Skip to content

v1shay/echo-OS

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

echo-OS Demo

Echo-OS is a voice-first autonomous OS that executes real-world tasks through continuous autonomous agents.

A real-time execution layer that runs on natural language input, built as the winner of an ElevenLabs, FeatherlessAI, and AoPS-backed hackathon.


Features

  • Voice → execution pipeline (not just transcription)
  • Continuous agent loop (not request/response)
  • Real-time reasoning + execution streaming
  • Native OS control via Electron layer
  • Tool use across local system and web
  • Persistent memory across sessions
  • End-to-end speech interface (STT + TTS)

Architecture

Layer Purpose Stack
Interface Real-time transcripts + execution state React + WebSockets
Agent Planning, reasoning, orchestration Python
Execution Local + web task execution Custom tool layer
Voice Input + output speech pipeline Whisper + ElevenLabs
Desktop System-level control Electron

Anatomy

echo-os/
├── frontend/        # realtime UI + streaming state
├── backend/         # agent loop + orchestration
├── desktop/         # electron system layer
├── agents/          # planning + execution logic
├── tools/           # local + web integrations
└── memory/          # session + persistent state

Install

git clone https://github.com/your-username/echo-os.git
cd echo-os

Backend

cd backend
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
uvicorn main:app --reload

Frontend

cd ../frontend
npm install
npm run dev

Desktop

cd ../desktop
npm install
npm run electron

About

Voice-native OS enabling hands-off computer use for blind users; winner of RavenHacks 2026

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors