Overview of the local assistant stack—workers, orchestration, and how they fit together.

Codmir Local Assistant

This page summarizes the local assistant stack:

Wakeword Listener: detects “codmir” using offline ASR
Orchestrator: coordinates a session with screen capture, audio record, transcription, and optional desktop control
Screen Monitor: low-FPS screenshots and blue-corner overlay
Audio Recorder: records mic to WAV (16 kHz)
Transcriber: Vosk-based offline speech-to-text
Desktop Automation: controls the desktop via X11 tools
TTS Worker: optional local speech synthesis (espeak-ng)

Run All (Docker Compose)

File: docker/compose.codmir.yml

xhost +local:root   # X11 only
docker compose -f docker/compose.codmir.yml up --build -d

Desktop automation opens http://localhost:3000 when asked to “open our app”. Configure via DEFAULT_APP_URL.

Screen overlay indicates when capture is active.
All processing can run offline; no cloud TTS is required (documented alternative only).

This page summarizes the local assistant stack:

Wakeword Listener: detects “codmir” using offline ASR
Orchestrator: coordinates a session with screen capture, audio record, transcription, and optional desktop control
Screen Monitor: low-FPS screenshots and blue-corner overlay
Audio Recorder: records mic to WAV (16 kHz)
Transcriber: Vosk-based offline speech-to-text
Desktop Automation: controls the desktop via X11 tools
TTS Worker: optional local speech synthesis (espeak-ng)

File: docker/compose.codmir.yml

xhost +local:root   # X11 only
docker compose -f docker/compose.codmir.yml up --build -d

Desktop automation opens http://localhost:3000 when asked to “open our app”. Configure via DEFAULT_APP_URL.

Screen overlay indicates when capture is active.
All processing can run offline; no cloud TTS is required (documented alternative only).