# morettt/my-neuro

This project lets you create your own AI desktop companion with customizable characters and voice conversations that respond in just 1 second. Features include long-term memory, visual recognition, voice cloning and LLM training. Compatible with various Live2D customizations.

Repository: https://github.com/morettt/my-neuro
Canonical: https://ross.abutalabs.com/products/my-neuro
Language: JavaScript
License: MIT
License Family: permissive
Topics: ai, live2d, llm, python, ai-vtuber, chatbots, agent, neuro-sama
Last push: 2026-08-25T18:27:03+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 43
- inputs: {"age_days": 611, "days_push": 8, "days_rel": 11, "gap_med": 1, "n_releases_24m": 202}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1342, forks 160 (observed 2026-08-28T04:04:26.233914+00:00)

## What it is
An open-source AI desktop companion framework inspired by Neuro-sama, letting users build a customizable Live2D character with sub-second voice conversations, long-term memory, vision, voice cloning (GPT-SoVITS), and optional local LLM fine-tuning. It also supports extras like Bilibili livestreaming, AI singing, desktop voice control, and co-op gameplay in games like Minecraft.

## Use cases
- build a personalized AI desktop companion with a Live2D avatar
- create an AI vtuber that can livestream on Bilibili
- clone a custom voice for my AI character with GPT-SoVITS
- run a local LLM chatbot with sub-1-second voice latency
- give my AI assistant long-term memory about me
- have an AI companion that can play games like Minecraft with me
- fine-tune an open-source LLM locally for my AI character
- add image recognition so my AI companion can see

## When to choose
- you want a highly customizable, character-driven AI companion with voice, memory, and a Live2D avatar
- you prefer local inference and open-source model fine-tuning over third-party APIs
- you want an AI vtuber for livestreaming or entertainment content creation
- you enjoy tinkering and want a workbench-style project to shape personality, voice, and appearance

## When to avoid
- you need a production-ready, polished commercial product with guaranteed support
- you want a simple chatbot without voice, avatars, or heavy local GPU requirements
- you cannot run local models or lack the hardware for low-latency speech and LLM inference
- you need Twitch/YouTube livestream integration, which is not yet supported

## Facets
- artifact type: application
- maturity: active
- function: chatbot, tts, speech-recognition, llm-inference, llm-training, agent-framework, mcp, rag, computer-vision, animation
- domain: artificial-intelligence, large-language-models, chatbots, speech-processing, entertainment, gaming-tools
- platform: windows, python, cross-platform
- tags: live2d, ai-companion, ai-vtuber, voice-cloning, desktop-pet, neuro-sama, local-inference, streaming, bilibili, ai-agents, desktop, android

## Member repositories
- morettt/my-neuro (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:26.233914+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 2026-08-30T04:43:41.870915+00:00, confidence not recorded.
  - readme: https://github.com/morettt/my-neuro (fetched 2026-08-28T04:04:26.233914+00:00, sha b345294e7857)
- Data as of 2026-08-30T08:39:29.467469+00:00.