Yes-Brainer asks several AI models one question and shows you where their answers differ. It runs entirely in your browser: there is no sign-up, and no server run by this project holds your conversations.
There is no sign-up form, no email, no password and no profile — because there is no backend to hold one. Recorded demo councils can be read without any API key at all.
The app is a static bundle of HTML, CSS and JavaScript. The network traffic from your browser is calls to the model providers you chose, with your keys — direct to the vendor for the native adapters, and through OpenRouter’s gateway first if you use OpenRouter, which is what its one-key-many-vendors convenience buys.
There is also one cookieless counter on the official site. It records the route pattern, screen size, language, the referrer that brought you, and counts of a few feature-level actions — that a feature was used, not what was in it. No cookies, no client-side identifier.
Bring keys for the providers you want — Anthropic, OpenAI, Google, Groq, OpenRouter, or a local Ollama that needs no key — and pay those providers directly. No subscription, no paywall on the app itself. Two duties stay yours: check the address bar reads yesbrainer.ai before pasting a key, and use a dedicated key with a spending limit set in your provider’s console.
Keeping data on your device moves the risk rather than removing it. Anything with access to your browser profile can read what is stored there, losing the device loses the data on it, and browsers can evict site storage. Your prompts still travel to whichever providers you point the app at, under their terms. The software is provided as-is, with no warranty.
Every answer Yes-Brainer shows is generated by an AI model and can be confidently wrong. Seeing several models agree is not evidence that they are right — the app shows the spread; the judgment stays yours.
Yes-Brainer — ask several AI models one question and see where they disagree. Free and open source; no account, and you bring your own API keys.