OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

Cyberverse

CyberVerse is an open-source, self-hosted Python framework for building real-time digital-human agents centered on voice interaction, with WebRTC, persona memory, tools, RAG and optional video.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Cyberverse — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use CyberVerse when you need a self-hosted framework for real-time voice interaction with configurable agent components, character memory, retrieval or tools. Choose the optional video path when an avatar is required and its additional infrastructure is suitable.

Who it is for

  • Developers building self-hosted voice-first AI agents.
  • Teams creating conversational personas that need persistent history or answers grounded in imported documents and biographical material.
  • Builders connecting live dialogue to tools or asynchronous research and summarization tasks.
  • Projects adding optional talking-avatar video to a voice agent.

Documented uses

  • Create a voice conversational agent with a configured LLM, speech and other provider components.
  • Preserve character conversation history across sessions and retrieve information from imported knowledge materials.
  • Delegate longer search, research, organization, summarization or HTML-report tasks to background SubAgents.
  • Add optional digital-human video through local avatar models or supported cloud services.
Before you choose

Requirements & limits

The project is open source under GPL-3.0. The README documents self-hosted local setup and lists cloud-image quick-start options.

  • The framework separates foreground dialogue from longer-running SubAgent work, allowing users to continue speaking or redirect a task while it runs.
  • Voice, hearing, brain, tools, memory and face are replaceable modules; provider configuration can be adjusted through files or the /settings web interface.
  • Pure voice sessions do not require a local avatar GPU, according to the README; local avatar video requires additional GPU and model setup.
  • The README lists local avatar options FlashHead and LiveAct, plus cloud digital-human integrations.
  • Local setup requires a mixed Python, Node, Go, Conda and audio/video dependency stack.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare a local CyberVerse environment

Set up the documented Python environment, copy the configuration files and add a supported provider credential.

Before you start

  • Node 18 or later, Go 1.25, Conda, Python 3.10 or later, FFmpeg, libopus-dev, libopusfile-dev, libsoxr-dev and pkg-config.
  • An API credential for one of the provider options described in the README.

Steps

  1. Clone the repository and change into the CyberVerse directory.

  2. Create and activate a Conda environment using Python 3.10.

  3. Copy the built-in configuration with cp -r infra/config config.

  4. Add the relevant provider credential to config/env; after the stack is running, provider keys and endpoints can also be changed at /settings.

Expected outcome

A prepared local configuration with a Python environment and provider credentials; the README continues with model and runtime configuration.

Guide limitations

  • These steps prepare the environment and configuration; they do not cover every stage required to run an agent.
  • Local avatar video has additional GPU, CUDA, PyTorch, model-weight and FFmpeg requirements.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
10 October 2026
Original website title
Lynpoint/CyberVerse · Official homepage title · retained in its source language
How we review sourcesSuggest a correction