Dashboard

AI Status: Idle
Twitch: Disconnected
Discord: Disconnected
VTube Software: Disconnected
OBS: Disconnected
Performance: N/A

Real-time Activity

Chat Messages

  • Waiting for chat messages...

AI Responses / Thoughts

Waiting for AI activity...
Voice Activity: Idle

Screen Perception (Preview)

Screen preview updates periodically based on Vision Model settings.

Configuration

Personality Studio

Helps guide the AI's tone and style.

Model Selection & Configuration

Large Language Model (LLM)

Specific model identifier for the selected provider/type.

Advanced LLM parameters (temperature, top_p, quantization, adapters) can be configured in Advanced Settings or via config file.

Vision Model

Select the model for screen perception tasks.
How often to capture the screen for analysis.

Capture region selection is planned for a future update.

Voice Settings

Text-to-Speech (TTS)

Enter the specific voice identifier or path to a local voice model file. Voice selection dropdown will be populated based on the chosen engine where possible.
1.0
1.0

Note: Emotion mapping from AI state to TTS prosody needs configuration (Not implemented in UI yet).

Speech-to-Text (STT)

Specify language code (like 'en', 'ja') or 'auto' if supported by the engine/model.
Helps detect when speech starts and stops to reduce processing and latency.

Integration Settings

Twitch

Discord

Vtubing Software

Default VTube Studio port is 8001. Warudo default is 19190.

OBS Studio

Requires obs-websocket plugin v5.x or later installed in OBS.

Alert Platforms (Webhooks)

Allows AI to react to follows, subs, etc. Requires setup in Streamlabs.
Allows AI to react to events. Requires setup in StreamElements.

API Keys & Authentication

Enter API keys required by selected models or integrations. Keys are intended to be stored securely using the OS credential manager (via `keytar` in the backend) and will not be displayed here after saving.

Required for sending messages. Generate via sites like twitchtokengenerator.com (ensure 'chat:read' and 'chat:edit' scopes are included). Use with caution and store securely.
Create a bot application in the Discord Developer Portal.

Note: Keys for external tools (Web Search, Weather) might be configured under the 'Actions' tab if required by the tool.

Memory System (Long-Term)

Determines how the AI remembers past interactions long-term.

Vector Database Settings (if enabled)

Path for local DB (will be created if it doesn't exist) or URL for remote.
Model used to create embeddings for memory storage/retrieval (local via Ollama/SentenceTransformers or API).
Max number of past interactions/facts to fetch for context (RAG).
Use Maximal Marginal Relevance (MMR) to diversify retrieved memories.
Helps condense information and manage database size. Requires an LLM call.

Action & Tool Configuration

Enable and configure actions the AI can perform beyond speaking. Available actions may depend on enabled integrations and plugins.

Available Actions:

(Requires OBS Integration)
(Requires Vtubing Software Integration)
(Requires configuration of sound files/commands)

More actions will appear here as they are developed or added via plugins. Configuration and permission settings for actions are planned.

Advanced Settings

Influences internal trade-offs between speed, resource usage, and response quality/complexity (e.g., model choices, queue priorities).
Controls the verbosity of logs shown in the 'Application Logs' section below.
Display intermediate steps like retrieved memory, chosen actions, or function calls in the AI Response view (if supported by the pipeline).
-1 for auto/max (uses all available VRAM), 0 for CPU only. Adjust based on your GPU VRAM. Requires GPU support compiled/installed.

More advanced settings (like LLM temperature, Top-P, RAG chunking, queue settings, specific model parameters) may be available via direct editing of the configuration file (e.g., `config.json` or `config.yaml`).

Application Logs

Application logs will appear here...