{"name":"CyberVerse: Self-Hosted Real-Time Digital Human Agent Platform","description":"CyberVerse is an open-source, self-hosted platform for building real-time digital human agents. It leverages WebRTC, persona memory, tools, and RAG to create voice-first AI agents, with optional digital-human video capabilities. This powerful framework allows developers to create highly interactive and lifelike AI companions.","github":"https://github.com/Lynpoint/CyberVerse","url":"https://osrepos.com/repo/lynpoint-cyberverse","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/lynpoint-cyberverse","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/lynpoint-cyberverse.md","json":"https://osrepos.com/repo/lynpoint-cyberverse.json","topics":["ai-agents","digital-human","voice-assistant","webrtc","python","open-source","ai-platform","real-time-ai"],"keywords":["ai-agents","digital-human","voice-assistant","webrtc","python","open-source","ai-platform","real-time-ai"],"stars":null,"summary":"CyberVerse is an open-source, self-hosted platform for building real-time digital human agents. It leverages WebRTC, persona memory, tools, and RAG to create voice-first AI agents, with optional digital-human video capabilities. This powerful framework allows developers to create highly interactive and lifelike AI companions.","content":"## Introduction\n\nCyberVerse is an innovative, open-source, and self-hosted platform designed for creating real-time digital human agents. It empowers developers to build sophisticated, voice-first AI agents by integrating cutting-edge technologies like WebRTC, persona memory, tools, and Retrieval Augmented Generation (RAG). A key feature is its optional digital-human video integration, enabling highly engaging and lifelike interactions from just a single photo. Imagine bringing your own J.A.R.V.I.S.-like AI to life, capable of seeing, hearing, and speaking with you in real-time.\n\n## Why Use CyberVerse and Its Benefits\n\nCyberVerse offers a compelling set of features and advantages for anyone looking to develop advanced AI agents:\n\n*   **Real-time Digital Human Interaction**: Create video-call capable digital humans from a single photo. Experience natural, full-duplex conversations with the ability to interrupt, just like a human video call. CyberVerse integrates with local models like FlashHead and LiveAct, and cloud services such as Baidu Xiling and Xunfei Digital Human.\n*   **Multi-Agent Architecture**: The platform utilizes a sophisticated multi-agent system. A `PersonaAgent` handles smooth user conversation and quick responses, while `SubAgents` asynchronously manage complex, time-consuming tasks like research, summarization, or report generation. This ensures that the main conversation flow remains uninterrupted.\n*   **Persistent Character Memory and RAG**: Each character maintains a persistent conversation history, ensuring continuity across sessions. You can also ingest knowledge bases, documents, and biographical materials for characters, which the system indexes for RAG. This allows for highly contextual and personalized responses aligned with the character's background.\n*   **Plugin-Based Stack**: CyberVerse is built with a modular design, where components like the brain, voice, hearing, tools, memory, and face are all pluggable modules. This flexibility allows users to easily swap providers and model configurations for LLMs, TTS, ASR, and Embedding services via configuration files or the Web UI.\n*   **Flexible Deployment**: Get started quickly with pre-built cloud images on platforms like Compshare and AutoDL, or deploy locally with comprehensive setup instructions.\n\n## Installation\n\nTo get CyberVerse up and running locally, follow these simplified steps. For detailed instructions and troubleshooting, please refer to the official GitHub repository.\n\n### Prerequisites\n\nEnsure you have the following installed:\n*   Node 18+\n*   Go 1.25 (with `protoc-gen-go`, `protoc-gen-go-grpc`)\n*   Conda\n*   Python 3.10+\n*   FFmpeg\n*   `libopus-dev`, `libopusfile-dev`, `libsoxr-dev`, `pkg-config`\n\nYou can verify installations with:\nbash\nnode --version\ngo version\nprotoc --version\nffmpeg -version\nconda --version\n\n\n### Steps\n\n1.  **Clone the repository**:\n    bash\ngit clone https://github.com/Lynpoint/CyberVerse.git\ncd CyberVerse\n    \n\n2.  **Create Python environment**:\n    bash\nconda create -n cyberverse python=3.10\nconda activate cyberverse\n    \n\n3.  **Set environment variables**:\n    bash\ncp -r infra/config config\n    \n    Edit `config/env` to add your API keys (e.g., `DASHSCOPE_API_KEY`, `DOUBAO_ACCESS_TOKEN`).\n\n4.  **Enable voice-only mode (optional, for initial setup)**:\n    Edit `config/cyberverse.yaml` and set `inference.avatar.enabled: false` if you don't want video inference initially.\n\n5.  **Install project dependencies**:\n    bash\nmake setup\npip install \".[all]\"\n    \n\n6.  **Start services (in three separate terminals)**:\n    *   **Terminal 1 (Python inference server)**:\n        bash\nconda activate cyberverse\nmake inference\n        \n    *   **Terminal 2 (Go API server)**:\n        bash\nmake server\n        \n    *   **Terminal 3 (Frontend)**:\n        bash\nmake frontend\n        \n\n7.  **Verify and access**:\n    Check API health:\n    bash\ncurl -s http://localhost:8080/api/v1/health\n    \n    Open your browser to `http://localhost:5173`.\n\nFor full digital human video setup, including GPU requirements and model weights download, please refer to the detailed instructions in the official CyberVerse README.\n\n## Examples\n\nCyberVerse showcases its capabilities through impressive demonstrations of digital human agents. The repository's README features demo images and links to YouTube videos where you can see these agents in action, demonstrating real-time video interaction and natural language processing.\n\n*   **Alice**: [Watch on YouTube](https://youtu.be/Lk88sew2x4o)\n*   **Lina**: [Watch on YouTube](https://youtu.be/8jdQ3ThcwgA)\n*   **Xiaolongnü**: [Watch on YouTube](https://youtu.be/WjEHUYZx5Gs)\n\nThese examples highlight the platform's ability to bring characters to life with expressive movements and synchronized speech.\n\n## Links\n\n*   **GitHub Repository**: [https://github.com/Lynpoint/CyberVerse](https://github.com/Lynpoint/CyberVerse)\n*   **License**: [GPL-3.0](https://github.com/Lynpoint/CyberVerse/blob/main/LICENSE)\n*   **Community**: Join the CyberVerse digital human technology exchange group by scanning the WeChat QR code in the official README or adding the maintainer (wx_dsd2077) and mentioning \"CyberVerse\" in your application.","metrics":{"detailViews":0,"githubClicks":0},"dates":{"published":null,"modified":"2026-09-18T12:10:53.000Z"}}