Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/discoposse/GUIness/llms.txt

Use this file to discover all available pages before exploring further.

GUIness is a single-file HTML application that runs entirely in your browser. It gives you a visual canvas for composing AI skill pipelines from reusable node primitives, connecting them together, and executing them against real LLM providers — all without installing anything or running a server.

Quick Start

Open GUIness and build your first AI pipeline in minutes

UI Overview

Learn the layout: canvas, node library, inspector, and toolbar

Node Primitives

The 6 building blocks every pipeline is made from

Run a Pipeline

Execute your pipeline against Claude, GPT, Gemini, or Ollama

What is GUIness?

GUIness is a visual AI workflow editor. You drag and drop node primitives onto a canvas, connect them with edges, and configure each node through an inspector panel. When you’re ready, you export or run your pipeline against any supported LLM provider. The entire application is a single .html file. There is no backend, no API server, no database, and no authentication service. Everything — your skills, pipelines, credentials, and settings — lives in your browser’s localStorage or optionally synced to a private GitHub Gist.

Key features

6 Node Primitives

TEXT, INPUTS, COMPUTE, CODE, ROUTER, and CONTEXT — compose any workflow from these building blocks

Multi-Provider LLM

Run pipelines against Anthropic Claude, OpenAI GPT, Google Gemini, or local Ollama/OpenClaw

Encrypted Vault

AES-GCM encrypted credential storage in the browser — API keys never leave your machine unencrypted

GitHub Gist Sync

Back up and sync your skill library and pipelines to a private GitHub Gist

Export Formats

Export pipelines as Markdown, GPT JSON (for Custom GPTs), or Gemini Gem format

Social Publishing

Post LLM output directly to Bluesky, LinkedIn, Twitter, and Instagram

How it works

GUIness pipelines are made of nodes connected by edges. Each node has a type (one of the 6 primitives), configurable fields, and input/output ports. You wire nodes together to define a data flow, then run the pipeline in one of two execution modes:
  • Single mode — compiles the entire connected graph into one prompt and sends it to the LLM as a single call
  • Chain mode — executes nodes sequentially in topological order, piping each node’s output as input to the next
GUIness runs entirely in the browser. No data is sent to any server except for the LLM API calls you explicitly trigger using your own API keys.

Build docs developers (and LLMs) love