Forging your experience...
FlowForge is a Web Onboarding Assistant that turns user intent into actionable UI guidance inside web applications.
- Explore content and interface instantly
- Ask anything about the page
- Get step-by-step onboarding flows
Try the live Demo at useflowforge.app ✦
Why? Modern web apps are powerful – but hard to navigate.
The Assistant lets you ask questions in natural language and get immediate, contextual guidance directly in the UI.
It can:
- highlight relevant elements
- explain what's on the page
- guide users step-by-step through workflows
It works on any website out of the box and becomes product-aware when integrated.
Under the hood: browser extension + AI agent (ReAct) + RAG pipeline.
- Ask a question and get a clear explanation of what the page is about.
- Locate links, buttons, or contacts without manual search.
- Follow step-by-step actions directly in the interface.
- Highlight and summarize important parts of long pages.
- Understand unfamiliar interfaces without onboarding.
This is an early-stage experimental project showcasing the ✦ Idea ✦ itself.
It is not production-ready, and the core engine is still evolving. Expect limitations, rough edges, and ongoing improvements.
Changelog – see the list of changes.
- Node.js 22+
- Chrome / Chromium browser
- Ollama (optional, for local LLM)
npm i
npm startThis will:
- Install dependencies
- Build backend and extension
- Guide you to install the extension in Chrome
- Start the backend at http://localhost:3477
- Open any website
- Click the Assistant extension icon
- Ask a question, e.g.:
- "Where is the login button?"
- "How do I checkout?"
- "Show me the search bar"
- View the answer and highlighted elements directly on the page
- DOM-only access — operates strictly on the visible page DOM, without access to cookies or session storage
- Sensitive data filtering — excludes inputs like passwords, payment details, and other private fields during extraction
- Local-first architecture — backend and vector storage run locally by default
- Optional local AI — supports fully local inference via Ollama (no external API required)
Note: As an early-stage MVP, security is evolving and not yet production-ready.
Focus areas:
- Improve the core engine: extractors, embeddings, reasoning, and tools
- Extend context from single pages to full websites
- Build a proper standalone extension distribution
Backlog — the full list of features and improvements
- Architecture — system design and component interaction
- DOM to RAG Pipeline – from DOM to actionable intelligence
- PageModel — DOM representation for UI understanding
- Backend — AI agent backend and RAG pipeline
- Extension — browser extension and page extraction
MIT License ✦ 2026 Antony Belov
See LICENSE for details.