Open Source & Free

Your AI assistant that
sees your screen

AI Cowork watches what's on your screen, reads it with OCR, and lets you ask questions about your work. 100% local. Your data never leaves your machine.

Download for Windows View on GitHub

v1.0.0 · Windows · 38 MB · or install from source →

📺 Live Screen Preview
Chat
Hi! I can see your screen. Ask me anything.
What am I working on?
You're editing app.py in VS Code — it looks like a Flask server with screen capture logic.
Summarize this page
You're viewing the CrewAI GitHub repo. It's a framework for building autonomous AI agents with Python.
100%
Local Processing
0
Data Sent to Cloud
3
LLM Providers
<5s
Screen Read Time
Everything you need to work smarter
AI Cowork runs quietly in the background, reading your screen and building context so you can ask questions anytime.
📸

Live Screen Capture

Automatically captures your screen every few seconds using the blazing-fast mss library. Multi-monitor supported.

🔍

OCR Text Extraction

Reads all text on screen using Tesseract OCR with smart preprocessing — contrast enhancement, dual-mode scanning, garbled line filtering.

💬

Chat About Your Screen

"What am I looking at?" "Summarize this page." "What was I doing 5 minutes ago?" — the AI knows because it was watching.

🔒

Privacy Filters

Exclude sensitive windows by title keyword — banking, passwords, private browsing. Capture auto-pauses when those windows are active.

Multiple LLM Backends

Use Ollama locally (zero data leaves your machine), or connect to OpenAI or Anthropic Claude for even smarter answers.

⏸️

Pause & Resume

One-click pause in the dashboard. When paused, nothing is captured or stored. Full control, always.

🧠

Session Memory

Keeps up to 50 screen observations in memory during your session. Nothing is written to disk — ever. Close the app, history is gone.

⚙️

Settings UI

Switch LLM providers, set API keys, adjust capture intervals, manage privacy filters — all from the web dashboard. No restart needed.

🌐

Web Dashboard

Clean, modern interface with live screen preview and chat panel. Runs on localhost:8080. Open in any browser.

Your data stays on your machine
Built from the ground up with privacy as a non-negotiable. No accounts, no telemetry, no cloud storage.
🏠

Fully Local Processing

Screen capture, OCR, and LLM inference all happen on your machine. With Ollama, zero bytes leave your network.

💾

No Persistence

Everything is stored in RAM only. Close the app and all observations are gone. No database, no files, no traces.

🚫

No Telemetry

No analytics, no crash reports, no usage tracking. The app makes zero outbound connections (except to your chosen LLM).

🔐

Smart Exclusions

Automatically skip capturing when sensitive apps are in focus. Set keywords like "bank", "password", "1password".

📺 Your Screen
🔍 Tesseract OCR (local)
🧠 LLM (Ollama — local)
💬 Your Answer

✓ Everything happens on localhost

No internet required when using Ollama

Choose your AI backend
Switch between providers anytime from the Settings panel — no restart needed.

Ollama

qwen2.5:7b, llama3, mistral, etc.
100% Local

Free. Runs on your GPU via Docker. Your data never leaves your machine. Requires NVIDIA GPU.

OpenAI

GPT-4o, GPT-4o-mini
Cloud API

Bring your own API key. Best quality answers. No GPU required. Pay per usage.

Anthropic

Claude Sonnet, Claude Haiku
Cloud API

Bring your own API key. Great for long context. No GPU required. Pay per usage.

Get started in 60 seconds

Clone, configure, run. It's that simple.

# Clone the repo
git clone https://github.com/Sami-Fd/ai-cowork.git
cd ai-cowork

# Configure
cp .env.example .env

# Install dependencies
pip install -r requirements.txt

# Start Ollama (optional — for local LLM)
docker compose up -d

# Run!
python app.py
Star on GitHub Download for Windows (v1.0.0)
Frequently Asked Questions
Is AI Cowork free?

Yes, AI Cowork is completely free and open-source under the MIT license. No paid plans, no subscriptions, no hidden costs.

Does AI Cowork send my screen data to the cloud?

No. When using Ollama (local LLM), all processing happens entirely on your machine. Zero data leaves your network. Cloud providers (OpenAI, Claude) are optional — the text is only sent if you choose to use them.

What LLMs does AI Cowork support?

AI Cowork supports Ollama for 100% local inference (qwen2.5, llama3, mistral, etc.), plus OpenAI GPT-4o and Anthropic Claude as optional cloud backends. You can switch between them at any time from the dashboard.

What are the system requirements?

Windows with Tesseract OCR installed. For local LLM: Docker and an NVIDIA GPU (4GB+ VRAM). For cloud LLMs: just an API key — no GPU needed.

Is my screen data stored anywhere?

No. Screen observations are kept in RAM only during your session. Nothing is written to disk. Close the app and all data is gone — no database, no files, no traces.

Can I exclude sensitive windows like banking apps?

Yes. Add keywords like "bank", "1password", or "private" to the privacy filter. AI Cowork will automatically skip capturing when those windows are in focus.