# xming521/WeClone

🚀 One-stop solution for creating your AI twin from chat history 💡 Fine-tune LLMs with your chat logs to capture your unique style, then bind to a chatbot to bring your digital self to life.

Repository: https://github.com/xming521/WeClone
Canonical: https://ross.abutalabs.com/products/weclone
Homepage: https://weclone.love
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: llm, qwen, chat-history, digital-avatar, telegram
Last push: 2026-08-18T13:47:06+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 64, longevity 67
- inputs: {"age_days": 945, "days_push": 15, "days_rel": 241, "gap_med": 14.5, "n_releases_24m": 11}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 18171, forks 1524 (observed 2026-08-28T04:11:26.406762+00:00)

## What it is
WeClone is an end-to-end Python framework for creating a personal AI digital twin by fine-tuning large language models on your exported chat history. It covers data export and preprocessing, privacy filtering, model fine-tuning, and deployment as a chatbot on platforms like Telegram.

## Use cases
- create an AI clone of myself from my chat logs
- fine-tune an LLM on my WeChat or Telegram message history
- build a chatbot that talks in my personal style
- train a digital avatar with my catchphrases and expressions
- run a personal AI twin locally for privacy
- deploy a fine-tuned persona bot to Telegram

## When to choose
- you want a complete pipeline from chat data export to deployed persona chatbot
- you need local fine-tuning and deployment with privacy filtering of personal data
- you want to integrate your AI twin with Telegram or other chat platforms

## When to avoid
- you need a production-grade enterprise chatbot with guaranteed response quality
- you cannot provide sufficient chat data volume for meaningful fine-tuning
- you lack GPU resources for local model training and inference

## Facets
- artifact type: framework
- maturity: active
- function: llm-training, llm-inference, chatbot, rag, etl, agent-framework
- domain: large-language-models, artificial-intelligence, chatbots, privacy
- platform: python, self-hosted, cli
- tags: digital-avatar, digital-twin, fine-tuning, chat-history, wechat, qwen, personalization, natural-language-processing, telegram, discord

## Member repositories
- xming521/WeClone (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:26.406762+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 2026-08-29T17:02:08.019733+00:00, confidence not recorded.
  - readme: https://github.com/xming521/WeClone (fetched 2026-08-28T04:11:26.406762+00:00, sha dbf7ec02017e)
  - homepage: https://weclone.love (fetched 2026-08-29T08:00:07.246061+00:00, sha e9d02e9bfa78)
  - site_page: https://www.weclone.love/en/docs/introduce/what-is-weclone.html (fetched 2026-08-29T08:00:07.255504+00:00, sha 7870193a638f)
- Data as of 2026-08-30T08:39:29.467469+00:00.