Ggui

🚧 Active development — iterating on v0.1.0 release candidates. APIs are converging; pin exact versions (see badges below) and watch Releases for the next RC and the v0.1.0 final.

Agents describe what they need in natural language; ggui generates ephemeral, interactive interfaces over MCP. No frontend code, no React templates, no custom components — agents talk, users see UI.

This repo is the open protocol + reference runtime. Self-host with ggui serve; pair against any MCP-aware agent runtime (Claude Desktop, Claude Code, claude.ai, Cursor, ChatGPT desktop, Goose, your own). Zero account required, zero managed infrastructure required, zero cloud dependency.

Quick start — pick your path

1. Composed golden path — platform-composed (guuey-sdk)

One flow from a guuey.json to a rendered, interactive todo UI — every piece a published SDK. guuey's dev tooling runs the agent (@guuey/cli + @guuey/worker), the ggui runtime is the dev router's injected MCP default, and the web client talks to the router with @guuey/agent-client. This path is platform-composed: it drives the ggui protocol through guuey's published SDKs. The protocol itself has no guuey dependency — paths 2–4 run without it, and the framework-native samples (path 2) stay first-class.

Prerequisites: Node.js 22+, pnpm, and an ANTHROPIC_API_KEY (one key drives both the agent and ggui's UI generation).

git clone https://github.com/ggui-ai/ggui && cd ggui
pnpm install                        # workspace deps — `guuey dev` spawns the colocated
                                    # todo MCP from samples/mcp-servers/todo
export ANTHROPIC_API_KEY=sk-ant-…   # in every terminal below

# terminal 1 — the ggui runtime MCP (guuey's dev router injects ggui → this port)
npx -y @ggui-ai/cli serve --mcp-only     # http://127.0.0.1:6781/mcp

# terminal 2 — the agent half: guuey.json + a Claude agent worker
cd samples/agents/with-guuey
npm install
npm run dev                              # guuey dev --serve → http://localhost:6790

# terminal 3 — the web half: chat + rendered ggui cards
cd samples/apps/with-guuey-web
npm install
npm run dev                              # http://127.0.0.1:6890

Browser-based clients. Pages served from localhost reach the MCP endpoint out of the box. A page on any other origin — a deployed site, an Electron renderer — must be allowlisted:

ggui serve --browser-origin https://app.example.com

(repeatable; or GGUI_BROWSER_ORIGINS=a,b). The allowlist drives both MCP-wire Origin validation and the CORS response headers, so one flag covers both. It is not authentication — /mcp still requires a bearer. Non-browser clients (Claude Desktop, agents, curl) are unaffected: they connect server-to-server and ignore CORS entirely.

Open http://127.0.0.1:6890 and ask for your todos: the agent calls the todo MCP, renders an interactive todo UI through ggui, and your clicks flow back to the agent. Per-sample detail (ports, env vars, known limitations): samples/agents/with-guuey · samples/apps/with-guuey-web. Prefer a scaffolded start? npx @guuey/create-agentic-app scaffolds a guuey agentic app of the same shape (agent + MCP + ggui + web) in one command.

Dev-server trust: guuey dev runs your agent unjailed with your environment — standard dev-server trust; run it in a container if that posture doesn't fit.

2. Bring your own framework — build from the framework-native samples

The framework-native path to ship an agent end-to-end — no guuey dependency. The canonical samples are complete, runnable pieces of an agentic app — an agent backend per SDK, a stock ggui server config, a reference MCP server, and a web client. Compose them into a workspace and run the whole thing:

git clone https://github.com/ggui-ai/ggui && cd ggui

# your app = four samples composed into one pnpm workspace:
#   samples/agents/<sdk>/        → servers/agent/     (claude-agent-sdk | openai-agents-sdk | google-adk)
#   samples/gguis/default/       → servers/ggui/      (stock `ggui serve` config)
#   samples/mcp-servers/todo/    → servers/mcps/todo/ (reference domain MCP)
#   samples/apps/ggui-basic-web/ → apps/web/          (Vite + React chat client)
# (e2e/samples-render/app-shell/ is the reference root wrapper — package.json
#  with the dev scripts + pnpm-workspace.yaml + the `pnpm dev` orchestrator.)

pnpm install
# put your LLM API key in .env.local, then:
pnpm dev                     # starts ggui + MCP servers + agent + web, then opens the app

pnpm dev brings all four services up together and opens http://localhost:6890 once it's ready — so you never have to guess which port to visit (server logs are hidden by default; pnpm dev --verbose streams them). The full loop runs locally: you type → the agent calls domain tools and renders a React UI → you click in that UI → the agent reacts. Each sample carries its own README with standalone run instructions.

Building a hosted agent instead? See guuey.com — the managed platform for running agents (not a drop-in replacement for the samples path).

3. Self-host the OSS MCP server + test from claude.ai

For testing the ggui protocol against a real chat host. Localhost won't work from claude.ai — you need a public HTTPS URL, which cloudflared provides for free.

# terminal 1 — boot the OSS MCP server
npm install -g @ggui-ai/cli
ANTHROPIC_API_KEY=sk-… ggui serve --mcp-only       # http://127.0.0.1:6781/mcp

# terminal 2 — expose it to the public internet (no Cloudflare account needed)
cloudflared tunnel --url http://127.0.0.1:6781     # prints https://<random>.trycloudflare.com

Browser-based clients. Pages served from localhost reach the MCP endpoint out of the box. A page on any other origin — a deployed site, an Electron renderer — must be allowlisted:

ggui serve --browser-origin https://app.example.com

(repeatable; or GGUI_BROWSER_ORIGINS=a,b). The allowlist drives both MCP-wire Origin validation and the CORS response headers, so one flag covers both. It is not authentication — /mcp still requires a bearer. Non-browser clients (Claude Desktop, agents, curl) are unaffected: they connect server-to-server and ignore CORS entirely.

Then in claude.ai → Settings → Connectors → Add custom connector, paste https://<random>.trycloudflare.com/mcp. Ask Claude to render any UI; the server generates the component and serves it back as a rich rendered card inside the chat.

Install cloudflared via your package manager: brew install cloudflared (macOS), apt install cloudflared (Debian), or grab a binary from cloudflare.com/products/tunnel.

4. Use the hosted ggui.ai cloud — mcp.ggui.ai (deploying soon)

For production, sign up at ggui.ai → create an app → get a managed MCP URL (form: https://mcp.ggui.ai/<app-id>/mcp). Paste into your chat host's connector settings — no self-hosting, no tunnel, no key management.

🚧 The hosted endpoint is deploying — coming in a follow-up rc. Use paths 1–3 in the meantime.

The ggui CLI

@ggui-ai/cli ships the ggui binary — the single entrypoint for every OSS workflow. Five verbs cover the full lifecycle:

Plus auth verbs for the hosted path: ggui login / ggui logout / ggui whoami / ggui keys. Run ggui --help for the top-level overview, or ggui <verb> --help for per-command flags.

Full CLI reference: @ggui-ai/cli README.

Runnable examples

samples/ holds end-to-end examples you can clone:

• samples/gguis/ — ready-to-run project configs (default, leaflet-demo, mapbox-demo, canvas-demo) showing how a ggui.json is shaped.
• samples/agents/ — framework-native reference agents per SDK (Claude Agent SDK, OpenAI Agents SDK, Google ADK) talking to ggui as an MCP server.
• samples/agents/with-guuey + samples/apps/with-guuey-web — the platform-composed (guuey-sdk) golden-path pair: a guuey.json Claude agent served by @guuey/cli's dev router, and a web client on @guuey/agent-client rendering ggui cards (see path 1 above).
• samples/gadgets/ — example component / hook gadgets for the marketplace.
• samples/mcp-servers/ — minimal domain MCP servers (e.g. a todo server) you can pair against.

Honest scope today

• ✅ Local server, viewer, cookie-authenticated WebSocket subscribe → ack all work end-to-end.
• ✅ ggui_render mints shortCodes and lands on the same-origin viewer.
• ✅ Component-code generation is wired on the OSS path via createUiGenerator() from @ggui-ai/ui-gen (the same harness the hosted runtime uses). When no BYOK credentials resolve (no ANTHROPIC_API_KEY / OPENAI_API_KEY / etc.), ggui_render returns an isError: true tool result whose structuredContent.error.code is NO_CREDENTIALS; supply a key to get full generation locally.
• 🔒 Default auth is dev-mode (any non-empty bearer → builder). Swap in a real AuthAdapter via createGguiServer({ auth }) before exposing beyond 127.0.0.1.

How it works

┌─────────┐     MCP Tools      ┌──────────┐     WebSocket     ┌──────────┐
│  Your   │ ────────────────→  │  ggui    │ ────────────────→ │  User's  │
│  Agent  │   ggui_render      │  server  │   real-time UI    │  browser │
│         │   ggui_update      │          │   updates         │          │
│         │ ←────────────────  │          │ ←──────────────── │          │
│         │   user events      │          │   clicks, forms   │          │
└─────────┘                    └──────────┘                   └──────────┘

Your agent uses MCP tools to push UIs and receive user events. The protocol is defined by @ggui-ai/protocol; the reference server lives in @ggui-ai/mcp-server; embedding primitives ship in @ggui-ai/react.

MCP tools (primary surface)

Plus a blueprint family (ggui_search_blueprints, ggui_render_blueprint, ggui_list_featured_blueprints, …) for catalogue lookups. Full reference: MCP Protocol Reference.

Zero agent code (MCP config only)

If your agent runtime supports MCP natively, skip the SDK entirely. Add ggui serve as an MCP server:

{
  "mcpServers": {
    "ggui": {
      "url": "http://127.0.0.1:6781/mcp",
      "headers": { "Authorization": "Bearer dev" }
    }
  }
}

The runtime's native tool-calling loop discovers ggui_render, ggui_update, ggui_consume, and the blueprint catalogue tools directly. Working examples per framework: Claude, OpenAI, Gemini, generic MCP.

Embedding UIs

<McpAppIframe> is the canonical consumer primitive. It takes an MCP Apps resource and mounts the ggui render inside a same-origin iframe. The iframe owns the WebSocket lifecycle, renderer bundle, and render mount — host code does not touch Render / WebSocket / renderer internals.

import { McpAppIframe, type ProtocolError } from "@ggui-ai/react";
import { useEffect, useState } from "react";

function App({ renderId }: { renderId: string }) {
  const [resource, setResource] = useState<{ uri: string; mimeType: string; text: string } | null>(
    null
  );

  useEffect(() => {
    // Fetch the render-resource envelope from your MCP host. On the
    // OSS path the renderer route at /r/<shortCode> embeds the
    // bootstrap inline, so a resource with just `{ uri }` is enough.
    fetchRenderResource(renderId).then((r) => setResource(r.contents[0]));
  }, [renderId]);

  if (!resource) return <p>Loading…</p>;

  return <McpAppIframe resource={resource} onError={(err: ProtocolError) => console.error(err)} />;
}

Implementer references for the full protocol: Architecture overview, MCP Apps support, WebSocket protocol.

For non-React frameworks, embed the viewer directly:

<iframe src="http://127.0.0.1:6781/r/{shortCode}" width="100%" height="600"></iframe>

Packages

Consumer-facing surface — what you npm install:

Package	Purpose	npm
@ggui-ai/cli	The ggui binary — serve, dev, blueprint, gadget, theme
@ggui-ai/mcp-server	Reference OSS server (programmatic embedding)
@ggui-ai/react	React embedding — chat shells + MCP-Apps chat hook
@ggui-ai/react-native	React Native embedding — <McpAppIframe> MCP-Apps host + shells
@ggui-ai/protocol	Wire types (events, sessions, WebSocket, MCP envelopes)
@ggui-ai/gadgets	Author wrappers for 3rd-party libs (Leaflet, Mapbox, …)

Plus 27 supporting packages under packages/ spanning the runtime (@ggui-ai/mcp-server-core, @ggui-ai/mcp-server-handlers, @ggui-ai/ui-gen, @ggui-ai/negotiator), authoring (@ggui-ai/project-config, @ggui-ai/ui-registry), registry (@ggui-ai/registry-core, @ggui-ai/registry-server), and dev tooling (@ggui-ai/dev-stack, @ggui-ai/agent-runtime, @ggui-ai/console). See each subdirectory for details.

Hosted providers

Self-hosting is the primary path. For managed infrastructure (no server to run, no LLM key to wire, hosted dashboards), the first-party hosted endpoint at mcp.ggui.ai is deploying — see path 4 above. Guuey hosts an upgraded experience built on top of the protocol. The protocol is identical on all paths — you can move between self-hosted and hosted without rewriting anything against this SDK.

Contributing

See CONTRIBUTING.md. Issues + PRs welcome.

License

Apache 2.0 — see LICENSE.