# open-llm-vtuber/open-llm-vtuber

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/open-llm-vtuber-open-llm-vtuber).**

5,946 stars · 779 forks · Python · other

## Links

- GitHub: https://github.com/Open-LLM-VTuber/Open-LLM-VTuber
- Homepage: https://open-llm-vtuber.github.io/
- awesome-repositories: https://awesome-repositories.com/repository/open-llm-vtuber-open-llm-vtuber.md

## Topics

`ai` `ai-companion` `ai-vtuber` `ai-waifu` `chatbots` `live2d` `live2d-web` `llm` `neuro-sama` `ollama`

## Tags

### Artificial Intelligence & ML

- [AI Desktop Companions](https://awesome-repositories.com/f/artificial-intelligence-ml/desktop-ai-clients/ai-desktop-companions.md) — Ships a fully local AI companion with a Live2D avatar, voice interaction, and offline processing. ([source](https://cdn.jsdelivr.net/gh/open-llm-vtuber/open-llm-vtuber@main/README.md))
- [Realtime Voice Conversation Facilitators](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/conversational-voice-interaction/voice-agents/realtime-voice-conversation-facilitators.md) — Enables spoken dialogue with an AI companion that listens, responds, and can be interrupted mid-speech. ([source](https://open-llm-vtuber.github.io/docs/category/%E5%BF%AB%E9%80%9F%E4%B8%8A%E6%89%8B))
- [AI Backend Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-backend-integrations.md) — Connects to multiple LLM, speech, and TTS backends through a modular configuration interface. ([source](https://cdn.jsdelivr.net/gh/open-llm-vtuber/open-llm-vtuber@main/README.md))
- [Conversational Voice AI](https://awesome-repositories.com/f/artificial-intelligence-ml/conversational-voice-ai.md) — Engages in real-time spoken conversations with an AI character using speech recognition and synthesis. ([source](https://cdn.jsdelivr.net/gh/open-llm-vtuber/open-llm-vtuber@main/README.md))
- [AI Companion Customizers](https://awesome-repositories.com/f/artificial-intelligence-ml/custom-ai-models/ai-companion-customizers.md) — Enables importing custom Live2D models, editing prompts, and cloning voices to define a unique companion. ([source](https://open-llm-vtuber.github.io/docs/intro))
- [Environmental Perception Captures](https://awesome-repositories.com/f/artificial-intelligence-ml/deep-learning-image-processors/perception-visualizations/environmental-perception-captures.md) — Captures camera feed, screen recordings, or screenshots so the AI can perceive the user's environment and display content. ([source](https://cdn.jsdelivr.net/gh/open-llm-vtuber/open-llm-vtuber@main/README.md))
- [Companion Appearance and Persona Customizers](https://awesome-repositories.com/f/artificial-intelligence-ml/desktop-ai-clients/ai-desktop-companions/companion-appearance-and-persona-customizers.md) — Provides tools to import Live2D models, modify prompts, and clone voices for companion personalization. ([source](https://cdn.jsdelivr.net/gh/open-llm-vtuber/open-llm-vtuber@main/README.md))
- [Companion Customizers](https://awesome-repositories.com/f/artificial-intelligence-ml/desktop-ai-clients/ai-desktop-companions/companion-customizers.md) — Allows defining AI character through prompts, Live2D models, and voice cloning for unique companions. ([source](https://open-llm-vtuber.github.io/docs/intro))
- [OpenAI-Compatible Backend Configurators](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/inference-optimization-and-tuning/large-language-model-configurations/openai-compatible-backend-configurators.md) — Connects to any OpenAI-compatible LLM backend, including local runners and cloud APIs. ([source](https://open-llm-vtuber.github.io/docs/quick-start))
- [Local LLM Configurations](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/local-and-on-device-inference/local-llm-configurations.md) — Connects to locally hosted language models via Ollama or LM Studio for offline inference. ([source](https://open-llm-vtuber.github.io/docs/faq))
- [Multi-Modal AI Toolkits](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-modal-ai-toolkits.md) — Connects diverse AI backends for language, vision, and speech through a unified interface with browser control.
- [Companion Persona Customizers](https://awesome-repositories.com/f/artificial-intelligence-ml/persistent-ai-companions/companion-persona-customizers.md) — Provides tools to define character appearance, voice, and personality through models, prompts, and cloning. ([source](https://cdn.jsdelivr.net/gh/open-llm-vtuber/open-llm-vtuber@main/README.md))
- [Real-Time Conversational AI Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/real-time-conversational-ai-frameworks.md) — Enables real-time spoken dialogue with a Live2D avatar using low-latency voice interaction.
- [Visual Input Captures](https://awesome-repositories.com/f/artificial-intelligence-ml/visual-input-captures.md) — Captures camera feed or screen content so the AI can see the user and their environment. ([source](https://open-llm-vtuber.github.io/docs/intro))
- [Character Appearance and Voice Customizers](https://awesome-repositories.com/f/artificial-intelligence-ml/voice-assistants/voice-personalization/character-appearance-and-voice-customizers.md) — Provides tools to import Live2D models, modify prompts, and clone voices for companion personalization. ([source](https://open-llm-vtuber.github.io/docs/intro))
- [Voice-Enabled Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/voice-enabled-agents.md) — Provides a fully local AI companion with speech input, on-device LLM responses, and a Live2D avatar.
- [Long-term Memory Stores](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/memory-management-systems/long-term-memory-stores.md) — Stores conversation history and uses a memory system for recalling past interactions across sessions. ([source](https://open-llm-vtuber.github.io/docs/intro))
- [External Memory Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/memory-management-systems/long-term-memory-stores/external-memory-integrations.md) — Integrates with Letta (MemGPT) to store and recall conversation history across sessions. ([source](https://open-llm-vtuber.github.io/docs/quick-start))
- [Group Chat Routing](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-collaboration-protocols/group-chat-routing.md) — Coordinates multiple AI characters to participate simultaneously in a single conversation.
- [Multi-Agent Session Facilitators](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/conversational-voice-interaction/conversational-ai-infrastructure/multi-agent-session-facilitators.md) — Orchestrates multiple AI characters to participate in the same conversation simultaneously. ([source](https://open-llm-vtuber.github.io/docs/intro))
- [Speech Interruption Handlers](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/conversational-voice-interaction/voice-agents/speech-interruption-handlers.md) — Allows the user to speak over the AI without the AI hearing its own output, enabling natural turn-taking. ([source](https://open-llm-vtuber.github.io/docs/intro))
- [Live Camera and Screen Perception](https://awesome-repositories.com/f/artificial-intelligence-ml/deep-learning-image-processors/perception-visualizations/live-camera-and-screen-perception.md) — Captures and interprets live camera feed or screen content so the AI can see the user and environment.
- [External Memory Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/external-memory-integrations.md) — Retains conversation history and long-term context by integrating with external memory systems like Letta.
- [Avatar Tap Interaction Configurators](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-pipelines/text-to-image-generators/image-inpainting/image-to-image-diffusion-toolkits/interaction-tap-detection/avatar-tap-interaction-configurators.md) — Allows configuration of click-triggered motion sequences on different avatar body parts. ([source](https://open-llm-vtuber.github.io/docs/user-guide/live2d))
- [Persistent Chat Histories](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/ai-memory-systems/persistent-chat-histories.md) — Saves conversation logs so users can resume previous interactions without losing context. ([source](https://cdn.jsdelivr.net/gh/open-llm-vtuber/open-llm-vtuber@main/README.md))
- [Tool Invocation Handlers](https://awesome-repositories.com/f/artificial-intelligence-ml/mcp-tool-connectors/tool-invocation-handlers.md) — Provides MCP-based tool invocation for web searches and time queries with status feedback. ([source](https://open-llm-vtuber.github.io/docs/intro))

### Business & Productivity Software

- [Interactive Desktop Companions](https://awesome-repositories.com/f/business-productivity-software/desktop-personalization-tools/interactive-desktop-companions.md) — Launches a transparent, always-on-top window that stays on the desktop as a virtual pet-like companion. ([source](https://open-llm-vtuber.github.io/docs/faq))

### Data & Databases

- [Local AI Operations](https://awesome-repositories.com/f/data-databases/offline-caching/offline-operation-modes/local-ai-operations.md) — Operates all core AI functions—voice, vision, and language—entirely offline using local models. ([source](https://open-llm-vtuber.github.io/docs/intro))
- [Conversation Memory Retrieval](https://awesome-repositories.com/f/data-databases/indexing-and-search/recall-optimization/conversation-memory-retrieval.md) — Stores chat history and long-term memories so the AI recalls previous interactions across sessions. ([source](https://open-llm-vtuber.github.io/docs/intro))

### Graphics & Multimedia

- [Live2D Avatar Renderers](https://awesome-repositories.com/f/graphics-multimedia/graphics-engines-rendering/webgl-gpu-rendering/live2d-avatar-renderers.md) — Renders and animates Live2D avatars in real-time using WebGL with expressions and click interactions.
- [Facial Expression Modulators](https://awesome-repositories.com/f/graphics-multimedia/audio-music/audio-processing/audio-emotion-classifiers/emotional-modulation/facial-expression-modulators.md) — Links the AI's emotional state to specific Live2D facial expressions for appropriate visual reactions. ([source](https://open-llm-vtuber.github.io/docs/user-guide/live2d))

### Networking & Communication

- [Real-Time Interaction Engines](https://awesome-repositories.com/f/networking-communication/websocket-clients/real-time-interaction-engines.md) — Enables low-latency bidirectional data streaming between the AI backend and the avatar interface.
- [Web-Based Interfaces](https://awesome-repositories.com/f/networking-communication/communication-platforms-services/communication-platforms/real-time-collaboration-suites/irc-clients/web-access-provisioning/web-based-interfaces.md) — Provides a web-based interface accessible from any device on the same network. ([source](https://open-llm-vtuber.github.io/docs/faq))

### Programming Languages & Runtimes

- [Browser-Based Runtimes](https://awesome-repositories.com/f/programming-languages-runtimes/browser-based-runtimes.md) — Operates the entire application within a web browser for cross-platform access and remote connectivity.

### Security & Cryptography

- [Multi-Character Conversations](https://awesome-repositories.com/f/security-cryptography/account-management/hierarchical-grouping/resource-management-groups/group-metadata-management/chat-group-metadata/multi-character-conversations.md) — Enable multiple AI characters to participate in the same conversation simultaneously. ([source](https://open-llm-vtuber.github.io/docs/intro))
- [LLM API Configurations](https://awesome-repositories.com/f/security-cryptography/api-access-control/endpoint-controls/endpoint-configurations/llm-api-configurations.md) — Connects to language models through OpenAI-compatible APIs or Groq for cloud-based inference. ([source](https://open-llm-vtuber.github.io/docs/faq))

### Software Engineering & Architecture

- [AI Backend Abstractions](https://awesome-repositories.com/f/software-engineering-architecture/execution-backend-abstractions/ai-backend-abstractions.md) — Provides a unified configuration interface for swapping between LLM, speech, and TTS backends.
- [Local-First Tool Processing](https://awesome-repositories.com/f/software-engineering-architecture/local-first-tool-processing.md) — Runs all core AI functions on-device without internet, using local models for privacy and independence.
- [Desktop Overlays](https://awesome-repositories.com/f/software-engineering-architecture/overlay-rendering-architectures/desktop-overlays.md) — Displays the avatar as a click-through, always-on-top window that integrates with the desktop environment.

### User Interface & Experience

- [Live2D Avatar Configurators](https://awesome-repositories.com/f/user-interface-experience/avatars/avatar-appearance-configurators/live2d-avatar-configurators.md) — Provides a setup interface for Live2D avatars that visually represent AI companions. ([source](https://open-llm-vtuber.github.io/docs/category/%E8%AF%A6%E7%BB%86%E6%8C%87%E5%8D%97))
- [Live2D Model Configurators](https://awesome-repositories.com/f/user-interface-experience/avatars/avatar-appearance-configurators/live2d-model-configurators.md) — Provides a dedicated interface for registering and configuring Live2D models with emotion and interaction mappings. ([source](https://open-llm-vtuber.github.io/docs/user-guide/live2d))
- [Realtime Avatar Renderers](https://awesome-repositories.com/f/user-interface-experience/avatars/realtime-avatar-renderers.md) — Renders customizable Live2D characters that react with expressions and emotions as AI companions. ([source](https://cdn.jsdelivr.net/gh/open-llm-vtuber/open-llm-vtuber@main/README.md))
- [Live2D Avatar Renderers](https://awesome-repositories.com/f/user-interface-experience/avatars/realtime-avatar-renderers/live2d-avatar-renderers.md) — Renders customizable Live2D models that display expressions and react to clicks based on AI state. ([source](https://open-llm-vtuber.github.io/docs/intro))
- [Live2D Animation Configurators](https://awesome-repositories.com/f/user-interface-experience/keyboard-input-visualizers/input-reactive-character-animators/conversational-avatar-animators/live2d-animation-configurators.md) — Ships a configuration system for Live2D model expressions, gestures, and click-triggered animations.
- [Character Appearance and Persona Customizers](https://awesome-repositories.com/f/user-interface-experience/terminal-user-interfaces/visual-styling-presentation/interface-appearance-customization/component-appearance-customizers/application-appearance-customizers/windows-appearance-customizers/character-appearance-and-persona-customizers.md) — Enables importing Live2D models, modifying prompts, and cloning voices for companion personalization. ([source](https://cdn.jsdelivr.net/gh/open-llm-vtuber/open-llm-vtuber@main/README.md))
- [Character Profile Switchers](https://awesome-repositories.com/f/user-interface-experience/character-encoding-support/chinese-character-support/customizable-character-models/character-profile-switchers.md) — Loads different Live2D models and settings by selecting named character configurations. ([source](https://open-llm-vtuber.github.io/docs/user-guide/live2d))
- [Live2D Character Importers](https://awesome-repositories.com/f/user-interface-experience/character-encoding-support/chinese-character-support/customizable-character-models/live2d-character-importers.md) — Provides a defined setup process for importing new Live2D characters into the system. ([source](https://open-llm-vtuber.github.io/docs/user-guide))
- [Model-to-Character Assignments](https://awesome-repositories.com/f/user-interface-experience/character-encoding-support/chinese-character-support/customizable-character-models/model-to-character-assignments.md) — Provides a mechanism to assign Live2D models to character profiles for avatar selection. ([source](https://open-llm-vtuber.github.io/docs/user-guide/live2d))
- [Desktop Overlay Toggles](https://awesome-repositories.com/f/user-interface-experience/terminal-user-interfaces/layout-structural-components/interface-display-modes/full-screen-modes/window-display-modes/desktop-overlay-toggles.md) — Toggles the client between a standard window and a transparent, always-on-top overlay that follows the cursor. ([source](https://open-llm-vtuber.github.io/docs/intro))

### Development Tools & Productivity

- [Multi-Agent Orchestrators](https://awesome-repositories.com/f/development-tools-productivity/plugin-orchestration/llm-plugin-orchestrators/multi-agent-orchestrators.md) — Manages multiple AI characters in a group chat by coordinating their responses through a plugin system.
- [Live2D Model Registrations](https://awesome-repositories.com/f/development-tools-productivity/snippet-management-tools/reusable-content-snippets/custom-model-registration/live2d-model-registrations.md) — Implements a registration system for Live2D models via file placement and JSON configuration. ([source](https://open-llm-vtuber.github.io/docs/user-guide/live2d))

### Web Development

- [AI-Driven Browser Controllers](https://awesome-repositories.com/f/web-development/headless-browser-controllers/ai-driven-browser-controllers.md) — Commands an AI to operate a web browser and execute tasks while showing a live view of the browser. ([source](https://open-llm-vtuber.github.io/docs/intro))
- [Remote Browser Controllers](https://awesome-repositories.com/f/web-development/remote-browser-controllers.md) — Commands an AI agent to operate a web browser remotely and perform tasks with a live view. ([source](https://open-llm-vtuber.github.io/docs/intro))
- [Browser Interaction Controls](https://awesome-repositories.com/f/web-development/web-automation-scraping/browser-control-protocols/browser-control-apis/browser-interaction-controls.md) — Commands an AI to navigate and interact with a web browser, showing a live view to the user. ([source](https://open-llm-vtuber.github.io/docs/intro))