# gaurav-xdev/voxy-commercial architecture

> Architecture diagram of the GitHub repository gaurav-xdev/voxy-commercial, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-29). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/gaurav-xdev/voxy-commercial
- Repository: https://github.com/gaurav-xdev/voxy-commercial

## Overview

VOXY is a voice-first autonomous assistant. Its main documented path takes voice or text input through speech recognition, conversation and decision-making, planning and task execution, then memory updates and spoken output. The sampled voice runtime directly connects audio processing with brain turn handling and streaming events; integration pipeline comments document the broader stages. Several major capabilities are visible in the README and tree but their wiring was not sampled, so those links are omitted.

Main entry points: [`crates/voice_runtime/src/engine.rs`](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/voice_runtime/src/engine.rs) (Voice Runtime), [`crates/brain/src/engine.rs`](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/brain/src/engine.rs) (Brain Turn Engine), [`crates/integration/src/pipeline.rs`](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/integration/src/pipeline.rs) (Unified Pipeline), [`apps/daemon/src/main.rs`](https://github.com/gaurav-xdev/voxy-commercial/blob/master/apps/daemon/src/main.rs) (Daemon)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_apps["Applications"]
  node_daemon["Daemon<br/>[main.rs]"]
  node_overlay["Desktop Overlay<br/>[main.rs]"]
end

subgraph group_voice["Voice Interaction"]
  node_voice_runtime["Voice Runtime<br/>[engine.rs]"]
  node_voice_pipeline["Voice Pipeline<br/>[pipeline.rs]"]
  node_audio["Audio Processing<br/>[lib.rs]"]
  node_stt["Streaming STT<br/>[streaming_stt.rs]"]
  node_voice_output["Voice Output<br/>[pipeline.rs]"]
end

subgraph group_reasoning["Reasoning And Action"]
  node_brain["Brain Turn Engine<br/>[engine.rs]"]
  node_cognition["Cognition<br/>[lib.rs]"]
  node_companion["Companion<br/>[engine.rs]"]
  node_human_dynamics["Human Dynamics<br/>[engine.rs]"]
  node_integration_pipeline["Unified Pipeline<br/>[pipeline.rs]"]
  node_goal_engine["Goal Engine<br/>[goal_engine_v2.rs]"]
  node_planner["Task Planner<br/>[lib.rs]"]
  node_orchestrator["Task Orchestrator<br/>[pipeline.rs]"]
  node_automation["Automation<br/>[lib.rs]"]
end

subgraph group_state["Context And State"]
  node_context["Context Fusion<br/>[manager.rs]"]
  node_memory["Long-Term Memory<br/>[lib.rs]"]
  node_memory_store[("SQLite Memory Store<br/>[sqlite_engine.rs]")]
end

subgraph group_platform["Platform And Services"]
  node_api["API Server<br/>[router.rs]"]
  node_windows["Windows Platform<br/>[platform.rs]"]
  node_model_services["Model Providers"]
end

node_user(("User"))

node_user -->|"starts interaction"| node_daemon
node_daemon -->|"runs voice runtime"| node_voice_runtime
node_user -->|"uses desktop UI"| node_overlay
node_voice_runtime -->|"initializes and processes"| node_voice_pipeline
node_voice_runtime -->|"submits recognized text"| node_brain
node_voice_runtime -->|"submits audio frames"| node_audio
node_voice_pipeline -->|"captures and processes"| node_audio
node_voice_pipeline -->|"transcribes speech"| node_stt
node_voice_pipeline -->|"streams speech chunks"| node_voice_output
node_brain -->|"collects context"| node_context
node_brain -->|"updates companion"| node_companion
node_brain -->|"updates dynamics"| node_human_dynamics
node_brain -->|"processes cognition"| node_cognition
node_integration_pipeline -->|"coordinates decisions"| node_goal_engine
node_integration_pipeline -->|"coordinates planning"| node_planner
node_integration_pipeline -->|"coordinates execution"| node_orchestrator
node_orchestrator -->|"executes automation"| node_automation
node_integration_pipeline -->|"updates memory"| node_memory
node_memory -->|"persists and retrieves"| node_memory_store
node_daemon -->|"serves API"| node_api
node_voice_runtime -.->|"uses configured engines"| node_model_services
node_daemon -.->|"uses platform services"| node_windows

click node_daemon "https://github.com/gaurav-xdev/voxy-commercial/blob/master/apps/daemon/src/main.rs"
click node_overlay "https://github.com/gaurav-xdev/voxy-commercial/blob/master/apps/overlay/src/main.rs"
click node_voice_runtime "https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/voice_runtime/src/engine.rs"
click node_voice_pipeline "https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/voice/src/pipeline.rs"
click node_audio "https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/audio/src/lib.rs"
click node_stt "https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/audio/src/streaming_stt.rs"
click node_voice_output "https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/voice/src/pipeline.rs"
click node_brain "https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/brain/src/engine.rs"
click node_cognition "https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/cognition/src/lib.rs"
click node_companion "https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/companion/src/engine.rs"
click node_human_dynamics "https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/human_dynamics/src/engine.rs"
click node_integration_pipeline "https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/integration/src/pipeline.rs"
click node_goal_engine "https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/cognitive_orchestrator/src/goal_engine_v2.rs"
click node_planner "https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/planner/src/lib.rs"
click node_orchestrator "https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/orchestrator/src/pipeline.rs"
click node_automation "https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/automation/src/lib.rs"
click node_context "https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/context/src/manager.rs"
click node_memory "https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/memory/src/lib.rs"
click node_memory_store "https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/memory/src/sqlite_engine.rs"
click node_api "https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/api_server/src/router.rs"
click node_windows "https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/platform_windows/src/platform.rs"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_daemon,node_overlay,node_user toneBlue
class node_voice_runtime,node_voice_pipeline,node_audio,node_stt,node_voice_output toneAmber
class node_brain,node_cognition,node_companion,node_human_dynamics,node_integration_pipeline,node_goal_engine,node_planner,node_orchestrator,node_automation toneMint
class node_context,node_memory,node_memory_store toneRose
class node_api,node_windows,node_model_services toneIndigo
```

## Components

### Applications

- [Daemon](https://github.com/gaurav-xdev/voxy-commercial/blob/master/apps/daemon/src/main.rs): `apps/daemon/src/main.rs`
- [Desktop Overlay](https://github.com/gaurav-xdev/voxy-commercial/blob/master/apps/overlay/src/main.rs): `apps/overlay/src/main.rs`

### Voice Interaction

- [Voice Runtime](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/voice_runtime/src/engine.rs): `crates/voice_runtime/src/engine.rs`
- [Voice Pipeline](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/voice/src/pipeline.rs): `crates/voice/src/pipeline.rs`
- [Audio Processing](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/audio/src/lib.rs): `crates/audio/src/lib.rs`
- [Streaming STT](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/audio/src/streaming_stt.rs): `crates/audio/src/streaming_stt.rs`
- [Voice Output](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/voice/src/pipeline.rs): `crates/voice/src/pipeline.rs`

### Reasoning And Action

- [Brain Turn Engine](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/brain/src/engine.rs): `crates/brain/src/engine.rs`
- [Cognition](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/cognition/src/lib.rs): `crates/cognition/src/lib.rs`
- [Companion](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/companion/src/engine.rs): `crates/companion/src/engine.rs`
- [Human Dynamics](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/human_dynamics/src/engine.rs): `crates/human_dynamics/src/engine.rs`
- [Unified Pipeline](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/integration/src/pipeline.rs): `crates/integration/src/pipeline.rs`
- [Goal Engine](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/cognitive_orchestrator/src/goal_engine_v2.rs): `crates/cognitive_orchestrator/src/goal_engine_v2.rs`
- [Task Planner](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/planner/src/lib.rs): `crates/planner/src/lib.rs`
- [Task Orchestrator](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/orchestrator/src/pipeline.rs): `crates/orchestrator/src/pipeline.rs`
- [Automation](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/automation/src/lib.rs): `crates/automation/src/lib.rs`

### Context And State

- [Context Fusion](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/context/src/manager.rs): `crates/context/src/manager.rs`
- [Long-Term Memory](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/memory/src/lib.rs): `crates/memory/src/lib.rs`
- [SQLite Memory Store](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/memory/src/sqlite_engine.rs): `crates/memory/src/sqlite_engine.rs`

### Platform And Services

- [API Server](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/api_server/src/router.rs): `crates/api_server/src/router.rs`
- [Windows Platform](https://github.com/gaurav-xdev/voxy-commercial/blob/master/crates/platform_windows/src/platform.rs): `crates/platform_windows/src/platform.rs`
- **Model Providers**

### Other components

- **User**

## Connections

- User → Daemon: starts interaction
- Daemon → Voice Runtime: runs voice runtime
- User → Desktop Overlay: uses desktop UI
- Voice Runtime → Voice Pipeline: initializes and processes
- Voice Runtime → Brain Turn Engine: submits recognized text
- Voice Runtime → Audio Processing: submits audio frames
- Voice Pipeline → Audio Processing: captures and processes
- Voice Pipeline → Streaming STT: transcribes speech
- Voice Pipeline → Voice Output: streams speech chunks
- Brain Turn Engine → Context Fusion: collects context
- Brain Turn Engine → Companion: updates companion
- Brain Turn Engine → Human Dynamics: updates dynamics
- Brain Turn Engine → Cognition: processes cognition
- Unified Pipeline → Goal Engine: coordinates decisions
- Unified Pipeline → Task Planner: coordinates planning
- Unified Pipeline → Task Orchestrator: coordinates execution
- Task Orchestrator → Automation: executes automation
- Unified Pipeline → Long-Term Memory: updates memory
- Long-Term Memory → SQLite Memory Store: persists and retrieves
- Daemon → API Server: serves API
- Voice Runtime → Model Providers: uses configured engines
- Daemon → Windows Platform: uses platform services
