Newsletter
Join the Community
Subscribe to our newsletter for the latest news and updates
Private AI chat, local agents, and image and video generation in one suite
DreamFort is a private AI suite that combines chat with frontier models, a local AI agent, and image and video generation in one app. It strips your identity from every request, ensuring no tracking, no logs tied to you, and no profiles. The suite includes confidential AI chat, a private AI agent that runs on your device, and a video and image studio with permissive models.
How do you make money? We sell credits - $1 buys 1,000, spent per message. That's the whole business model. We don't run ads and we don't sell data; the architecture means we never even see who asked what.
Can you really not read my chats? Really - and not as a promise, as a protocol. Messages are encrypted on your device, routed through Oblivious HTTP relays that hide who you are, and only decrypted inside attested secure enclaves. No single party, including us, ever holds both your identity and your prompt.
How is this different from ChatGPT's temporary chats? Temporary chat is a retention policy: OpenAI still receives your account, IP address, and prompt together, and may keep them for up to 30 days. Here, the link between you and the prompt never exists in the first place.
Which models do I get? ChatGPT, Claude, Gemini, Grok, DeepSeek, ByteDance Seed, and Z.ai GLM - including unrestricted open AI models - switchable mid-conversation in one app. The Studio adds Seedance 2.5, Veo, Kling, and the unrestricted Wan line for video, plus Nano Banana, GPT Image, Seedream, and Grok Imagine for images.
Where does the Local Agent's code actually run? On your device. Unlike every other AI agent, the Local Agent's loop executes in a sandbox inside your browser, so the code it writes, the files it builds, and the data it reads never touch our servers. Only its calls to the models go out - through the same anonymizing layer as your chats.
What can the Video Studio actually make? Clips up to 30 seconds with synced audio on Seedance 2.5, ByteDance's newest model, aspect ratios from 21:9 cinema to 9:16 vertical, image-to-video animation of any photo or generation, style presets, and 2x/4x upscaling. An AI director agent can plan multi-scene films - it writes per-shot prompts and keeps characters consistent across cuts. Start from a blank prompt or remix a template.
Will the video and image models refuse my prompts? The Studio carries permissive models - Wan for video, Seedream for images - alongside Veo, Kling, Nano Banana, and GPT Image. Pick one and it generates what you asked for with minimal filtering - and the prompt travels through the same anonymity layer as everything else, so it's never tied to your name.
Do I need an account? No. Hit send in the chat box at the top of the page to try it as a guest. When you want chat history and every model, sign up with Google — or with just a crypto wallet, no email required.
What does it cost? Free messages when you sign up, no card. After that you pay per message from a credit balance ($1 = 1,000 credits). Subscribe from $14.99/month for credits that renew automatically — cancel anytime — or buy a one-time top-up instead.
