AI prompt optimizer

DRAFT. SHARPEN. SEND.

Prompy vague typo'd half-formed structured on-topic concise

Prompy rewrites your rough draft into a clear, well-structured prompt — right where you type, in ChatGPT, Claude, Gemini and more. Bring your own key or run a fully local model.

Add to Chrome soon Get started → ★ GitHub

// free & open source · extension + desktop app

4
Improvement styles — Detailed, Concise, Professional, Coding
8+
AI tools supported, plus any local model
0
Servers. Keys stay on your device, encrypted at rest

Connect any model — Claude, GPT, Gemini, Mistral, or Ollama / LM Studio. Prompy sharpens the prompt before it's sent.

Get the extension →
#00.01How it works

Three keystrokes from rough to sharp

01

Type a draft

Write your prompt however it comes out — messy and half-formed is fine.

02

Pause

Prompy streams a sharper, better-structured version into a quiet card beside your cursor.

03

Replace

One click swaps it in — or copy it, switch styles, or generate another variation.

chat.example.com
PROMPY thinking
#00.02The cost

Vague prompts quietly burn tokens

A fuzzy prompt usually takes a few clarifying rounds and a redo to land — every round costs more tokens than getting it right the first time.

Tokens to reach a good answer -74%
0
0
Vague prompt1 vague + ~2 clarifying rounds + 1 redo
Sharp promptOne Prompy-optimized prompt

Illustrative estimate — assumes a vague prompt needs ~3 follow-up rounds to land. Actual savings vary by task and model.

#00.03Features

Everything you need to prompt better

Any model

Claude, GPT, Gemini, Mistral — or run fully local with Ollama / LM Studio. No lock-in.

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 alternatives on demand and pick the one that lands.

See what changed

A word-level diff shows exactly how your prompt was sharpened — trust every rewrite.

Private by design

Keys live on your device (encrypted on desktop). No server, no tracking, no accounts.

Hotkey & right-click

Improve the focused field on demand, or right-click any text — even where the card can't reach.

Streaming & fast

Suggestions appear token-by-token, with caching so repeats are instant.

Your keys never leave your device

Prompy has no backend and no database — there's nothing to breach. Your prompts go straight to the provider you chose (or a model running on your own machine), authenticated with your own key.

+ Device-only API keys + Encrypted at rest (desktop) + 100% local mode + Open source
#00.04Styles

One draft, your way

The same rough idea — “make a prompt to help me write cold emails for my saas” — rewritten in each style.

GET STARTED →

Install the extension or run the desktop app today — free and open source. Heads-up when it hits the Web Store?

Read the quick-start →