# Lynpoint/CyberVerse

Self hosted, real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video.

Repository: https://github.com/Lynpoint/CyberVerse
Canonical: https://ross.abutalabs.com/products/cyberverse
Homepage: https://www.cyberverse.cc
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: ai-agents, ai-companion, digital-human, digital-life, jarvis-assistant, streaming, webrtc, voice-agent, voice-assistant, talking-head, talking-avatar, lip-sync
Last push: 2026-08-05T08:17:26+00:00

## Health v2 (maintenance only)
Score: 63/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 96, release rhythm 52, longevity 9
- inputs: {"age_days": 137, "days_push": 28, "days_rel": 109, "gap_med": null, "n_releases_24m": 1}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1612, forks 223 (observed 2026-08-28T04:05:10.987369+00:00)

## What it is
CyberVerse is an open-source, self-hosted framework for building real-time, voice-first AI agents with optional digital-human video (talking avatar with lip-sync). It combines WebRTC streaming, persona memory, tool use, and RAG to create lifelike interactive characters from a single photo.

## Use cases
- build a J.A.R.V.I.S.-style real-time voice assistant
- create a talking avatar from a single photo
- build an AI companion with persona memory
- stream a digital human over WebRTC with lip-sync
- add RAG knowledge and tools to a voice agent
- self-host a real-time conversational agent

## When to choose
- you want a self-hosted, voice-first agent with optional digital-human video
- you need real-time WebRTC streaming with lip-synced avatars
- you want persona memory, tools, and RAG integrated in one framework

## When to avoid
- you only need a text chatbot without voice or video
- you need a fully managed cloud service rather than self-hosting
- you require a permissive license (it is GPL-3.0)

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, rag, speech-recognition, tts, chatbot, video-processing, webhook, llm-inference
- domain: artificial-intelligence, chatbots, speech-processing, self-hosted
- platform: python, self-hosted, cross-platform
- tags: digital-human, voice-agent, talking-avatar, lip-sync, webrtc, persona-memory, real-time, ai-companion, talking-head, ai-agents, retrieval-augmented-generation, web-server, docker

## Member repositories
- Lynpoint/CyberVerse (main) score 63

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:10.987369+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:51:08.437771+00:00, confidence not recorded.
  - readme: https://github.com/Lynpoint/CyberVerse (fetched 2026-08-28T04:05:10.987369+00:00, sha 6ea33a9cfd34)
- Data as of 2026-08-30T08:39:29.467469+00:00.