Neural Companion

Neural Companion is a local desktop AI companion for realtime chat, speech, avatars, visual replies, and addon-driven workflows. Windows is the original target; Linux support is being ported in this branch.

It is designed for users who want a configurable AI companion that can talk, listen, roleplay, use local or API models, drive avatars, and grow through addons.

What It Can Do

• Chat through local or API providers such as LM Studio, OpenAI, xAI/Grok, Claude, DeepSeek, Ollama, and addon providers.
• Speak through TTS backends such as Chatterbox, Gemini TTS Preview, PocketTTS, and addon backends.
• Drive avatars through MuseTalk, Scenic still-image packs, VSeeFace, VaM, or no-avatar mode.
• Use screen, webcam, clipboard, heart-rate, and visual-reply workflows.
• Save and reload chat contexts.
• Use Continuity Memory summaries and Long-Term Memory archive retrieval.
• Run Multi Persona Roleplay Companion, tutorials, presets, hotkeys, chat replay, and addon tools.
• Use spellchecking in typed chat and optional dependency repair for supported features.

Current Highlights

• Multi Persona Roleplay Companion: story setup, personas, narrator and character routing, a dedicated Play view, voice routing, visual prompt debugging, and story state tools.
• Scenic Avatar Engine: portable still-image avatar packs that map tags to images and can be previewed through the MuseTalk Preview window.
• Memory systems: per-chat Continuity Memory summaries and Long-Term Memory archive retrieval with optional embeddings.
• Local provider support: LM Studio and Ollama support for local chat model workflows.

Screenshots and Basic Workflow

Neural Companion starts as a desktop control surface for configuring the companion, choosing runtimes, starting the system, and watching chat/runtime status. The Linux screenshots below show the current runtime-backed UI.

The Host view is where most first-run setup happens. Choose the avatar engine, input mode, preset, LLM runtime, STT backend, TTS backend, and Visual Reply provider. Each runtime area has provider tabs, a small active-runtime selector, and a provider setup panel for model, URL, key, and generation settings.

The Chat Window contains the system console and chat view. Use it to verify that addons loaded, runtimes initialized, and replies are flowing. The bottom controls start and stop the companion, reset chat memory, pause or resume speech, and skip queued output.

The Addons area collects optional capabilities and guided walkthroughs. Addons can provide chat providers, voice bridges, sensory sources, avatar backends, story tools, tutorials, and workflow-specific controls without hardcoding every feature into the main window.

Visual Reply is the image response panel. When enabled with a supported image provider, generated or loaded images appear here, can be captioned, reused as style references, or cleared from the current visual reply history.

The MuseTalk view is the avatar preview surface. It keeps the preview, reset, freeze, and avatar-focus controls in one place so avatar testing does not need to be mixed into the chat or runtime setup panels.

The most basic manual flow is:

1. Start a chat provider such as LM Studio or Ollama, or configure an API provider.
2. Start Neural Companion and open the Host view.
3. Select None as Avatar Engine for the first test run.
4. Select an LLM runtime, an STT backend if you want microphone input, and a TTS backend if you want spoken replies.
5. Press Initialize System.
6. Use typed chat or push-to-talk and watch the Chat Window console for runtime status.

For release history, see CHANGELOG.md.

Requirements

Neural Companion currently requires:

• Windows, or a Linux environment with the porting notes below
• Python 3.11
• FFmpeg, either installed on PATH or provided by the bundled installer tools
• A local or API chat provider
• An NVIDIA CUDA GPU for MuseTalk avatar generation and playback

Python 3.11 is required. Python 3.12+ is not currently supported by the full runtime stack, and older Python versions may fail during dependency installation.

Useful external tools:

• LM Studio for local LLMs
• VSeeFace for VRM-style avatar output
• VaM plus the Neural Companion bridge/plugin for VaM output

Install

For most users, use the graphical installer:

INSTALL_NEURAL_COMPANION.bat

On Linux, use:

./INSTALL_NEURAL_COMPANION.sh

The installer should be run with Python 3.11 available on the system. If Python 3.11 is not your default Python, choose or provide the Python 3.11 executable when installing.

For the detailed public install guide, see:

• docs/install.md
• docs/linux.md
• docs/manual/installation.md

Advanced command-line install options are documented in the manual. They are intended for users who already know which runtime components they want to install.

Linux command-line install work is in progress. On Linux, use Python 3.11 directly and prefer the command-line installer:

python3.11 install_neural_companion.py --main --non-interactive

Install FFmpeg through your distribution package manager. The bundled FFmpeg download path is Windows-only.

Run

Start Neural Companion with:

run_neural_companion.bat

On Linux, start it with:

./run_neural_companion.sh

This is the recommended launch method because it uses the installed Neural Companion environment.

If you need to run the app manually from the project folder, use the installed environment explicitly:

.venv\Scripts\python.exe qt_app.py

Linux equivalent:

.venv/bin/python qt_app.py

Or activate the environment first:

.venv\Scripts\activate.bat
python qt_app.py

First Run

The simplest first run is to follow the tutorial displayed at first launch.

If you want to start manually:

1. Start LM Studio and load a chat model.
2. Start Neural Companion.
3. Select LM Studio as Chat Provider.
4. Select None as Avatar Engine.
5. Select a TTS backend.
6. Press Initialize System.
7. Use push-to-talk or typed input to verify chat and speech.

Once that works, enable MuseTalk, VSeeFace, VaM, visual replies, or sensory addons one at a time.

Voices

The public repo ships with two voice samples.

If you want Chatterbox or another backend to clone a reference voice, place your own .wav files under:

voices/

Only use voice files you have the right to use.

Avatar Packs

MuseTalk avatar packs belong in:

avatar_packs/<pack_id>/

Large avatar packs and frame caches are intentionally not stored in the main repository. Demo packs live in the separate NeuralCompanion-AvatarPacks repository.

Useful docs:

• docs/avatar_packs.md
• docs/release_asset_policy.md

Addons

Most runtime capabilities are implemented as addons under addons/.

The catalog below is generated from addon manifests so every bundled addon is listed. Each row is a dropdown; click the bold addon title to expand its description, UI surfaces, services, permissions, and screenshot link.

Generated from addons/*/addon.json. Addon count: 43.

Every addon below is in a GitHub dropdown. Click the row with the bold addon title to expand details.

Audio Addons

1 addon.

Spotify Sense - click to expand (UI tab, enabled)

Addon ID: nc.spotify_sense

Folder: addons/spotify_sense

Version: 0.1.0

Description: Optional Spotify Web API controls, current-track awareness, and safe music tools for NeuralCompanion.

UI surfaces:

• Spotify Sense; UI area: top_level; Connect Spotify, control playback safely, and expose optional music awareness tools.

Permissions: ui.tabs, storage.read, storage.write, events.publish, services.register

Avatar Addons

6 addons.

MuseTalk Avatar - click to expand (UI tab, enabled)

Addon ID: nc.musetalk_avatar

Folder: addons/musetalk_avatar

Version: 0.1.0

Description: MuseTalk avatar engine provider.

UI surfaces:

• MuseTalk; UI area: top_level; Designer UI: ui/musetalk_avatar.ui; MuseTalk avatar runtime and preview controls.

Services: avatar_provider_registry (musetalk)

Permissions: ui.tabs

MuseTalk Preprocess - click to expand (UI tab, enabled)

Addon ID: nc.musetalk_preprocess

Folder: addons/musetalk_preprocess

Version: 0.1.0

Description: First-party MuseTalk preprocess/debug tab provided through the addon framework.

UI surfaces:

• Preprocess; UI area: avatar_tools; Designer UI: ui/musetalk_preprocess.ui; First-party MuseTalk preprocessing and debug tools provided through the addon framework.

Permissions: ui.tabs, events.subscribe

No Avatar - click to expand (backend/provider, enabled)

Addon ID: nc.no_avatar

Folder: addons/no_avatar

Version: 0.1.0

Description: Audio-only avatar provider.

Screenshot: backend/provider addon; no dedicated tab screenshot is expected.

Backend/provider addon; no dedicated tab.

Services: avatar_provider_registry (none)

Scenic Avatar - click to expand (UI tab, enabled)

Addon ID: nc.scenic_avatar

Folder: addons/scenic_avatar

Version: 0.1.0

Description: Simple tag-to-image avatar engine using portable Scenic Packs.

UI surfaces:

• Scenic; UI area: top_level; Designer UI: ui/scenic_avatar.ui; Create portable Scenic Packs that map emotion tags to still images.

Services: avatar_provider_registry (scenic)

Permissions: ui.tabs

VaM Avatar - click to expand (UI tab, enabled)

Addon ID: nc.vam_avatar

Folder: addons/vam_avatar

Version: 0.1.0

Description: Virt-A-Mate avatar bridge provider.

UI surfaces:

• VaM; UI area: top_level; Designer UI: ui/vam_avatar.ui; Virt-A-Mate bridge and launch controls.

Services: avatar_provider_registry (vam)

Permissions: ui.tabs

VSeeFace Avatar - click to expand (UI tab, enabled)

Addon ID: nc.vseeface_avatar

Folder: addons/vseeface_avatar

Version: 0.1.0

Description: VSeeFace/VMC avatar engine provider.

UI surfaces:

• VSeeFace; UI area: top_level; Designer UI: ui/vseeface_avatar.ui; VSeeFace body pose and runtime controls.

Services: avatar_provider_registry (vseeface)

Permissions: ui.tabs

Chat Addons

12 addons.

Claude Chat Provider - click to expand (backend/provider, enabled)

Addon ID: nc.claude_provider

Folder: addons/claude_provider

Version: 0.1.0

Description: Anthropic Claude provider addon for NC's dynamic chat-provider registry.

Screenshot: backend/provider addon; no dedicated tab screenshot is expected.

Backend/provider addon; no dedicated tab.

Services: chat_provider_registry (claude)

Conversation Replay - click to expand (UI tab, enabled)

Addon ID: nc.chat_session_player

Folder: addons/chat_session_player

Version: 0.1.0

Description: Dedicated conversation replay and context loading tools.

UI surfaces:

• Conversation Replay; UI area: top_level; Designer UI: ui/chat_session_player.ui; Standalone conversation replay and context loading tools.

Permissions: ui.tabs

DeepSeek Chat Provider - click to expand (backend/provider, enabled)

Addon ID: nc.deepseek_provider

Folder: addons/deepseek_provider

Version: 0.1.0

Description: DeepSeek chat provider addon for NC's dynamic chat-provider registry.

Screenshot: backend/provider addon; no dedicated tab screenshot is expected.

Backend/provider addon; no dedicated tab.

Services: chat_provider_registry (deepseek)

Discord Voice Bridge - click to expand (UI tab, enabled)

Addon ID: nc.discord_voice_bridge

Folder: addons/discord_voice_bridge

Version: 0.1.0

Description: Discord voice-channel bridge for isolated NC voice bot turns.

UI surfaces:

• Discord Voice; UI area: top_level; Designer UI: ui/discord_voice_bridge.ui; Configure Discord voice bots, capture, playback, response filtering, and bridge diagnostics.

Permissions: ui.tabs

Document Memory - click to expand (UI tab, enabled)

Addon ID: nc.rag_context

Folder: addons/rag_context

Version: 0.1.0

Description: Optional chat memory from user-selected text/PDF files.

UI surfaces:

• Document Memory; UI area: host_settings; Designer UI: ui/rag_context.ui; Build and use searchable local text/PDF memory for chat sessions.

Permissions: storage.read, storage.write, ui.tabs

Identity Artifacts - click to expand (UI tab, enabled)

Addon ID: nc.identity_artifacts

Folder: addons/identity_artifacts

Version: 0.1.0

Description: Import, preserve, and inspect raw ReflectAndExportIdentity artifacts.

UI surfaces:

• Identity Artifacts; UI area: top_level; Import source-native identity artifacts and inspect their raw and structured views.

Permissions: storage.read, storage.write, ui.tabs

LM Studio Chat Provider - click to expand (backend/provider, enabled)

Addon ID: nc.chat_provider_lmstudio

Folder: addons/lmstudio_provider

Version: 0.1.0

Description: Local LM Studio chat provider addon for NC's dynamic chat-provider registry.

Screenshot: backend/provider addon; no dedicated tab screenshot is expected.

Backend/provider addon; no dedicated tab.

Services: chat_provider_registry (lmstudio)

Main Chat Remote - click to expand (UI tab, enabled)

Addon ID: nc.main_chat_remote

Folder: addons/main_chat_remote

Version: 0.1.0

Description: LAN phone bridge for the real NeuralCompanion main chat runtime.

UI surfaces:

• Main Chat Remote; UI area: top_level; Local bridge status and controls for the phone remote.

Services: service_registry

Permissions: ui.tabs, services.register, llm.read, tts.read, avatar.read

Multi Persona Roleplay - click to expand (UI tab, enabled)

Addon ID: nc.multi_persona_roleplay

Folder: addons/multi_persona_roleplay

Version: 0.2.0

Description: Run AlternativeReality story production with narrator-led AR, personas, voice routing, Visual Reply, AudioFX, memory, validation, repair, recovery, and story bundles.

UI surfaces:

• Roleplay; UI area: top_level; Designer UI: ui/roleplay.ui; Configure multi-persona roleplay, persona voices, and persona-aware Visual Reply prompts.

Permissions: ui.tabs, storage.read, storage.write, events.subscribe, events.publish, services.consume, services.register, llm.read, tts.read, avatar.read

Ollama Chat Provider - click to expand (backend/provider, enabled)

Addon ID: nc.chat_provider_ollama

Folder: addons/ollama_provider

Version: 0.1.0

Description: Local Ollama chat provider addon for NC's dynamic chat-provider registry.

Screenshot: backend/provider addon; no dedicated tab screenshot is expected.

Backend/provider addon; no dedicated tab.

Services: chat_provider_registry (ollama)

Permissions: events.subscribe

OpenAI Chat Provider - click to expand (backend/provider, enabled)

Addon ID: nc.chat_provider_openai

Folder: addons/openai_provider

Version: 0.1.0

Description: Hosted OpenAI chat provider addon for NC's dynamic chat-provider registry.

Screenshot: backend/provider addon; no dedicated tab screenshot is expected.

Backend/provider addon; no dedicated tab.

Services: chat_provider_registry (openai)

xAI / Grok Chat Provider - click to expand (backend/provider, enabled)

Addon ID: nc.chat_provider_xai

Folder: addons/xai_provider

Version: 0.1.0

Description: Hosted xAI / Grok chat provider addon for NC's dynamic chat-provider registry.

Screenshot: backend/provider addon; no dedicated tab screenshot is expected.

Backend/provider addon; no dedicated tab.

Services: chat_provider_registry (xai)

Global Addons

9 addons.

Chatterbox Multilingual TTS - click to expand (UI tab, enabled)

Addon ID: nc.chatterbox_multilingual_tts

Folder: addons/chatterbox_multilingual_tts

Version: 0.1.0

Description: Local Chatterbox Multilingual TTS backend exposed as a separate addon.

UI surfaces:

• Chatterbox Multilingual; UI area: tts_runtime; Designer UI: ui/chatterbox_tts.ui; Local Chatterbox Multilingual TTS settings.

Services: tts_backend_service (chatterbox_multilingual)

Permissions: services.register, ui.tabs

Chatterbox TTS - click to expand (UI tab, enabled)

Addon ID: nc.chatterbox_tts

Folder: addons/chatterbox_tts

Version: 0.1.0

Description: Built-in Chatterbox TTS backend exposed as an addon.

UI surfaces:

• Chatterbox; UI area: tts_runtime; Designer UI: ui/chatterbox_tts.ui; Local Chatterbox TTS settings.

Services: tts_backend_service (chatterbox)

Permissions: services.register, ui.tabs

Gemini TTS Preview - click to expand (UI tab, enabled)

Addon ID: nc.gemini_tts_preview

Folder: addons/gemini_tts_preview

Version: 0.1.0

Description: Gemini preview TTS backend addon for Neural Companion.

UI surfaces:

• Gemini TTS; UI area: tts_runtime; Designer UI: ui/gemini_tts_preview.ui; Gemini preview TTS backend settings.

Services: tts_backend_service (gemini_tts_preview)

Permissions: services.register, ui.tabs

Hotkeys - click to expand (UI tab, enabled)

Addon ID: nc.hotkeys

Folder: addons/hotkeys

Version: 0.1.0

Description: Configurable hotkeys for push-to-talk, control actions, and focused-window UI actions.

UI surfaces:

• Hotkeys; UI area: top_level; Designer UI: ui/hotkeys.ui; Configure push-to-talk and other available shortcuts.

Permissions: ui.tabs

No STT - click to expand (backend/provider, enabled)

Addon ID: nc.no_stt

Folder: addons/no_stt

Version: 0.1.0

Description: Disables microphone speech-to-text while keeping manually typed chat available.

Screenshot: backend/provider addon; no dedicated tab screenshot is expected.

Backend/provider addon; no dedicated tab.

Permissions: services.register

PocketTTS - click to expand (UI tab, enabled)

Addon ID: nc.pockettts

Folder: addons/pockettts

Version: 0.1.0

Description: Built-in PocketTTS backend exposed as an addon.

UI surfaces:

• PocketTTS; UI area: tts_runtime; Designer UI: ui/pockettts.ui; PocketTTS interpreter settings.

Services: tts_backend_service (pockettts)

Permissions: services.register, ui.tabs

PocketTTS Multilingual - click to expand (UI tab, enabled)

Addon ID: nc.pockettts_multilingual_tts

Folder: addons/pockettts_multilingual_tts

Version: 0.1.0

Description: PocketTTS multilingual backend exposed as a separate TTS addon.

UI surfaces:

• PocketTTS Multilingual; UI area: tts_runtime; Designer UI: ui/pockettts_multilingual_tts.ui; PocketTTS multilingual model settings.

Services: tts_backend_service (pockettts_multilingual)

Permissions: services.register, ui.tabs

Whisper English STT - click to expand (backend/provider, enabled)

Addon ID: nc.whisper_english_stt

Folder: addons/whisper_english_stt

Version: 0.1.0

Description: Current local faster-whisper STT backend optimized for English speech.

Screenshot: backend/provider addon; no dedicated tab screenshot is expected.

Backend/provider addon; no dedicated tab.

Permissions: services.register

Whisper Multilingual STT - click to expand (backend/provider, enabled)

Addon ID: nc.whisper_multilingual_stt

Folder: addons/whisper_multilingual_stt

Version: 0.1.0

Description: Local faster-whisper STT backend for auto-detected or non-English speech.

Screenshot: backend/provider addon; no dedicated tab screenshot is expected.

Backend/provider addon; no dedicated tab.

Permissions: services.register

Vision Addons

8 addons.

Clipboard Source - click to expand (UI tab, enabled)

Addon ID: nc.clipboard_source

Folder: addons/clipboard_source

Version: 0.1.0

Description: Clipboard-backed Vision source for manually or automatically attaching copied images to chat turns or the hidden loop.

UI surfaces:

• Source; UI area: vision_source; parent: clipboard; Designer UI: ui/clipboard_source.ui; Clipboard image source controls and status.

Services: sensory_registry (clipboard)

Permissions: ui.tabs

Clipboard Supervisor - click to expand (UI tab, enabled)

Addon ID: nc.clipboard_supervisor

Folder: addons/clipboard_supervisor

Version: 0.1.0

Description: Persona-driven clipboard image reactions for newly copied reference images.

UI surfaces:

• Supervisor; UI area: vision_source; parent: clipboard; Designer UI: ui/clipboard_supervisor.ui; Persona-driven clipboard-image reactions for newly copied images.

Services: sensory_prompt_contributor (clipboard)

Permissions: ui.tabs

Heart Rate Behavior - click to expand (UI tab, enabled)

Addon ID: nc.heart_rate_behavior

Folder: addons/heart_rate_behavior

Version: 0.1.0

Description: No description provided.

UI surfaces:

• Threshold Rules; UI area: vision_source; parent: heart_rate; Designer UI: ui/heart_rate_behavior.ui; Persona-driven behavior rules that attach to the heart_rate sensory source.

Services: sensory_prompt_contributor (heart_rate)

Permissions: ui.tabs

Mock Heart Rate - click to expand (UI tab, enabled)

Addon ID: nc.mock_heart_rate

Folder: addons/mock_heart_rate

Version: 0.1.0

Description: Floating mock BPM window plus a reusable heart-rate service and sensory provider for addon experiments.

UI surfaces:

• Source; UI area: vision_source; parent: heart_rate; Designer UI: ui/mock_heart_rate.ui; Floating heart-rate sensor window and source status.

Services: service_registry, sensory_registry (heart_rate)

Permissions: ui.tabs, events.publish, services.register

Screen Source - click to expand (UI tab, enabled)

Addon ID: nc.screen_source

Folder: addons/screen_source

Version: 0.1.0

Description: Screen-backed hidden Vision source for attaching screenshots as ambient sensory context.

UI surfaces:

• Capture; UI area: vision_source; parent: screen; Designer UI: ui/screen_source_capture.ui; Screen screenshot size and compression settings.

Services: sensory_registry (screen)

Permissions: ui.tabs

Screen Supervisor - click to expand (UI tab, enabled)

Addon ID: nc.screen_supervisor

Folder: addons/screen_supervisor

Version: 0.1.0

Description: Playful screen-based behavior rules that can interrupt when noteworthy on-screen content appears.

UI surfaces:

• Supervisor; UI area: vision_source; parent: screen; Designer UI: ui/screen_supervisor.ui; Persona-driven screen reactions for noteworthy on-screen content.

Services: sensory_prompt_contributor (screen)

Permissions: ui.tabs

Webcam Source - click to expand (backend/provider, enabled)

Addon ID: nc.webcam_source

Folder: addons/webcam_source

Version: 0.1.0

Description: Webcam-backed hidden Vision source for attaching webcam snapshots as ambient sensory context.

Screenshot: backend/provider addon; no dedicated tab screenshot is expected.

Backend/provider addon; no dedicated tab.

Services: sensory_registry (webcam)

Webcam Supervisor - click to expand (UI tab, enabled)

Addon ID: nc.webcam_supervisor

Folder: addons/webcam_supervisor

Version: 0.1.0

Description: Persona-driven webcam behavior rules that can react to posture, expression, and attention cues.

UI surfaces:

• Supervisor; UI area: vision_source; parent: webcam; Designer UI: ui/webcam_supervisor.ui; Persona-driven webcam reactions for noteworthy posture, expression, and attention cues.

Services: sensory_prompt_contributor (webcam)

Permissions: ui.tabs

Visuals Addons

7 addons.

AI Presence Mode - click to expand (UI tab, enabled)

Addon ID: nc.ai_presence_mode

Folder: addons/ai_presence_mode

Version: 0.1.0

Description: Configure the native fullscreen and floating AI Presence visualizer for thinking and spoken audio.

UI surfaces:

• AI Presence; UI area: top_level; Configure AI Presence fullscreen, floating window, visual styles, transparency, and audio sync.

Permissions: ui.tabs, storage.read, storage.write, events.publish

Audio Story Mode - click to expand (UI tab, enabled)

Addon ID: nc.audio_story_mode

Folder: addons/audio_story_mode

Version: 0.1.0

Description: Import story audio, transcribe it locally, and sync visual story images to playback.

UI surfaces:

• Audio Story Mode; UI area: top_level; Designer UI: ui/audio_story_mode.ui; Import story audio, transcribe it locally, and sync visual replies to playback.

Permissions: ui.tabs, storage.read, storage.write

Companion Orb Overlay - click to expand (UI tab, enabled)

Addon ID: nc.companion_orb_overlay

Folder: addons/companion_orb_overlay

Version: 0.1.0

Description: Configure and run the Companion Orb Overlay from its own addon tab.

UI surfaces:

• Companion Orb; UI area: top_level; Configure the Companion Orb Overlay, movement, particles, voice sync, sensory target, and hotkeys.

Services: visual_overlay (companion_orb_overlay)

Permissions: ui.tabs, storage.read, storage.write, services.register, events.subscribe

Neural Face Presence - click to expand (UI tab, enabled)

Addon ID: nc.neural_face_presence

Folder: addons/neural_face_presence

Version: 0.1.0

Description: Configure the Neural Face Presence wireframe face renderer as its own addon tab.

UI surfaces:

• Neural Face; UI area: top_level; Configure Neural Face Presence topology, lip sync, blink, gaze, glow, and face animation.

Permissions: ui.tabs, storage.read, storage.write

Ua Companion Orb Overlay - click to expand (backend/provider, enabled)

Addon ID: nc.ua_companion_orb_overlay

Folder: addons/ua_companion_orb_overlay

Version: 0.1.0

Description: Streams MuseTalk grayscale face masks to the Unreal Companion Orb overlay.

Screenshot: backend/provider addon; no dedicated tab screenshot is expected.

Backend/provider addon; no dedicated tab.

Permissions: services.register

Visual Reply - click to expand (UI tab, enabled)

Addon ID: nc.visual_reply

Folder: addons/visual_reply

Version: 0.1.0

Description: Addon-owned Visuals host tab for visual reply runtime settings.

UI surfaces:

• Visuals; UI area: visual_reply_runtime; Designer UI: ui/visual_reply_core.ui; Visual reply runtime settings and future visual addons.

Permissions: ui.tabs

Visual Story Settings - click to expand (UI tab, enabled)

Addon ID: nc.visual_story_settings

Folder: addons/visual_story_settings

Version: 0.1.0

Description: Controls story-mode visual reply generation, continuity, styles, and master prompt guards.

UI surfaces:

• Story Visuals; UI area: host_settings; Designer UI: ui/visual_story_settings.ui; Story-mode visual reply settings.

Permissions: ui.tabs

Useful docs:

• docs/addon_quickstart.md
• docs/chat_provider_addons.md
• docs/vision_source_addons.md
• docs/visual_reply_addons.md
• docs/addon_state_and_presets.md

More Documentation

See the Neural Companion Manual for installation, first-run, avatar, TTS, PocketTTS, MuseTalk, addon, and troubleshooting guidance.

For development and repository details, see:

• CONTRIBUTING.md
• docs/release_checklist.md
• docs/third_party_and_assets.md
• docs/troubleshooting.md
• docs/known_limitations.md

Licensing

Neural Companion is released under the MIT License. See LICENSE.

Bundled third-party components may carry their own licenses. MuseTalk is included under its upstream MIT license in MuseTalk/LICENSE.

You are responsible for complying with the terms of any external model, provider, voice, avatar, or generated asset you use with the app.

Current Limitations

• Neural Companion is Windows-first; Linux support is being ported through the shell launchers, Linux installer paths, and docs/linux.md setup notes.
• MuseTalk requires an NVIDIA CUDA GPU.
• Some integrations require external applications or plugins.
• Public demo assets are intentionally not bundled in the main repo.