Welcome
Every click, turned into a polished guide.
ClickToDoc records what you do in the browser and hands you back a clean, step-by-step walkthrough. Record, tidy, enhance with your own AI, export.
ClickToDoc quietly records what you do in the browser and hands you back a clean, annotated, step-by-step walkthrough. Polish it with your own AI - your key, or a fully local model - then export it anywhere. No accounts, no telemetry, nothing leaves your machine.
Free forever. Local-first. No sign-in, no cloud, no tracking.
At a glance
The 30-second tour
The same walkthrough that greets you on first run. Step through it, or let it play.
Welcome
ClickToDoc records what you do in the browser and hands you back a clean, step-by-step walkthrough. Record, tidy, enhance with your own AI, export.
Step one
Every click, page change and keystroke becomes a captured step, screenshot and all. Narrate with Voice Notes, fold menu sequences into one numbered step with Multi-click, or press Alt+Shift+S for a manual snapshot.
Step two
Arrows, highlights, numbered badges, speech-bubble callouts, focus dim, smart erase and blur. Turn on Smart zoom to crop tight on the click - or let your own AI annotate, describe and translate for you.
Step three
A self-contained HTML page, a Word DOCX, Markdown, a print-ready PDF, an animated GIF walkthrough, a ZIP of every step image, or AI-readable JSON. Everything is embedded: nothing to host, no attachments to chase.
Yours, only yours
100% local. No telemetry, no sign-in, no cloud. Switch on automatic backups to your Downloads folder so your work is always safe, entirely on your own machine.
Why ClickToDoc
Every feature exists to turn a click-by-click task into a document you'd be happy to send anyone, in less time than the screenshots alone used to take.
Plug in OpenAI, Gemini, Claude, OpenRouter - or a fully local Ollama model. It polishes titles, writes descriptions, translates, annotates screenshots by sight and redacts sensitive data. You review every change; one undo reverts it all.
Multi-click mode folds a whole dropdown-and-menu sequence into a single screenshot with numbered markers - and the AI can merge near-duplicate steps after the fact.
Turn on Voice Notes and everything you say lands on the step you're on, live - your spoken context becomes the written guide.
Arrows (straight, curved, hand-drawn), highlights, boxes, numbered markers with leader tails, speech bubbles, blur, focus dim, zoom callouts and smart erase that blends into the background. Pixel-identical in every export.
Drag steps to reorder in the list or the grid view, insert headings, notes and images exactly where you are, duplicate steps, paste screenshots straight from your clipboard - and move or copy steps between workflows.
Click-marker styles and colours, stroke widths, text sizes, per-step spotlight and smart zoom, Word templates from your own .docx, palettes, banners and logos - the guide looks like yours.
Self-contained HTML, branded Word DOCX with a table of contents, print-ready PDF, Markdown, an animated GIF walkthrough, all images as ZIP - or a documented JSON that any AI agent can read and edit.
No accounts, no servers, no telemetry. Sensitive fields are masked at capture; smart redact finds emails, cards and phone numbers. Even AI requests go straight from your machine to your provider - with your redactions burned in.
Scheduled JSON backups to your own Downloads folder; restore on any machine. Optional publish to your own server and Google Drive upload for self-hosters. A desktop app records beyond the browser.
In action
Straight from the extension: capture, mark up, export.
Install
Works in any Chromium browser. Both listings are live and free.
Other Chromium browsers (Brave, Arc, Vivaldi, Opera) can install from either store. Questions? Email me.