The Shotgun Prompt
Send one prompt to GPT-4, Claude 3, and Gemini simultaneously. Stop copy-pasting between browser tabs.
A local-first workbench for testing GPT, Claude, Mistral, Grok, and Gemini side-by-side. Version control your prompts.
Send one prompt to GPT-4, Claude 3, and Gemini simultaneously. Stop copy-pasting between browser tabs.
Your API keys and prompt history are stored in a local SQLite database. Nothing touches our servers.
Treat prompts like code. Fork your iterations, switch between versions, and never lose a winning prompt again.
Never lose a good prompt again. Fork your prompts, iterate safely, and seamlessly switch between past versions. A complete timeline of your prompt evolution.
Don't settle for a chat interface. Inspect raw API responses, latency stats, and token usage for every single request.
Your API keys never leave your device. All data is stored locally in SQLite. Zero telemetry. Zero middleman.
Bring your own keys. Connect OpenAI, Anthropic, Mistral, Gemini and XAI in seconds. Toggle models on/off to keep your workspace clean.
Stop guessing. Tweak temperature, top_p, and frequency penalties to see exactly how they change the output.
We chose Electron to ship everywhere, but we stripped the bloat to respect your RAM.
Built directly on top of native browser APIs and standard Web Components.
Your data lives in a standard SQLite file on your disk. Backup, sync, or delete it whenever you want.
{
"runtime": "Electron",
"security": "Context Isolated",
"frontend": "Vanilla JS + Web Components",
"database": "SQLite3 (Local-only)",
"telemetry": false,
"idle_memory": "~240MB"
}
We don't rent software. No subscriptions or hidden fees. $29 to own it forever.
(Currently in Public Beta: Enjoy the app for free while we build towards our v1.0 release!)
Download for Mac Download for Windows Download for Linux
Want to learn more about our perpetual license model?
View the pricing details →