v0.10.0

What's New

Features

• Visual workflow guidance system - Flashing highlights guide users through the recording → training → online workflow
  • Highlights Training tab after 2+ recordings
  • Auto-selects newly created datasets
  • Auto-loads trained models in Online protocol
• CLI entry point - Run MyoGestic directly with myogestic command after installation
• Package installable - Proper pip/uv installation support with package = true

Fixes

• Fixed asset path resolution to work from any working directory
• Hide default recording UI when no visual interface is selected

Security

• CVE-2025-3730 (Medium): Fixed PyTorch Improper Resource Shutdown vulnerability
• CVE-2025-2953 (Low): Fixed PyTorch local Denial of Service vulnerability
• Upgraded PyTorch from 2.6.0 to 2.10.0
• Switched CUDA index from cu124 to cu126

Dependencies

• Added vispy>=0.16.0
• Updated torch>=2.8.0, torchvision>=0.23.0, torchaudio>=2.8.0

v0.9.0

[0.9.0]

Documentation overhaul, Sphinx compatibility, and multi-VI support.

Added

• Multiple active Visual Interfaces — Run several VIs simultaneously with shared task selector and unified recording controls.
• Ground truth source selector for multi-VI dataset creation.
• Sphinx-Gallery tutorial suite covering models, features, filters, output systems, and visual interface integration.
• Full API reference pages with autosummary for Config, Models, and Visual Interface modules.
• Default method stubs in RecordingInterfaceTemplate for easier VI development.

Changed

• Refactored visual interface system architecture to support multiple active VIs.
• Re-enabled autosummary_generate by fixing PySide6 mock metaclass compatibility.
• Wrapped catboost.get_gpu_device_count to handle mocked imports during docs build.
• Rewrote all example files with Sphinx :class:, :meth:, and :attr: cross-references.

v0.8.0

What's New

• Add Ctrl+C signal handling for graceful shutdown
• Improve main window UI layout and sizing
• Add Default Recording Interface for recording without visual interface
• Update visual interface UIs
• Minor GUI improvements and fixes
• Update dependencies
• Use biosignal-device-interface from PyPI (>=0.2.4)

v0.7.0 - UI/UX Improvements & macOS Support

Overview

This release focuses on improving the user experience with better UI feedback and full macOS compatibility for the Virtual Hand Interface.

✨ New Features

Improved User Interface

• Logging Tab - Moved logging to a separate tab, freeing up vertical screen space
• Tooltips - Added helpful tooltips throughout the UI explaining button functions and workflow steps
• Status Feedback - Status bar now shows messages for device connection and streaming actions
• Visual Hierarchy - Color-coded buttons make it clear which actions are available (green for Connect, blue for Stream)
• Plot Placeholder - EMG plot area now shows an informative placeholder when no device is connected

macOS Support

• Virtual Hand Interface - Now works out of the box on macOS
• Automatic executable permission handling
• Automatic quarantine attribute removal

🔧 Changes

• Platform-specific dependency overrides for torch and vispy on macOS
• Updated Biosignal-Device-Interface dependency with UI improvements

Full Changelog: v0.6.0...v0.7.0

v0.6.0 - Virtual Cursor Interface

Overview

This release adds a new virtual cursor interface for foot movement control.

✨ New Features

• Virtual Cursor Interface - New interface for controlling cursor movements, designed for foot movement applications

👥 Contributors

• @RaulSimpetru - Headless training implementation
• @wizzardkyd96 made their first contribution

Full Changelog: v0.5.2...v0.6.0

v0.5.2 - Headless Training

Overview

This release enables training without requiring a visual interface to be open.

🔧 Changes

• Headless Training - Now possible to train models without having a visual interface open

Full Changelog: v0.5.1...v0.5.2

v0.5.1 - Dependency Updates

Overview

This release updates dependencies and simplifies package configurations.

🔧 Changes

• Updated dependencies and sources in lockfile and config
• Replaced myoverse Git source with versioned PyPI source (>=1.1.2)
• Simplified torch and torchvision specifications by removing platform-specific markers and redundant configurations

Full Changelog: v0.5.0...v0.5.1

v0.5.0 - Virtual Hand Interface Enhancements

Overview

Enhanced Virtual Hand Interface integration and improved user experience.

✨ New Features

• Updated UI and task options for Virtual Hand Interface

🔧 Changes

• Renamed gesture labels for clarity and consistency
• Updated task labels for clarity in recording UI

👥 New Contributors

• @Mario200212 made their first contribution

Full Changelog: v0.4.0...v0.5.0

v0.4.0 - Cross-Platform Compatibility

Overview

Enhanced user interface and improved cross-platform compatibility.

✨ New Features

• Changelog file to track project changes
• Virtual Hand Interface integration with updated UI and task options

🔧 Changes

• Renamed gesture labels for clarity and consistency
• Updated task labels for clarity in recording UI
• Adjusted dataloader parameters for cross-platform compatibility
• Adjusted multiprocessing settings for cross-platform compatibility
• Updated MyoVerse to latest version with fixes
• Fixed import paths for CONFIG_REGISTRY

🗑️ Removed

• Redundant parameters and dead code in dataset module

Full Changelog: v0.1.0...v0.4.0

v0.1.0 (Paper Version)

Fix wrong link in README.md