Skip to content
2nd Place

Meet Beaker

Meet Beaker — an app that streamlines experimental protocols for scientists by shortening prep time and providing a spoken interface for step-by-step guidance, note-taking, and progress tracking.

Code Video Cerebral Valley

Core trick

An on-device ExecuTorch model parses uploaded protocol documents into steps and handles voice commands offline.

Tags

sciencevoice

Description

Meet Beaker — an app that streamlines experimental protocols for scientists by shortening prep time and providing a spoken interface for step-by-step guidance, note-taking, and progress tracking. Beaker uses on-device Edge AI, so it’s instantly ready to go. Labs don’t need to set up or maintain inference servers, and scientists can use it even in hands-free environments with no internet access. Three easy use cases: upload a protocol document to automatically generate steps; use voice commands for guidance and note-taking during experiments; and track progress effortlessly — cutting logging time by up to sevenfold. Beaker keeps protocol progress stored locally for each experiment, helping scientists stay focused and in their flow state without breaking rhythm.
sskarz/Beaker★ 12 forksTypeScriptApache-2.0Created Oct 20, 2025 · last push Feb 12, 2026

README excerpt

<p align="center">
  <img src="assets/icons/beakericon.png" alt="Beaker Logo" width="200" />
</p>

<h1 align="center">Beaker</h1>

<p align="center">
  <strong>Voice-Guided Lab Protocol Execution with On-Device AI</strong>
</p>

<p align="center">
  <a href="https://cerebralvalley.ai/e/executorch-hackathon"><img src="https://img.shields.io/badge/Meta%20ExecuTorch%20Hackathon-2nd%20Place%20%F0%9F%8F%86-blue" alt="2nd Place Winner" /></a>
</p>

Beaker is a React Native mobile app that helps scientists execute laboratory protocols hands-free using voice commands and on-device AI. All inference runs locally on the device via [ExecuTorch](https://github.com/pytorch/executorch) — no cloud, no latency, full privacy.

## Demo

[Watch the full demo on Loom](https://www.loom.com/share/0d70b0c95c484c898bf662b66cfd2ce1?sid=fbeac786-c993-48c6-aa7d-47c73769814e)

## How It Works

1. **Select a protocol** — Choose from built-in protocols (PCR, ELISA, Plasmid Miniprep) or load your own
2. **Start execution** — The AI reads out the current step via text-to-speech
3. **Work hands-free** — Say "next step" or "go back" to navigate, or ask questions about the current step
4. **Get instant answers** — The on-device LLM answers protocol-related questions in real time
5. **Track your runs** — Notes, step completion, and run history are all persisted locally

## Key Features

- **Fully on-device AI** — LLM inference (Llama 3.2 1B) and speech-to-text (Whisper Tiny) run entirely on the device via Execu

Team