How system-nebula/maya-unified works
Maya Unified combines a local, dashboard-operated voice assistant with optional platform APIs and music tools. The primary path is operator audio through speech recognition, the LLM agent, and speech synthesis, with the gateway and voice hub handling dashboard requests. Separate branches represent documented memory, music playback, and platform capabilities. Some branches are documented only at product level; dashed, uncited links mark relationships not verified in the sampled source.
Main entry points: agent.py Voice agent · hub.py Voice hub · dashboard Web dashboard · main.py Platform API
Components 20
Voice runtime
- Voice hub
services/voice/hub.py - Session control
services/voice/session_controller.py - Voice agent
packages/voice-runtime/agent.py - Speech recognition
packages/voice-runtime/stt.py - Language model
packages/voice-runtime/llm.py - Speech synthesis
packages/voice-runtime/tts.py
Dashboard access
- Web dashboard
apps/dashboard - Voice routes
apps/gateway/voice_routes.py
Memory and state
- Memory manager
packages/voice-runtime/memory/manager.py - Operator settings
services/settings/public.py - Postgres store
packages/maya-db/src/maya_db/connection.py
Music tools
- Queue command
services/cmd/executors/queue.py - Dashboard player
services/dashboard/player.py - Music ontology
services/music/ontology.py
Platform services
- Platform API
apps/maya-gateway/src/maya_gateway/main.py - Platform routes
apps/maya-gateway/src/maya_gateway/routes - Feed ingestion
apps/maya-ingest/src/maya_ingest/flows - Research service
apps/maya-gateway/src/maya_gateway/services/research_service.py - Image generation
packages/maya-image/src/maya_image/api.py
Other components
- Operator
Connections 21
- Operator → Web dashboard: uses
README.md - Web dashboard → Voice routes: requests voice
- Voice routes → Voice hub: calls
apps/gateway/voice_routes.py - Voice hub → Voice agent: delegates
services/voice/hub.py - Voice hub → Session control: coordinates
services/voice/hub.py - Operator → Speech recognition: provides audio
README.md - Speech recognition → Voice agent: transcribes for
README.md - Voice agent → Language model: requests response
README.md - Language model → Voice agent: returns text
README.md - Voice agent → Speech synthesis: synthesizes reply
README.md - Voice agent → Memory manager: uses memory
- Voice hub → Operator settings: loads settings
services/voice/hub.py - Operator settings → Postgres store: persists state
- Web dashboard → Queue command: submits queue command
- Queue command → Dashboard player: schedules resolution
services/cmd/executors/queue.py - Dashboard player → Music ontology: looks up music
services/dashboard/player.py - Operator → Platform API: uses platform APIs
README.md - Platform API → Platform routes: registers routes
apps/maya-gateway/src/maya_gateway/main.py - Platform routes → Research service: runs research
- Platform API → Image generation: exposes image API
apps/maya-gateway/src/maya_gateway/main.py - Operator → Feed ingestion: publishes feed sources