build-small-hackathon/puck

1---2title: Puck3emoji: 🧚4colorFrom: green5colorTo: purple6sdk: docker7app_port: 78608pinned: false9license: mit10short_description: A mischievous desktop fairy that comments on your work11tags:12  - build-small13  - thousand-token-wood14  - off-brand15  - off-the-grid16  - field-notes17  - best-demo18  - track:wood19  - sponsor:nvidia20  - sponsor:modal21  - achievement:offgrid22  - achievement:offbrand23  - achievement:llama24  - achievement:fieldnotes25---26 27<!-- TRACK + BADGES: the tag slugs above are my best guess. Before submitting, paste this28     README into the field-guide validator (https://build-small-hackathon-field-guide.hf.space/submit)29     and use the EXACT slugs it expects for the Thousand Token Wood track + each badge. -->30 31# 🧚 Puck — a desktop fairy familiar32 33Puck is a small, mischievous creature that lives on your screen. He **roams**, **peeks** at one little patch of whatever you're doing, and **murmurs** a single in-character line about it — then drifts on. He's not an assistant and not a notifier. He's company: *marginally useful, reliably charming.*34 35> **This Space is the playable demo** (a simulated desktop in your browser). Puck's real home is a transparent always-on-top overlay on your actual Mac desktop — that's the video. Here you can poke him, watch him roam, peek, react, and blend into the desktop.36 37**▶️ Demo video:** [watch on YouTube](https://youtu.be/Jzzt_UE11jU) · **📣 Social post:** [on X](https://x.com/_vu/status/2066577250137587853) · **📓 Field notes:** [read the writeup](https://huggingface.co/blog/build-small-hackathon/meet-puck)38 39## What he does40- **Roam → peek → quip.** Every so often he flutters somewhere and looks at the small region under him. A vision-language model *sees that patch and speaks in his voice* in one shot — the AI is doing the fun thing, not narrating from a script.41- **Feels things.** Each peek is classified into an emotion that drives his whole reaction together — a **gesture** (giddy laugh, NANI-confusion, a worried tremble, a wistful droop), an **aura color**, and an **emotional voice** (pitch + pace). Puck's a *learning* creature, so confusion is his honest default — and endearing.42- **Reads the room.** On a real terminal he uses on-device OCR to tell *which* coding agent you're running (Claude Code vs Codex vs opencode vs pi) and grounds his quip in the actual text on screen.43- **Camouflages.** Sit still and he cloaks — his skin clears so the desktop reads right through him, with a faint shimmer and two watching eyes. Move, and he snaps back.44- **Dreams.** At night he **blooms** the day's peeks into a small garden of memories.45 46## Built Small47Puck is a constellation of small, laptop-sized models — **nothing over 32B**, and it fits in your pocket:48- 👁️ **Vision + voice-of-the-fairy:** **Holotron-12B** — H Company's computer-use VLM post-trained from NVIDIA's Nemotron-Nano-12B-VL (one model that both *sees* and *speaks* the quip).49- 🔤 **Tool/site recognition:** on-device **Vision OCR** + an **ONNX CLIP ViT-B/32** (~88M) fingerprinter.50- 🗣️ **Neural voice:** **Kokoro-82M**, running in-browser (WebGPU) — a fairy voice in 82M params.51 52The whole companion runs locally and offline ("Off the Grid"). *This hosted Space* uses a cloud (Modal) copy of the 12B so it works in your browser — which scales to zero, so **the first peek may take a moment while Puck stretches his wings.** ✨53 54## Under the hood55A custom React UI served by a **`gradio.Server`** daemon (Off-Brand) — two habitats from one app: this browser **sim**, and a **Tauri** overlay for the real desktop. Region peeks, an emotion contract, a memory log that blooms into a garden.56 57*HF Build Small — Thousand Token Wood (Creative).*58