Hawkeye

🦅 The First Proactive AI Assistant for Desktop

Watch keenly. Act thoughtfully. 10x your productivity.

🌐 Website · 📖 Documentation · 🐛 Report Bug · 💡 Request Feature

---

🎯 What is Hawkeye?

Traditional AI waits for your commands. Hawkeye watches and helps proactively.

Hawkeye is an AI-powered desktop assistant that observes your work environment—screen, clipboard, files—and proactively offers intelligent suggestions. No prompts needed.

Feature	Copilot / Cursor / Claude Code	Hawkeye
Mode	Reactive (you ask)	Proactive (it watches)
Scope	Code only	Everything: coding, browsing, writing
Privacy	Cloud-based	Local-first, your data stays local
Control	AI executes	You decide what to execute

✨ Key Features

🔍 Zero-Prompt Intelligence Automatically understands your context No need to explain what you're doing Suggests actions before you ask	🏠 Privacy-First Architecture All perception runs 100% locally Data never leaves your device Works offline with local LLMs
🎯 Smart Task Tracking Identifies your main task goal Generates actionable next steps Learns from your workflow	🔗 Multi-Platform Sync Desktop ↔ Browser seamless sync VS Code extension integration Cross-app workflow automation

🚀 Quick Start

Download

Platform	Download
	Apple Silicon (.dmg) · Intel (.dmg)
	Installer (.exe)
	Debian/Ubuntu (.deb) · AppImage

⚠️ macOS: "App is damaged" fix

# Remove quarantine attribute
xattr -cr /Applications/Hawkeye.app

Setup in 60 Seconds

# 1. Clone
git clone https://github.com/anthropics/hawkeye.git && cd hawkeye

# 2. Install
pnpm install

# 3. Run
pnpm dev

Configure AI Provider

Option 1: Claude API (Recommended)

Enter your Anthropic API key in Settings → API Configuration.

Option 2: Local LLM with Ollama (100% Offline)

# Install Ollama
brew install ollama  # macOS
# Windows/Linux: https://ollama.com/download

# Download models
ollama pull qwen3:8b        # Text (8GB+ RAM)
ollama pull qwen2.5vl:7b    # Vision

# Select "Ollama" in Hawkeye settings

🏗️ Architecture

┌─────────────────────────────────────────────────────────────────┐
│                        HAWKEYE ENGINE                           │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│  ┌─────────────┐    ┌─────────────┐    ┌─────────────┐         │
│  │  PERCEPTION │───▶│  REASONING  │───▶│  EXECUTION  │         │
│  │   Engine    │    │   Engine    │    │   Engine    │         │
│  └─────────────┘    └─────────────┘    └─────────────┘         │
│        │                  │                  │                  │
│   • Screen OCR      • Claude/Ollama     • Shell Commands       │
│   • Clipboard       • Task Analysis     • File Operations      │
│   • File Watch      • Intent Detect     • App Control          │
│   • Window Track    • Suggestions       • Browser Auto         │
│                                                                 │
├─────────────────────────────────────────────────────────────────┤
│                         INTERFACES                              │
├───────────────┬───────────────┬───────────────┬─────────────────┤
│   🖥️ Desktop   │  🧩 VS Code    │  🌐 Chrome     │    📦 Core      │
│   (Electron)  │  Extension    │  Extension    │    (npm pkg)    │
└───────────────┴───────────────┴───────────────┴─────────────────┘

📦 Project Structure

hawkeye/
├── packages/
│   ├── core/                 # 🧠 Core engine (local processing)
│   │   ├── perception/       #    Screen, clipboard, file monitoring
│   │   ├── ai/               #    AI providers (Claude, Ollama, etc.)
│   │   ├── execution/        #    Action execution system
│   │   └── storage/          #    Local database (SQLite)
│   │
│   ├── desktop/              # 🖥️  Electron desktop app
│   ├── vscode-extension/     # 🧩 VS Code extension
│   └── chrome-extension/     # 🌐 Chrome browser extension
│
├── docs/                     # 📖 Documentation
└── website/                  # 🌐 Marketing site

🔒 Privacy & Security

Aspect	How We Protect You
Screenshots	✅ Analyzed locally, never uploaded
Clipboard	✅ Processed on-device only
Files	✅ Monitored locally, paths never sent
AI Calls	✅ Only minimal context text sent (or use local LLM)
Dangerous Ops	✅ Always requires your confirmation

📁 All data stored in ~/.hawkeye/ — you own your data.

📖 Usage Examples

As a Library

import { HawkeyeEngine } from '@hawkeye/core';

const engine = new HawkeyeEngine({
  provider: 'ollama',
  model: 'qwen3:8b'
});

// Get AI-powered suggestions based on current context
const suggestions = await engine.observe();

// Execute a suggestion with user confirmation
await engine.execute(suggestions[0].id);

File Watcher

import { FileWatcher } from '@hawkeye/core';

const watcher = new FileWatcher({
  paths: ['~/Downloads', '~/Documents'],
  events: ['create', 'move']
});

watcher.on('change', (event) => {
  console.log(`${event.type}: ${event.path}`);
});

🗺️ Roadmap

• Core perception engine
• Desktop app (Electron)
• VS Code extension
• Chrome extension
• Local LLM support (Ollama)
• Desktop ↔ Extension real-time sync
• Plugin system
• Custom workflow builder
• Mobile companion app

🤝 Contributing

Contributions are what make the open source community amazing! Any contributions you make are greatly appreciated.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

See CONTRIBUTING.md for detailed guidelines.

⭐ Star History

📄 License

Distributed under the MIT License. See LICENSE for more information.

---

🌐 Website · 📖 Docs · 🐦 Twitter · 💬 Discord

_{Built with ❤️ by the Hawkeye Team}

If Hawkeye helps you, please consider giving it a ⭐