Licheng Wang AlphaAvatar

Learnable, configurable, and pluggable Omni Personal Assistant for everyone

AlphaAvatar Introduction

AlphaAvatar is a self-hostable Omni Personal Assistant framework designed to evolve into an intelligent personal butler — a continuous, personalized, and proactive assistant that can remember, understand, plan, and act on behalf of the user.

It is built around a plugin-based real-time Agent architecture, combining:

🧠 Memory for long-term user, assistant, and tool interaction history
🧬 Persona for user understanding, identity continuity, and personalization
💡 Reflection for self-improvement and long-term behavioral adaptation
📅 Planning for task decomposition, reminders, and future-oriented actions
⚙️ Behavior for response style, workflow policy, and proactive assistance
🧰 Tools through MCP, RAG, DeepResearch, and external integrations
😊 Virtual Character for real-time voice/avatar interaction

✨ Fully self-hostable and privacy-first — AlphaAvatar can run locally or on your own infrastructure, giving you control over your data, memory, tools, and behavior.

What AlphaAvatar Is Designed For

1️⃣ Personal Data & Life Metrics Management 📊 Track and analyze personal metrics such as health, fitness, sleep, and study progress 📈 Provide long-term insights and trend analysis 🎯 Suggest improvements based on historical patterns	2️⃣ Knowledge & Notes Management 📖 Organize personal notes, documents, and knowledge 🔍 Retrieve relevant information through RAG 🧠 Build a personal knowledge base over time
3️⃣ Task & Event Management 📅 Schedule tasks and reminders ⏰ Proactively notify based on context and priority 🔄 Break down long-term goals into actionable steps	4️⃣ Autonomous Planning & Execution 🧠 Plan multi-step workflows such as learning plans, projects, and research 🔧 Call tools automatically to complete tasks 📌 Maintain consistency across long time horizons
5️⃣ Personalized Companion & Context Awareness 🧬 Understand user preferences, habits, and personality 💬 Provide highly personalized responses 🤝 Maintain continuity across conversations and modalities	6️⃣ External World Interaction 🌐 Search, research, and summarize real-world information 🧰 Integrate with tools such as email, databases, APIs, and messaging apps 🔗 Act as a bridge between user intent and external systems

💡 AlphaAvatar is not just a chatbot. It is a foundation for building stateful, proactive, multimodal, and self-evolving personal AI assistants.

AlphaAvatar Plugins

🟢 Status

Intermediate status system for reducing perceived latency during thinking, tool calls, and multi-step workflows.

README↗

🎯 Interaction Router

Omni interaction routing module that decides whether the Avatar should respond, how the request should be handled, and which status feedback should be emitted.

README↗

🧠 Memory

Self-improving memory module for Omni-Avatar.

README↗

🧬 Persona

Automatic extraction and real-time matching of multimodal user persona.

README↗

💡 Reflection

A self-improvement module that reflects on memory, behavior, and interaction history.

README↗

📅 Planning

Long-horizon planning module for tasks, reminders, goals, and multi-step workflows.

README↗

🤖 Behavior

Controls response style, workflow policy, tool-use behavior, and proactive assistance rules.

README↗

😊 Virtual Character

The real-time generated virtual character that visually represents the Avatar during interactions.

README↗

Tools Plugins

🔍 DeepResearch

Allow AlphaAvatar to access the network and perform single-step/multi-step inference through a separate Agent service to search for more accurate content.

README↗

📖 RAG

Allow AlphaAvatar to access Documents/Skills (user-uploaded/generated by the Reflection module/URL access) to obtain document-related information.

README↗

🧰 MCP

Allows AlphaAvatar to discover and call real-world external tools such as databases, email, calendars, APIs, and productivity apps.

README↗

🌍 Sandbox

Provide AlphaAvatar with a sandbox environment to interact with the external world or with other agents, thereby enabling multi-agent interaction and exploration.

README↗

Latest News 🔥

[2026/06] Released AlphaAvatar version 0.6.0: Added the Status plugin, sampled visual input support, and status-aware DeepResearch / RAG / MCP tool feedback.
[2026/05] Released AlphaAvatar version 0.5.4:
- Added LanceDB-backed MCP tool retrieval, enabling AlphaAvatar to semantically search relevant MCP tools from Agent queries.
- Refactored system prompt and runtime prompt composition, improved Persona runtime state tracking, added temporary-user to real-user identity merging, and improved RAG runtime behavior.
- Released AlphaAvatar version 0.5.5: Fixed the inference runner registration lifecycle for production start mode, ensuring plugins runners are registered after config parsing and before LiveKit creates the inference executor.
[2026/04] Released AlphaAvatar version 0.5.3:
- Added localized Markdown backup for the Memory plugin.
- Added LanceDB as the default local VDB option when Qdrant credentials are not provided.
[2026/03] Released AlphaAvatar version 0.5.0:
- Added the MCP plugin, enabling retrieval and concurrent invocation of MCP tools.
- Released AlphaAvatar version 0.5.1: Added WhatsApp channel support via Baileys.
- Released AlphaAvatar version 0.5.2: Added the AlphaAvatar Voice plugin with Voice.ai TTS support.
[2026/02] Released AlphaAvatar version 0.4.0:
- Added RAG support through RAG-Anything.
- Optimized the Memory and DeepResearch modules.
- Released AlphaAvatar version 0.4.1: Fixed Persona plugin bugs and added a new MCP plugin.
[2026/01] Released AlphaAvatar version 0.3.0:
- Added DeepResearch support through the Tavily API.
- Released AlphaAvatar version 0.3.1: Added tool-call memory extraction during user–assistant interactions.

2025 Release History

[2025/12] Released AlphaAvatar version 0.2.0:
- Added AIRI Live2D-based virtual character display.
[2025/11] Released AlphaAvatar version 0.1.0:
- Added automatic memory extraction.
- Added automatic user persona extraction and matching.

Installation ⚙️

Install stable AlphaAvatar version from PyPI:

uv venv .my-env --python 3.11
source .my-env/bin/activate
pip install alpha-avatar-agents

Install latest AlphaAvatar version from GitHub:

git clone --recurse-submodules https://github.com/AlphaAvatar/AlphaAvatar.git
cd AlphaAvatar

uv venv .venv --python 3.11
source .venv/bin/activate
uv sync --all-packages

Quick Start ⚡️

Start your agent in dev mode to connect it to LiveKit and make it available from anywhere on the internet.

🧩 Step 1. Configure Environment Variables

cd AlphaAvatar

# Copy template
cp .env.template .env.dev

Edit .env.dev and set required environment variables.

📦 Step 2. Download Required Files

alphaavatar download-files

✅ Step 3. Run the Agent

ENV_FILE=.env.dev alphaavatar dev examples/agent_configs/voice/pipeline_openai_tools.yaml
# or
ENV_FILE=.env.dev alphaavatar dev examples/agent_configs/mm/pipeline_openai_tools.yaml

To see more supported modes, please refer to the LiveKit doc.

To see more examples, please refer to the Examples README

Runtime Architecture 🧠

AlphaAvatar is built around a real-time multimodal Agent runtime. It separates streaming interaction, model reasoning, runtime context, plugin state, tool execution, and channel adapters.

                         AlphaAvatar Runtime
                         ───────────────────

        ┌──────────────────────────────────────────────┐
        │                 LiveKit Room                 │
        │        audio / text / video / data streams   │
        └──────────────────────┬───────────────────────┘
                               │
                               ▼
        ┌──────────────────────────────────────────────┐
        │                 AgentSession                 │
        │      real-time turn detection / streaming IO │
        └──────────────────────┬───────────────────────┘
                               │
                               ▼
        ┌──────────────────────────────────────────────┐
        │                 AvatarEngine                 │
        │  Realtime Model Pipeline                     │
        │  STT / VAD / LLM / TTS / video-ready input   │
        └──────────────────────┬───────────────────────┘
                               │
                               ▼
        ┌──────────────────────────────────────────────┐
        │          Prompt & Runtime Context Layer       │
        │  system prompt / runtime prompt / time / mode │
        │  memory / persona / plan / reflection / rules │
        └──────────────────────┬───────────────────────┘
                               │
        ┌──────────────────────┼───────────────────────┐
        │                      │                       │
        ▼                      ▼                       ▼
┌──────────────────┐  ┌──────────────────┐   ┌──────────────────┐
│  Memory Plugin   │  │  Persona Plugin  │   │   Tools Plugins  │
│ conversation     │  │ user profile     │   │ MCP / RAG        │
│ tool memory      │  │ speaker / face   │   │ DeepResearch     │
│ avatar memory    │  │ runtime state    │   │ external APIs    │
└──────────────────┘  └──────────────────┘   └──────────────────┘

┌──────────────────┐  ┌──────────────────┐   ┌──────────────────┐
│ Reflection Plugin│  │ Planning Plugin  │   │ Behavior Plugin │
│ self-analysis    │  │ tasks / plans    │   │ response policy │
│ adaptation       │  │ reminders        │   │ workflow rules  │
└──────────────────┘  └──────────────────┘   └──────────────────┘
                               │
                               ▼
        ┌──────────────────────────────────────────────┐
        │              UserPath Workspace              │
        │  local data / cache / logs / memory / RAG    │
        │  persona state / artifacts / user files      │
        └──────────────────────┬───────────────────────┘
                               │
        ┌──────────────────────┴───────────────────────┐
        │                                              │
        ▼                                              ▼
┌──────────────────────┐                    ┌──────────────────────┐
│ Native Web / App     │                    │ Channel Adapters     │
│ voice / text / video │                    │ WhatsApp / future    │
│ WebRTC / UI          │                    │ messaging platforms  │
└──────────────────────┘                    └──────────────────────┘

Usage 🚀

AlphaAvatar supports multiple Access Channels, allowing different types of users — from end users to developers — to interact with the system.

🌐 Web Access

AlphaAvatar now provides a browser-based realtime demo interface built on LiveKit.

👉 Try the Web Demo: https://www.alphaavatar.ai/demo

The Web Demo supports:

🎙️ Real-time voice interaction
💬 Text chat with the Avatar
📷 Camera preview and video-ready interaction
🔊 Agent audio playback
😊 Virtual character / avatar stage
🧠 Full plugin support, including Memory, Persona, RAG, MCP, and DeepResearch
🌍 Browser timezone metadata, enabling AlphaAvatar to understand local login time

The Web Demo is the recommended way to try AlphaAvatar with a full realtime multimodal experience.

💬 Social & Messaging Platforms

Interact with AlphaAvatar directly inside messaging platforms.

Capabilities:

💬 Text-based conversation
🎤 Voice message interaction
🧰 Tool invocation via chat interface

WhatsApp

📦 Channel introduction: README

▶️ Start WhatsApp Channel

Make sure AlphaAvatar Agent is already running (see Quick Start above).

ENV_FILE=.env.dev sh examples/channels/start_whatsapp.sh

💡 The WhatsApp channel runs as an independent bridge process and connects to the Agent runtime.

WeChat

Slack

📲 Native Mobile App

A dedicated AlphaAvatar mobile application providing:

🎙️ Real-time voice communication
😊 Live2D / Virtual character visualization
🧠 Persistent memory & persona

🧪 Developer Playground

Developers can immediately access AlphaAvatar via the LiveKit Playground.

👉 https://agents-playground.livekit.io/

After starting your AlphaAvatar server:

Connect to your LiveKit instance
Configure the Agent name in the Playground (must match avatar_name, default: Assistant) to enable Explicit Dispatch.
Connect to the agent room
Start testing real-time interaction

Supported capabilities:

🎙️ Voice interaction
🧠 Memory extraction
🔍 RAG retrieval
🧰 MCP tool invocation
😊 Virtual character display

💡 AlphaAvatar is currently developer-first, with a Web Demo available for realtime interaction.

More user-facing web and mobile experiences are under active development.

Licheng Wang AlphaAvatar

Achievements

Achievements

Learnable, configurable, and pluggable Omni Personal Assistant for everyone

AlphaAvatar Introduction

What AlphaAvatar Is Designed For

1️⃣ Personal Data & Life Metrics Management

2️⃣ Knowledge & Notes Management

3️⃣ Task & Event Management

4️⃣ Autonomous Planning & Execution

5️⃣ Personalized Companion & Context Awareness

6️⃣ External World Interaction

AlphaAvatar Plugins

🟢 Status

🎯 Interaction Router

🧠 Memory

🧬 Persona

💡 Reflection

📅 Planning

🤖 Behavior

😊 Virtual Character

Tools Plugins

🔍 DeepResearch

📖 RAG

🧰 MCP

🌍 Sandbox

Latest News 🔥

Installation ⚙️

Quick Start ⚡️

Runtime Architecture 🧠

Usage 🚀

🌐 Web Access

💬 Social & Messaging Platforms

WhatsApp

WeChat

Slack

📲 Native Mobile App

🧪 Developer Playground

Pinned Loading

Uh oh!