Public runtime traffic
Website widgets, headless public sessions, visitor identity, page context, lead capture, and engagement events.
Developer Runtime
Embed governed AI agents without rebuilding the runtime layer.
AgentShelf gives developers SDKs, widget embeds, headless runtime APIs, and integration patterns for bringing governed agents into websites, products, workflows, and external applications.
- Widget embeds
- Headless APIs
- SDK access
- Public runtime sessions
- Usage telemetry
Runtime surfaces
One agent runtime, multiple ways to deploy.
Use the surface that matches the experience you are building while keeping runtime behavior connected to the same AgentShelf control plane.
Standard widget embed
Add a hosted website agent with the existing widget script when you want the AgentShelf-provided shell, launcher, and visitor experience.
- Best for website AI front desks, visitor questions, lead capture, and support handoff.
Headless widget API
Use the browser SDK and public headless runtime when you want to design your own chat UI while relying on AgentShelf for sessions and streaming.
- Best for custom website chat, branded support surfaces, and embedded product workflows.
SDK-based product embedding
Build custom agent interfaces with SDK access to sessions, streamed responses, visitor identity, page traces, and lead capture helpers.
- Best for frontend teams building bespoke agent experiences inside web applications.
API-backed integrations
Connect agent experiences to external systems and workflows through approved runtime patterns instead of wiring every application directly to model providers.
- Best for portals, partner apps, workflow tools, and system-backed agent experiences.
Runtime boundaries
Separate public experiences from authenticated platform controls.
Public-facing agent sessions can use guarded configuration, origin checks, runtime access controls, telemetry, and usage tracking without exposing administrative controls.
Governed runtime
Model routing, usage telemetry, policies, runtime events, traces, and attribution connect runtime activity to the platform.
Authenticated controls
Agent configuration, admin controls, billing, workspaces, private context management, and governance settings.
Boundary rule
Website agent traffic stays separate from authenticated platform administration while remaining governed and observable.
SDK access
Build custom interfaces on top of the AgentShelf widget runtime.
The browser-first AgentShelf widget SDK gives frontend developers access to the headless widget runtime without forcing the standard iframe, modal, launcher, or default UI shell.
- Create or restore visitor sessions.
- Stream assistant responses into your own UI.
- Render lead forms selected by the runtime.
- Collect browser attribution and page trace events.
- Use storage adapters for custom session persistence.
import {
collectBrowserClientContext,
collectStream,
createWidgetClient,
} from '@agentshelf/widget-sdk';
const client = createWidgetClient({
siteId: 'widget_site_id',
apiBase: 'https://api.agentshelf.ai',
});
await client.ensureSession({
visitorFingerprint: 'anon-visitor-123',
clientContext: collectBrowserClientContext({
sessionTraceConsent: 'granted',
}),
});
const reply = await collectStream(
await client.streamMessage({
content: 'What can this agent help me with?',
}),
);Integration patterns
Bring agents into the surfaces your users already use.
Developers can create custom frontends, stream responses, pass approved external context, handle client-side continuations, and capture structured lead or workflow data through supported runtime APIs.
Custom chat UI
Render your own transcript, inputs, quick replies, streaming states, and errors while AgentShelf manages runtime sessions.
In-product assistant
Embed an AgentShelf-powered agent inside a product workflow, portal, or customer experience.
Lead capture flow
Use runtime form signals and lead capture helpers to collect contact details, route follow-up, and preserve conversation context.
Proactive engagement
Evaluate configured engagement gates and show contextual prompts from your own UI.
External context
Pass approved external context from the host app while keeping public sessions separate from administrative platform access.
Client-side tools
Handle tool calls in the host application and continue the same assistant turn with validated tool results.
Trust layer
Designed for governed public and embedded agent experiences.
Developer integrations keep authenticated controls inside the platform, keep public runtime sessions governed, and keep runtime activity observable.
Origin and access checks
Restrict public runtime access to approved origins, expected host applications, and configured access rules.
Guarded responses
Keep public-facing agent behavior aligned to approved configuration and safe response patterns.
Runtime telemetry
Maintain runtime traces, usage records, and event visibility for debugging and governance review.
Public runtime boundary
Public-facing agents run through controlled runtime sessions with telemetry, routing, and governance while private workspace access stays behind authenticated platform controls.
Design the agent experience. Use AgentShelf for the runtime.
Bring AgentShelf-powered agents into your website, product, portal, or workflow without rebuilding session management, streaming, engagement, lead capture, telemetry, model routing, and governance infrastructure from scratch.