Your invisible AI companion for confident conversations 🤖✨

The first free open-source version of Cluely - The invisible AI assistant built by Roy "Chungin" Lee that provides real-time insights, answers, and support during meetings, interviews, presentations, and professional conversations.

• Students - Never get caught off-guard in presentations or oral exams
• Sales Professionals - Get instant product info and objection handling
• Job Seekers - Ace interviews with real-time coaching
• Consultants - Access relevant data and insights on-the-fly
• Executives - Stay sharp in high-stakes meetings
• Anyone who wants to appear more prepared and confident

If you’re looking for a hosted desktop recording API, consider checking out Recall.ai, an API that records Zoom, Google Meet, Microsoft Teams, in-person meetings, and more.

• Make sure you have Node.js installed on your computer
• Git installed on your computer
• Either a Gemini API key (get it from Google AI Studio)
• Or Ollama installed locally for private LLM usage (recommended for privacy)

1. Clone the repository:

git clone [repository-url]
cd free-cluely

2. Install dependencies:

# If you encounter Sharp/Python build errors, use this:
SHARP_IGNORE_GLOBAL_LIBVIPS=1 npm install --ignore-scripts
npm rebuild sharp

# Or for normal installation:
npm install

3. Set up environment variables:

   • Create a file named .env in the root folder

   For Gemini (Cloud AI):

   GEMINI_API_KEY=your_api_key_here

   For Ollama (Local/Private AI):

   USE_OLLAMA=true
   OLLAMA_MODEL=llama3.2
   OLLAMA_URL=http://localhost:11434

   • Save the file

1. Start the development server:

npm start

This command automatically:

• Starts the Vite dev server on port 5180
• Waits for the server to be ready
• Launches the Electron app

npm run dist

The built app will be in the release folder.

Pros:

• 100% private - data never leaves your computer
• No API costs
• Works offline
• Supports many models: llama3.2, codellama, mistral, etc.

Setup:

1. Install Ollama from ollama.ai
2. Pull a model: ollama pull llama3.2
3. Set environment variables as shown above

Pros:

• Latest AI technology
• Fastest responses
• Best accuracy for complex tasks

Cons:

• Requires API key and internet
• Data sent to Google servers
• Usage costs apply

1. Closing the App:

   • Press Cmd + Q (Mac) or Ctrl + Q (Windows/Linux) to quit
   • Or use Activity Monitor/Task Manager to close Interview Coder
   • The X button currently doesn't work (known issue)

2. If the app doesn't start:

   • Make sure no other app is using port 5180
   • Try killing existing processes:

     # Find processes using port 5180
     lsof -i :5180
     # Kill them (replace [PID] with the process ID)
     kill [PID]

   • For Ollama users: Make sure Ollama is running (ollama serve)

3. Keyboard Shortcuts:

   • Cmd/Ctrl + B: Toggle window visibility
   • Cmd/Ctrl + H: Take screenshot
   • 'Cmd/Enter': Get solution
   • Cmd/Ctrl + Arrow Keys: Move window

• UI not loading: Port mismatch resolved
• Electron crashes: Improved error handling
• Build failures: Production config updated
• Window focus problems: Platform-specific fixes applied

• Window interaction: Fixed focusable settings
• Installation confusion: Clear setup instructions
• Missing dependencies: All requirements documented

If you see gyp ERR! find Python or Sharp build errors:

# Solution 1: Use prebuilt binaries
rm -rf node_modules package-lock.json
SHARP_IGNORE_GLOBAL_LIBVIPS=1 npm install --ignore-scripts
npm rebuild sharp

# Solution 2: Or install Python (if you prefer building from source)
brew install python3  # macOS
# Then run: npm install

If you see other errors:

1. Delete the node_modules folder
2. Delete package-lock.json
3. Run npm install again
4. Try running with npm start

• Windows: App now works on Windows 10/11
• Ubuntu/Linux: Tested on Ubuntu 20.04+ and most Linux distros
• macOS: Native support with proper window management

• Translucent, always-on-top window that's barely noticeable
• Hide/show instantly with global hotkeys
• Works seamlessly across all applications

• Take screenshots of any content with Cmd/Ctrl + H
• AI analyzes images, documents, presentations, or problems
• Get instant explanations, answers, and solutions

• Process audio files and recordings
• Real-time transcription and analysis
• Perfect for meeting notes and content review

• Chat with AI about anything you see on screen
• Maintains conversation context
• Ask follow-up questions for deeper insights

• Local AI Option: Use Ollama for 100% private processing
• Cloud Option: Google Gemini for maximum performance
• Screenshots auto-deleted after processing
• No data tracking or storage

• Windows 10/11 - Full support with native performance
• Ubuntu/Linux - Optimized for all major distributions
• macOS - Native window management and shortcuts

✓ Live presentation support during classes
✓ Quick research during online exams  
✓ Language translation and explanations
✓ Math and science problem solving

✓ Sales call preparation and objection handling
✓ Technical interview coaching
✓ Client presentation support
✓ Real-time fact-checking and data lookup

✓ Debug error messages instantly
✓ Code explanation and optimization
✓ Documentation and API references
✓ Algorithm and architecture guidance

• Gemini 2.0 Flash - Latest Google AI with vision capabilities
• Llama 3.2 - Meta's advanced local model via Ollama
• CodeLlama - Specialized coding assistance
• Mistral - Lightweight, fast responses
• Custom Models - Any Ollama-compatible model

Minimum:  4GB RAM, Dual-core CPU, 2GB storage
Recommended: 8GB+ RAM, Quad-core CPU, 5GB+ storage
Optimal: 16GB+ RAM for local AI models

This project welcomes contributions! While I have limited time for active maintenance, I'll review and merge quality PRs.

Ways to contribute:

• 🐛 Bug fixes and stability improvements
• ✨ New features and AI model integrations
• 📚 Documentation and tutorial improvements
• 🌍 Translations and internationalization
• 🎨 UI/UX enhancements

For commercial integrations or custom development, reach out on Twitter

ISC License - Free for personal and commercial use.

⭐ Star this repo if Free Cluely helps you succeed in meetings, interviews, or presentations!

ai-assistant meeting-notes interview-helper presentation-support ollama gemini-ai electron-app cross-platform privacy-focused open-source local-ai screenshot-analysis academic-helper sales-assistant coding-companion