Skip to content

About

Speak a job, get a quote. Local open-weight model, no account, no server.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Repository files navigation

HushQuote

Speak a job. Get a quote. Nothing leaves your device.

License: MIT Hacktoberfest 2026 — Week 2 Powered by Gemma 3 270M PRs welcome

Live demo · DEV write-up · Build log · Risks

HushQuote — real job in, itemized quote out, all on-device

say the job, confirm the lines, export the PDF. Gemma 3 270M runs entirely in your browser tab.


Every tradesperson I know who works for themselves does the same thing after a job: sits in the van, opens a notes app, and tries to turn "forty square meters, two days, plus materials" into something a client will actually pay against. Then they forget a line, round a number wrong, or just don't send the quote for three days because writing it feels like a second job.

The invoicing SaaS fix is a $15/month subscription and an account you have to make, for software that's worse at the one job that actually matters: turning what you just said out loud into a document. HushQuote fills that gap. It's cheap enough to be a real side-hustle tool, not a line item.

Features

  • Fully local. Gemma 3 270M (Q8_0 GGUF) runs entirely in the browser via WebGPU/WASM through wllama. No API key, no backend, no account. Client names and day rates never leave the device they were typed on.
  • The model extracts; the app decides what's true. Every model-sourced line is visually provisional ("Estimated. Yours to set." label, dashed border) until you tap to confirm it. Math is always computed by plain JS over whatever's on the sheet — not by the model.
  • Dashboard + Sheet + Command Bar. Every saved quote in one list with stat cards; one living quote document instead of a wizard; mic or textarea, one submit button, nothing else.
  • PDF export via the browser's own print dialog. Zero added dependencies.
  • Manual mode fallback. If the model fails to load, you can still type lines by hand. The app degrades honestly.
  • Hallucination filter + zod schema validation + one repair retry. When the model goes off-script, the app catches it, retries once, and surrenders to manual rather than ship a wrong number silently.

Try it

Live: https://hushquote.onrender.com

Or run locally:

git clone https://github.com/ibrahim-iqbal/hushquote-hf26-wk2.git
cd hushquote-hf26-wk2
npm ci
npm run fetch-model   # one-time ~278 MB Gemma 3 270M download
npm run dev

Then open http://localhost:5173.

Stack

  • UI: React 19 + Vite, static site, no backend
  • Model runtime: wllama (llama.cpp compiled to WebAssembly / WebGPU) running Gemma 3 270M-instruct Q8_0 GGUF
  • Validation: zod schemas (src/lib/schema.js) check every model response before it touches the sheet
  • Storage: localStorage only — quotes, business profile, rate library all on-device
  • PDF export: the browser's native print dialog
  • Deploy: Render static site, auto-deploys on push

Honest limits

Stated plainly, same as in the DEV write-up:

  • The 270M model has specific, repeatable failure modes documented in docs/RISKS.md and the 20-transcript table in the DEV post — "Callout" line leaks (filtered in src/lib/filterHallucinations.js), fragmented line items, occasional verbatim echo of unrelated training examples.
  • JSON-schema grammar guarantees valid tokens; it doesn't guarantee semantically correct content. That's what the "estimated → tap to confirm" UI is there for.
  • Voice input needs Chrome or a Chromium-based browser (Web Speech API support is patchy on Safari/Firefox).

Contributing

Issues and PRs welcome. The repo has a full planning trail:

Guideline: keep the "nothing uploaded" invariant honest. New features must not add server-side calls. The model is a file, not a service.

Acknowledgements

  • Gemma 3 270M by Google — small enough to ship as a file.
  • wllama — llama.cpp in your browser.
  • Render — static hosting, zero config.
  • The Hacktoberfest Open-Source AI Challenge — the forcing function.

License

MIT.


crafted by ibrahim-iqbal · dev.to

About

Speak a job, get a quote. Local open-weight model, no account, no server.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Used by

Contributors

Languages