How lara-srl/xiaozhi-openclaw works
XiaoZhi is ESP32 voice-chatbot firmware: a user speaks or invokes device controls, audio is captured and processed, and a selected network protocol exchanges the interaction with an AI service; replies are played and shown on-device. Application coordinates startup and device state, while board implementations adapt the firmware to many supported hardware designs. The README also documents wake-word detection, MCP control, displays, assets, power management, and multiple connectivity options. Several subsystems are documented but their full implementation was not sampled, so those relationships are cited to the README rather than inferred from filenames.
Main entry points: application.cc Application · audio_service.cc Audio service · board.cc Board adapter · protocol.cc Protocol interface
Components 20
Runtime coordination
- Application
main/application.cc - Device state
main/device_state_machine.cc - Settings
main/settings.cc
Voice pipeline
- Audio service
main/audio/audio_service.cc - Audio codec
main/audio/audio_codec.cc - Wake words
main/audio/wake_words - Audio processing
main/audio/processors - OGG demuxer
main/audio/demuxer/ogg_demuxer.cc
Network and control
- Protocol interface
main/protocols/protocol.cc - WebSocket protocol
main/protocols/websocket_protocol.cc - MQTT protocol
main/protocols/mqtt_protocol.cc - MCP server
main/mcp_server.cc
Hardware and interface
- Board adapter
main/boards/common/board.cc - Display
main/display/display.cc - Custom assets
main/assets.cc - Camera
main/boards/common/esp32_camera.cc - LED control
main/led/led.h - Power management
main/boards/common/power_save_timer.cc
Other components
- User
- AI service
Connections 22
- User → Application: starts interaction
README.md - Application → Board adapter: gets hardware
main/application.cc - Application → Device state: transitions state
main/application.cc - Application → Audio service: initializes audio
main/application.cc - Application → Display: sets up UI
main/application.cc - Audio service → Audio codec: starts codec
main/audio/audio_service.cc - Audio service → Wake words: initializes detection
main/audio/audio_service.cc - Audio service → Audio processing: initializes processor
main/audio/audio_service.cc - Audio service → OGG demuxer: uses for playback
- Application → Protocol interface: initializes protocol
main/application.cc - Protocol interface → WebSocket protocol: selects transport
README.md - Protocol interface → MQTT protocol: selects transport
README.md - WebSocket protocol → AI service: exchanges chat
README.md - MQTT protocol → AI service: exchanges chat
README.md - Application → MCP server: supports device control
README.md - MCP server → Board adapter: invokes device actions
README.md - Application → Settings: uses configuration
- Board adapter → Camera: provides camera
README.md - Board adapter → LED control: provides LED
README.md - Board adapter → Power management: manages power
README.md - Display → Custom assets: shows custom assets
README.md - AI service → User: returns voice reply
README.md