How vigneshwaran484/jarvis works
Jarvis is a desktop voice assistant. In the main V2 workflow, a user wakes the assistant, speaks a command, and the background agent asks a local Ollama model whether to invoke a tool or answer; tool results return to the agent, which speaks the final response. The Tkinter reactor displays assistant state. The repository also has a separate console-only V1 agent. Tool implementations and V2 orchestration share one large file. The README documents capabilities beyond the sampled excerpts; links to those features are included only where the README supports them.
Main entry points: agent_v2.py ReAct reasoning loop · agent_v1.py Console agent · wakeword.py Wake listener · config.py Runtime configuration
Components 17
Voice and interface
- Wake listener
wakeword.py - Speech input and TTS
agent_v2.py - Arc Reactor GUI
reactor.py
Agent runtime
- Voice agent
agent_v2.py - Runtime configuration
config.py - ReAct reasoning loop
agent_v2.py - Console agent
agent_v1.py
Assistant tools
- App control
agent_v2.py - Web and weather
agent_v2.py - System controls
agent_v2.py - Screen capture
agent_v2.py - File operations
agent_v2.py
External integrations
- Ollama
- Speech services
- Desktop and OS
- Web services
Other components
- User
Connections 22
- User → Wake listener: says wake word
README.md - Wake listener → Voice agent: activates
README.md - Voice agent → Speech input and TTS: captures and speaks
README.md - Voice agent → ReAct reasoning loop: runs
agent_v2.py - ReAct reasoning loop → Ollama: requests inference
agent_v2.py - ReAct reasoning loop → App control: dispatches tools
agent_v2.py - ReAct reasoning loop → Web and weather: dispatches tools
agent_v2.py - ReAct reasoning loop → System controls: dispatches tools
agent_v2.py - ReAct reasoning loop → Screen capture: dispatches tools
agent_v2.py - ReAct reasoning loop → File operations: dispatches tools
agent_v2.py - Speech input and TTS → Speech services: uses TTS and recognition
README.md - Speech input and TTS → Desktop and OS: plays audio
agent_v2.py - App control → Desktop and OS: controls apps
- System controls → Desktop and OS: reads and controls
- Screen capture → Desktop and OS: captures screen
agent_v2.py - Web and weather → Web services: queries services
agent_v2.py - Voice agent → Arc Reactor GUI: updates state
README.md - Voice agent → Runtime configuration: loads settings
agent_v2.py - Wake listener → Runtime configuration: reads wake settings
wakeword.py - Console agent → Ollama: requests inference
agent_v1.py - Console agent → Runtime configuration: loads app allowlist
agent_v1.py - Console agent → User: accepts console input
README.md