+
+Add `provideAgUiAgent()` to your application config with your AG-UI backend URL.
+
+```ts
+// app.config.ts
+import { ApplicationConfig } from '@angular/core';
+import { provideAgUiAgent } from '@ngaf/ag-ui';
+
+export const appConfig: ApplicationConfig = {
+  providers: [
+    provideAgUiAgent({ url: 'http://localhost:3000/agent' }),
+  ],
+};
+```
+
+For offline development without a backend, swap to `provideFakeAgUiAgent({})` — it serves canned streaming responses for UI work.
+
+</Step>
+<Step title="Use in a component">
+
+```ts
+import { Component, inject } from '@angular/core';
+import { ChatComponent } from '@ngaf/chat';
+import { AG_UI_AGENT } from '@ngaf/ag-ui';
+
+@Component({
+  selector: 'app-streaming',
+  standalone: true,
+  imports: [ChatComponent],
+  template: `<chat [agent]="agent" />`,
+})
+export class StreamingComponent {
+  protected readonly agent = inject(AG_UI_AGENT);
+}
+```
+
+That's it. The `<chat>` composition handles streaming messages, tool calls, errors, and submit — all bound to the AG-UI backend through the `Agent` contract.
+
+</Step>
+</Steps>
+
+## What to read next
+
+- The [`@ngaf/chat` Components](/docs/chat/components/chat) reference covers the primitives the `<chat>` composition uses internally — handy if you want to compose your own layout.
+- Looking for LangGraph instead of AG-UI? See [`@ngaf/langgraph`](/docs/agent/getting-started/quickstart).
+
+## Switching backends without changing UI
+
+The point of the runtime-neutral `Agent` contract is that swapping backends is a one-line change in `app.config.ts`. The component code stays the same:
+
+```diff
+- providers: [provideAgent({ apiUrl: '...' })],   // LangGraph
++ providers: [provideAgUiAgent({ url: '...' })],  // AG-UI
+```

apps/website/e2e/website.spec.ts

@@ -14,14 +14,12 @@ test('landing page renders architecture section', async ({ page }) => {
 
 test('landing page renders libraries section', async ({ page }) => {
   await page.goto('/');
-  await expect(page.getByText('Three libraries. One architecture.').first()).toBeVisible();
+  await expect(page.getByText('Four libraries. One architecture.').first()).toBeVisible();
 });
 
-test('pricing page shows 4 plan cards', async ({ page }) => {
+test('pricing page shows plan cards', async ({ page }) => {
   await page.goto('/pricing');
-  await expect(page.getByText('Community').first()).toBeVisible();
-  await expect(page.getByText('Developer Seat').first()).toBeVisible();
-  await expect(page.getByText('App Deployment').first()).toBeVisible();
+  await expect(page.getByText('Open Source').first()).toBeVisible();
   await expect(page.getByText('Enterprise').first()).toBeVisible();
 });
 
@@ -42,6 +40,7 @@ test('docs landing page shows library cards', async ({ page }) => {
   await expect(page.getByText('Agent').first()).toBeVisible();
   await expect(page.getByText('Render').first()).toBeVisible();
   await expect(page.getByText('Chat').first()).toBeVisible();
+  await expect(page.getByText('AG-UI').first()).toBeVisible();
 });
 
 test('api reference renders in docs', async ({ page }) => {

apps/website/src/app/api/email-preview/route.ts

@@ -22,9 +22,9 @@ const TEMPLATES: Record<string, () => { subject: string; html: string }> = {
   'lead-notification': () => ({
     subject: 'New lead: Brian at Cacheplane',
     html: leadNotificationHtml({
-      name: 'Brian Love',
-      email: 'brian@cacheplane.io',
-      company: 'Cacheplane',
+      name: 'Sample Lead',
+      email: 'demo@example.com',
+      company: 'Example Corp',
       message: 'Interested in the pilot program for our Angular + LangGraph project.',
       ts: new Date().toISOString(),
     }),

apps/website/src/app/llms-full.txt/route.ts

@@ -38,12 +38,6 @@ export async function GET() {
       'Do not mock agent() in tests — use MockAgentTransport.',
       'RxJS is an internal implementation detail — do not import rxjs in consumer code.',
     ].join('\n'),
-    [
-      '## MCP server',
-      '',
-      'npx @ngaf/langgraph-mcp',
-      'Add to Claude Code settings.json, Cursor .cursor/mcp.json, or any MCP-compatible agent.',
-    ].join('\n'),
   ];
 
   return new NextResponse(sections.join('\n\n---\n\n'), {

apps/website/src/app/llms.txt/route.ts

@@ -2,33 +2,51 @@ import { NextResponse } from 'next/server';
 
 // Build compact LLMs summary at request time so version is always current
 function buildLlmsTxt(): string {
-  // Inline version — updated by publish workflow
-  const version = '0.1.0';
+  // Inline version — bump on each release
+  const version = '0.0.1';
   return [
     `# Angular Agent Framework v${version}`,
     '',
-    "Angular Agent Framework — the enterprise streaming library for LangChain/LangGraph. Provides agent() — full parity with React's useStream() hook, built on Angular Signals.",
+    "Angular Agent Framework is a runtime-neutral chat UI SDK for Angular. The @ngaf/chat library provides streaming chat primitives bound to a runtime-neutral 'Agent' contract; runtime adapters (@ngaf/langgraph, @ngaf/ag-ui) translate between the contract and the actual backend.",
+    '',
+    '## Packages',
+    '- @ngaf/chat — chat UI primitives (messages, input, tool calls, interrupt, debug, etc.) consuming the Agent contract',
+    '- @ngaf/langgraph — adapter for LangGraph / LangGraph Platform',
+    '- @ngaf/ag-ui — adapter for any AG-UI-compatible backend (CrewAI, Mastra, Microsoft AF, AG2, Pydantic AI, AWS Strands, CopilotKit runtime)',
+    '- @ngaf/render — generative UI runtime (Vercel json-render + Google A2UI)',
+    '- @ngaf/a2ui — A2UI catalog components',
+    '- @ngaf/partial-json — streaming JSON parser',
+    '- @ngaf/licensing — license verification client',
     '',
     '## Install',
-    'npm install @ngaf/langgraph',
-    '',
-    '## Key API',
-    '- agent(options): AgentRef — call in Angular injection context (constructor or field initializer)',
-    '- provideAgent(config): Provider — register in app.config.ts for global defaults',
-    "- AgentRef.messages(): Signal<BaseMessage[]> — updates token by token",
-    '- AgentRef.submit(values): Promise<void> — send a message / trigger a run',
-    "- AgentRef.status(): Signal<'idle'|'loading'|'resolved'|'error'>",
-    '- AgentRef.threadId signal + onThreadId callback — thread persistence across refreshes',
-    '- MockAgentTransport — deterministic unit testing without a real server',
-    '',
-    '## Minimal example',
-    "import { agent } from '@ngaf/langgraph';",
-    "const chat = agent({ assistantId: 'chat_agent', apiUrl: 'http://localhost:2024' });",
-    '// Template: @for (msg of chat.messages(); track $index) { <p>{{ msg.content }}</p> }',
-    "// Submit: chat.submit({ messages: [{ role: 'human', content: input }] })",
-    '',
-    '## MCP server',
-    'npx @ngaf/langgraph-mcp',
+    '# LangGraph backend:',
+    'npm install @ngaf/chat @ngaf/langgraph',
+    '# AG-UI backend:',
+    'npm install @ngaf/chat @ngaf/ag-ui',
+    '',
+    '## Key API (chat library)',
+    '- Agent — runtime-neutral contract with messages/status/isLoading/error/toolCalls/state signals + events$ observable + submit/stop methods',
+    '- ChatComponent, ChatMessagesComponent, ChatInputComponent — composable Angular components consuming Agent',
+    '- mockAgent — testing utility with a writable signal-backed Agent',
+    '- runAgentConformance / runAgentWithHistoryConformance — conformance suites for adapter authors',
+    '',
+    '## Minimal LangGraph example',
+    "import { agent, toAgent } from '@ngaf/langgraph';",
+    "import { ChatComponent } from '@ngaf/chat';",
+    '// In a component:',
+    "stream = agent({ apiUrl: 'http://localhost:2024', assistantId: 'chat_agent' });",
+    'chatAgent = toAgent(this.stream);',
+    '// Template: <chat [agent]="chatAgent" />',
+    '',
+    '## Minimal AG-UI example',
+    "import { provideAgUiAgent, AG_UI_AGENT } from '@ngaf/ag-ui';",
+    "import { ChatComponent } from '@ngaf/chat';",
+    "// app.config.ts: providers: [provideAgUiAgent({ url: 'https://your.endpoint' })]",
+    "// Component: agent = inject(AG_UI_AGENT);",
+    '// Template: <chat [agent]="agent" />',
+    '',
+    '## License',
+    'MIT — free for any use, commercial or noncommercial.',
     '',
     '## Full reference',
     'https://cacheplane.ai/llms-full.txt',