How anubhavchaturvedi-github/jarvis-ai-assistant works
J.A.R.V.I.S is a voice-controlled desktop assistant: a user speaks, speech recognition produces text for intent routing, and the selected capability performs a task before the assistant speaks a reply. The README identifies reasoning and conversation memory, live search, image generation, vision, desktop automation, WhatsApp, weather, and scheduling as major capabilities. The sampled code confirms speech input/output and several service integrations, but the main router and many feature implementations were not sampled; their documented routing links are therefore shown at subsystem level only.
Main entry points: jarvis.py Intent router · listen.py Speech recognition · Fast_DF_TTS.py Speech output · ui.py Desktop interface
Components 17
Voice interaction
- Speech recognition
NetHyTechSTT/listen.py - Speech output
TextToSpeech/Fast_DF_TTS.py - Desktop interface
ui.py
Reasoning and routing
- Intent router
jarvis.py - Reasoning and memory
co_brain.py
Information and media
- Live web search
Real_Time - Image generation
TextToImage/gen_image.py - Camera vision
Vision - Weather lookup
Weather_Check/check_weather.py
Assistant actions
- Desktop automation
Automation - WhatsApp messaging
Whatsapp_automation/wa.py - Alarms and scheduling
Time_Operations
Other components
- User
- Web search
- Desktop and web apps
- WhatsApp service
- Speech synthesis service
Connections 18
- User → Speech recognition: speaks
- Speech recognition → Intent router: writes recognized text
- User → Desktop interface: uses
- Desktop interface → Intent router: submits requests
- Intent router → Reasoning and memory: requests reasoning
- Intent router → Live web search: routes search
- Intent router → Image generation: routes generation
- Intent router → Camera vision: routes vision
- Intent router → Weather lookup: routes weather
- Intent router → Desktop automation: routes tasks
- Intent router → WhatsApp messaging: routes messages
- Intent router → Alarms and scheduling: routes scheduling
- Live web search → Web search: searches web
- Weather lookup → Web search: fetches weather
- Desktop automation → Desktop and web apps: controls apps
- WhatsApp messaging → WhatsApp service: sends messages
- Speech output → Speech synthesis service: requests audio
- Intent router → Speech output: speaks response