Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.useraven.ai/llms.txt

Use this file to discover all available pages before exploring further.

This guide is for the open-source version of Raven. If you just want to use Raven, download the app instead - no build steps required.
The open-source version lets you build Raven from source and provide your own API keys. Pick your platform and follow each step in order.

​
Prerequisites

  • Deepgram - real-time transcription (free tier available)
  • Anthropic or OpenAI - AI assistance
  • After onboarding, open Settings → API Keys to switch provider and model (Haiku/Sonnet/Opus or GPT-5.x)
  • Node.js 22.12.0 or higher
  • GStreamer for echo cancellation
  • Platform-specific build tools (Xcode CLI on macOS, Visual Studio Build Tools on Windows)

​
Choose Your Platform

macOS Setup

macOS 12 (Monterey) through macOS 15 (Sequoia), Intel and Apple Silicon.

Windows Setup

Windows 10 (21H2+) and Windows 11. All commands for PowerShell.

​
Testing

After setup, verify everything works: 
npm test              # Unit + integration tests
npm run test:coverage # With coverage report
npm run test:e2e      # End-to-end (requires npm run build first)
npm run test:all      # Everything

​
Troubleshooting

SymptomLikely CauseFix
NODE_MODULE_VERSION mismatch at runtimeNative module built for wrong Electron versionnpx @electron/rebuild -f -w better-sqlite3
App starts, no audio on macOSMissing system permissionsSystem Settings > Privacy & Security: grant Microphone and Screen Recording
App starts, no audio on WindowsWrong default audio deviceSettings > Sound: set correct default playback/recording devices
Reset all data (fresh start): 
rm -rf ~/Library/Application\ Support/project-raven/