Offline Tiny-LM Advisor
25MB local models suggest goals and copy advice while you type, fully on-device
- Problem
- Writers want live suggestions tied to their goals, career plans or pitch decks while drafting, but cloud models raise privacy concerns and need connectivity. Someone already built 25MB tiny models running entirely in the browser, proving the demand, yet regular users still lack a ready-made product.
- Solution
- A local-first writing assistant that runs in the browser or a menu bar, using tiny fine-tuned models to match what you are typing against tens of thousands of built-in advice rules and surface related concepts and phrasing; everything runs offline, and you can import your own notes and book summaries as advice sources.
- Users
- Professionals writing weekly reports, goal reviews and fundraising materials; privacy-sensitive writers and students
- MVP
- Browser-side offline tiny models plus three scenario rule sets (personal goals, career, pitch); a live side-panel suggestion overlay; import personal notes to extend rules; skip collaboration, cloud sync and general chat
- Revenue
- Free for one scenario plus a one-time unlock for all scenarios and custom corpus import; on-prem license for enterprises.
- Why now
- Tiny models plus WebGPU/MLX make local inference practical, and privacy-sensitive users are pushing back on cloud AI; existing demos are technical showcases without packaging for specific writing scenarios.