How-to guides

Recipes for specific tasks. Each guide assumes you've worked through Getting Started and at least skimmed Concepts.

Extending the framework

• Add a custom source - implement the Source protocol for a new device, file format, or transport.
• Add a custom output - push predictions to actuators, robots, or other processes.
• Add a custom widget - write a stateless function that draws ImGui commands from ctx.
• Add a custom model - wire extract / train / predict for any ML library.

Recording and post-processing

• Record and replay - capture sessions, read them back programmatically.
• Record good training data - cycle-style recording, how many cycles you actually need, verifying templates before training.
• Feature extraction cookbook - copy-paste @pipeline.extract snippets (RMS+MAV, bandpass+envelope, spectral, sliding RMS, onset detection, multi-stream fusion).
• Post-process predictions - FilterControl and myogestic.filters for output smoothing.
• Integrate the Virtual Hand - myogestic.interfaces.virtual_hand and the launcher pattern.

Operations

• Run headless (no GUI) - unattended recording and prediction; signal handling; protocol-driven scripts.