# elevenyellow/handcrafted-persona-engine

An AI-powered interactive avatar engine using Live2D, LLM, ASR, TTS, and RVC. Ideal for VTubing, streaming, and virtual assistant applications.

Repository: https://github.com/elevenyellow/handcrafted-persona-engine
Canonical: https://ross.abutalabs.com/products/handcrafted-persona-engine
Language: C#
License Family: other
Topics: ai, ai-vtuber, ai-waifu, chatbot, live2d, vtuber
Last push: 2026-05-20T13:51:14+00:00

## Health v2 (maintenance only)
Score: 73/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 83, release rhythm 80, longevity 37
- inputs: {"age_days": 523, "days_push": 105, "days_rel": 132, "gap_med": 11.5, "n_releases_24m": 5}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1357, forks 156 (observed 2026-08-28T04:04:29.466965+00:00)

## What it is
Persona Engine is a Windows desktop application that drives a Live2D avatar with an AI pipeline: microphone speech recognition, an LLM guided by a personality file, real-time TTS with optional voice cloning, and synchronized lip-sync and expressions. It includes a transparent overlay and Spout output for piping the character into OBS for streaming.

## Use cases
- run an AI VTuber that listens and responds live on stream
- create an interactive AI waifu companion with a Live2D avatar
- build a virtual assistant with a talking animated character
- stream a voice-driven Live2D character into OBS
- voice-clone TTS for a virtual persona
- make a Live2D character lip-sync to AI-generated speech

## When to choose
- you want a ready-to-run AI VTuber stack on Windows with an NVIDIA GPU
- you need Live2D lip-sync, LLM conversation, and TTS integrated out of the box
- you want to pipe an animated avatar into OBS via Spout

## When to avoid
- you need Linux or macOS support
- you have no NVIDIA CUDA-capable GPU
- you need a library or SDK to embed in your own application rather than a standalone app
- you require a permissively licensed dependency since the repo has no license file

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, tts, llm-inference, chatbot, animation, audio-processing
- domain: artificial-intelligence, chatbots, large-language-models, speech-processing, entertainment, gaming-tools
- platform: windows
- tags: live2d, vtuber, ai-waifu, streaming, obs, spout, voice-cloning, rvc, avatar, lip-sync, desktop, gpu

## Member repositories
- elevenyellow/handcrafted-persona-engine (main) score 73

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:29.466965+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 2026-08-30T04:41:49.804879+00:00, confidence not recorded.
  - readme: https://github.com/elevenyellow/handcrafted-persona-engine (fetched 2026-08-28T04:04:29.466965+00:00, sha 83ad28221679)
- Data as of 2026-08-30T08:39:29.467469+00:00.