Skip to content

About

Dump anything. Ask anything. Nothing leaves your device. — local-first semantic memory, in-browser embeddings.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Repository files navigation

cubby

Dump anything. Ask anything. Nothing leaves your device.

License: MIT Hacktoberfest 2026 — Week 3 Powered by EmbeddingGemma PRs welcome

Live demo · DEV write-up · Architecture · Honesty table

cubby — the UI at a glance

dump anything. ask it back in your own words. ranked by meaning. nothing uploaded.


Everyone has the "I know I saved that somewhere" problem. You copy ~50 things a day and lose most of them — a wifi password, a docker run incantation, a flight number, that one address. Every notes app's fix is the same: organize it. Folders, tags, a system you abandon by week two.

cubby asks for nothing. Paste anything. One keypress. No folders, no tags, no title. Later, ask for it back in your own words — not the words you saved it with. An open-weight embedding model (EmbeddingGemma, 300M) runs entirely in your browser tab and ranks what you saved by meaning, offline.


Features

  • Fully local. Your dumps never touch a server. The model is a file the app downloads once (~300 MB) and runs in the tab. No account, no API key, no telemetry. Saving, searching and switching themes made zero network requests in my check; the only traffic is the model download on first visit and a small model config request at page load, both to Hugging Face. Checkable in the network tab.

  • Semantic + lexical hybrid search. 0.7 · cosine + 0.3 · lexical, so a paraphrased query finds its target and an exact keyword never loses to a weak semantic guess. Measured recall@3 of 20/20 on a fixed test set vs. keyword's 14/20 — full honesty table here.

  • Offline-first PWA. Service worker caches the app shell + model weights; search keeps working on a plane.

  • Share-to-cubby. On Android, the OS Share sheet writes straight into cubby — no app opening, no pasting. (iOS Safari's Web Share Target support is weak; see RISKS.md R8.)

  • Five themes × light/dark, all WCAG AA–verified (test/contrast.mjs). Terminal / paper / mono / cobalt / ember.

  • Keyboard-first. Cmd/Ctrl+K to focus, arrows to navigate, Enter to copy, Esc to clear. No mouse needed for the full dump → ask → copy loop.

Five themes in dark (top) and light (bottom)

5 themes × light/dark. Each pair passes WCAG AA.

Demo

dump → ask → copy loop in under 5 seconds
dump → ask → copy, in under 5 seconds. Also the 10-second intro video.

Try it

Live: https://cubby-6mn8.onrender.com

Or run locally:

git clone https://github.com/ibrahim-iqbal/cubby-hf26-wk3.git
cd cubby
npm ci
npm run dev

Then open http://localhost:5173. First load downloads the model (~300 MB, one time, cached by the service worker thereafter).

Build + preview the production bundle:

npm run build
npm run preview

How it works

Everything inside the dashed box lives on your device, forever:

%%{init: {'theme':'base','themeVariables':{'primaryColor':'#141619','primaryTextColor':'#e8e9ea','primaryBorderColor':'#2d3136','lineColor':'#7ee0b8','fontFamily':'monospace'}}}%%
flowchart LR
    subgraph browser["your browser tab — nothing leaves here"]
        ui[React UI<br/>dump / ask]
        model[EmbeddingGemma 300M<br/>transformers.js]
        store[(IndexedDB<br/>items + vectors)]
        sw[Service Worker<br/>offline cache]
        ui <--> model
        ui <--> store
        sw -.caches.-> ui
        sw -.caches.-> model
    end
    hf[Hugging Face hub<br/>one-time model download]
    hf -.first load only.-> model
    user((you)) --> ui
Loading

Full detail: ARCHITECTURE.md (model choice, Matryoshka 256-dim truncation, hybrid-ranking math, failure/fallback ladder), SPEC.md (features, flows, data shapes, acceptance criteria).

Stack

  • UI: React 19 + Vite + TypeScript, static site, no backend
  • Model runtime: @huggingface/transformers v3 (transformers.js) running onnx-community/embeddinggemma-300m-ONNX with q8 quantization
  • Storage: IndexedDB for items + 256-dim Float32 vectors; localStorage for settings (read before first paint to avoid theme flash)
  • Offline: vite-plugin-pwa (service worker precaches shell + runtime-caches model weights)
  • Deploy: Render static site — render.yaml blueprint, no env vars needed

Deploy your own

render.yaml is a Render static-site blueprint: npm ci && npm run build, publish dist, SPA-rewrite every route to index.html (so /share and client routes work). On Render pick New → Blueprint, point at your fork, done. No environment variables, no secrets, no cost beyond Render's free static tier.

Any static host works — Netlify, Vercel, Cloudflare Pages, GitHub Pages (with a rewrite rule) — the build output is a plain dist/ folder.

Contributing

Issues and PRs welcome. The repo has a full planning trail if you want to read before contributing:

  • docs/PLAN.md — scope, non-goals, day-by-day plan, decisions log
  • docs/SPEC.md — features, user flows, data shapes, acceptance criteria
  • docs/ARCHITECTURE.md — model, embeddings, storage, search pipeline
  • docs/UI.md — minimal + terminal aesthetic, 5 themes × light/dark, motion rules
  • docs/RISKS.md — risk register with mitigations and kill-switches
  • test/queries.md — D4 recall measurement + honesty table

Local setup: standard Node 22+. npm ci && npm run dev.

Verification scripts in test/:

node test/contrast.mjs    # WCAG AA check across all 5 themes × 2 modes

For retrieval-quality checks, open the dev console in a running build and paste the small harness in src/testdata/queries.mjs (D4 honesty table).

Guidelines:

  • Keep the "nothing uploaded" invariant honest. New features must not add outbound network calls at runtime (model fetch at first load is the only one, cached permanently thereafter).
  • Changes to the ranking math must be measured against test/queries.md.
  • All 5 themes × light/dark must pass WCAG AA (test/contrast.mjs).

Honest limits

(Stated plainly, same as in the DEV post.)

  • No image/OCR capture — text only, by design for v1.
  • No sync across devices. JSON export/import is the only portability — there's no server to sync through.
  • Hybrid ranking narrows but doesn't erase cases where the semantic and lexical signals disagree. Shown as a known behavior, not hidden.
  • The honesty table is 20 items — it's the fixed set this project commits to re-running, not a claim the ceiling is infinite.
  • iOS Share-to-cubby is unreliable (Web Share Target support is weak on Safari). Falls back to manual paste; stated outright rather than implied.

Acknowledgements

  • EmbeddingGemma by Google — the model that makes this whole thing possible.
  • transformers.js by Hugging Face — in-browser ONNX runtime.
  • Render — static hosting, zero config.
  • The Hacktoberfest Open-Source AI Challenge — the forcing function.

License

MIT.

About

Dump anything. Ask anything. Nothing leaves your device. — local-first semantic memory, in-browser embeddings.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Used by

Contributors

Languages