Just install it. Start typing.
The Built-in engine runs on your device with Chrome's built-in AI — no account, no API key, no cost. Bring your own key any time for more control.
No account · No API key · No credit card · No config
Three keystrokes from rough to sharp
Type a draft
Write your prompt however it comes out. Messy and half-formed is fine.
Pause
Prompy streams a sharper, better-structured version into a quiet card beside your cursor.
Replace
One click swaps it in. Or copy it, switch styles, generate another variation.
PROMPY
thinking
Vague prompts quietly burn tokens
A fuzzy prompt usually takes a few clarifying rounds and a redo. Every round costs more tokens than getting it right the first time.
Illustrative estimate: assumes a vague prompt needs ~3 follow-up rounds. Actual savings vary by task and model.
A short list of things it does well
Any model, no lock-in
Use the on-device Built-in engine, bring your own Claude, GPT, Gemini, or Mistral key, or run fully local with Ollama or LM Studio. Switch anytime — the same Prompy works across all of them.
Private by design
No accounts, no analytics, no middleman server. With the built-in engine nothing leaves your device at all; with your own key, requests go provider-direct and keys stay encrypted on your machine. What you type is between you and your model.
Tuned to the AI you're on
Shapes each rewrite to that model — XML for Claude, tight specs for ChatGPT, grounding for Gemini. Single-platform tools can't.
Four styles
Detailed, Concise, Professional, or Coding. Switch and re-run from the card.
Conversation-aware
Reads the on-page chat so follow-ups fit what you're actually discussing.
Multiple variations
Not sure? Generate a few alternatives and pick your favorite.
Hotkey & right-click
Improve the focused field with a keystroke, or right-click any text.
Streaming & fast
Suggestions appear token-by-token, with caching so repeats are instant.
Nothing leaves your device without you
Prompy has no backend and no database, so there's nothing to breach. Run it on your device with the built-in AI and your text never leaves your machine at all — or bring your own key and your prompt goes straight to the provider you chose. Never through us.
There is no middle step. We never see your draft — there's nothing to see it with.
One draft, your way
The same rough idea — “make a prompt to help me write cold emails for my saas” — rewritten in each style.
For the sites we haven't added yet
ChatGPT, Claude, Gemini and the other usual suspects are built in. But new AI tools land every week, and no list stays current.
So instead of a list, there's a shortcut. Focus any prompt field, press the keys, and Prompy wakes up for the rest of the tab — same card, same styles. It loads only when you call it and reads nothing in the background.
on Windows / Linux: Ctrl + Shift + P
Or skip the cloud entirely
Point Prompy at a model running on your own machine (Ollama or LM Studio) and you don't need an API key, a network connection, or anyone's permission. Nothing else changes. Just zero dollars and zero packets leaving the laptop.
People reach for this when they're working with health records, customer data, NDA material, or anything where "this prompt is going to a third-party API" isn't a sentence they're willing to say. Also when they're on a plane.
Two minutes, three lines:
# 1. Install Ollama (ollama.com), then pull whatever you like ollama pull llama3.2 # 2. In Prompy, pick "Local" and use this URL http://localhost:11434/v1 # 3. Browser extension only — let it talk to Ollama OLLAMA_ORIGINS=chrome-extension://* ollama serve
LM Studio works the same way at http://localhost:1234/v1 (CORS already on).
The tutorial has the longer version →
Not your usual prompt tool
Most prompt helpers want an account, a subscription, and your prompts on their servers. Prompy asks for none of that.
Live on the Chrome Web Store — free to use, no API key needed.