# Ch1rpy2613/Mirrai

Repository: https://github.com/Ch1rpy2613/Mirrai
Canonical: https://ross.abutalabs.com/products/mirrai
Language: TypeScript
License Family: other
Last push: 2026-08-16T00:48:59+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 35, longevity 8
- inputs: {"age_days": 120, "days_push": 18, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1365, forks 5 (observed 2026-08-28T04:04:31.126202+00:00)

## What it is
Mirrai is a self-hosted web application that builds AI 'digital twins' of people from uploaded chat logs, photos, and videos, then lets users chat with the persona in an immersive interface. It uses a multi-stage personality distillation pipeline, a dynamic emotional state machine, pluggable LLM backends (10 providers), and a Wechaty-based WeChat bot for automatic replies.

## Use cases
- recreate a loved one as an AI chatbot from chat history
- build a digital persona that mimics someone's texting style
- auto-reply to WeChat messages as a digital twin
- analyze chat logs to extract personality traits with AI
- chat with an AI companion that has emotional states
- self-host an AI companion app with any LLM provider
- generate AI diaries and memory milestones from conversations

## When to choose
- you want a self-hosted AI persona/companion app with full control over LLM providers
- you need WeChat integration so a persona can reply on your behalf
- you want structured personality extraction from real chat logs rather than simple prompting
- you prefer a full-stack TypeScript codebase with end-to-end type safety

## When to avoid
- you need a polished hosted SaaS with no setup
- you want a general-purpose chatbot framework rather than a persona-companion application
- you need official support or a clear license for commercial use (no license file is published)
- you require enterprise-grade security or multi-tenant deployment

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, chatbot, rag, tts, agent-framework, auth, web-framework, api-framework, data-science, nlp
- domain: artificial-intelligence, large-language-models, chatbots, web-development, self-hosted, messaging-platforms
- platform: self-hosted, cross-platform
- tags: digital-persona, ai-companion, personality-distillation, wechat-bot, wechaty, trpc, drizzle-orm, react, emotion-state-machine, llm-provider-abstraction, chat-log-analysis, intimacy-system, natural-language-processing, nodejs, web-server, wechat

## Member repositories
- Ch1rpy2613/Mirrai (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:31.126202+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 2026-08-30T04:41:14.687584+00:00, confidence not recorded.
  - readme: https://github.com/Ch1rpy2613/Mirrai (fetched 2026-08-28T04:04:31.126202+00:00, sha 4bfa9cf950b8)
- Data as of 2026-08-30T08:39:29.467469+00:00.