How vigneshwaran484/jarvis-linux works
Jarvis-Linux is a Linux voice assistant: a user wakes it, speaks a request, and the agent transcribes it, reasons through an Ollama ReAct loop, optionally invokes tools or memory, then speaks a response. Its runtime also updates a live HUD and logs errors. The README documents desktop, file, media, system, screenshot, and weather tools; they are grouped by role rather than listed individually. Source excerpts confirm key calls, while some tool details and integration wiring are documented only in the README.
Main entry points: agent_v2.py Voice agent · memory.py Memory manager · wakeword.py Wake detection · config.py Configuration
Components 19
Voice interaction
- Wake detection
wakeword.py - Speech recognition
agent_v2.py - Speech synthesis
agent_v2.py
Agent and tools
- Voice agent
agent_v2.py - ReAct tool loop
agent_v2.py - Desktop and system tools
agent_v2.py - File and capture tools
agent_v2.py - Web and weather tools
agent_v2.py
Memory
- Memory manager
memory.py - Conversation memory
memory.py - Semantic memory
memory.py - Embedding backend
memory.py
Runtime support
- Arc Reactor HUD
reactor.py - Waybar state file
reactor.py - Configuration
config.py - Rotating logger
jarvis_log.py
Other components
- User
- Local Ollama
- Edge TTS service
Connections 22
- User → Voice agent: speaks request
README.md - Voice agent → Wake detection: checks wake word
README.md - Wake detection → Speech recognition: recognizes speech
wakeword.py - Voice agent → Speech recognition: transcribes command
agent_v2.py - Voice agent → ReAct tool loop: runs goal
README.md - ReAct tool loop → Local Ollama: requests reasoning
agent_v2.py - ReAct tool loop → Desktop and system tools: dispatches tools
README.md - ReAct tool loop → File and capture tools: dispatches tools
README.md - ReAct tool loop → Web and weather tools: dispatches tools
README.md - Voice agent → Memory manager: uses memory
agent_v2.py - Memory manager → Conversation memory: records exchanges
memory.py - Memory manager → Semantic memory: stores and searches
memory.py - Semantic memory → Embedding backend: embeds facts
memory.py - Voice agent → Speech synthesis: speaks reply
README.md - Speech synthesis → Edge TTS service: synthesizes audio
agent_v2.py - Voice agent → Arc Reactor HUD: updates state
README.md - Arc Reactor HUD → Waybar state file: writes state
reactor.py - Voice agent → Configuration: reads settings
agent_v2.py - Wake detection → Configuration: reads wake settings
wakeword.py - Memory manager → Configuration: reads memory settings
memory.py - Voice agent → Rotating logger: logs activity
README.md - Memory manager → Rotating logger: logs memory events
memory.py