# agenmod/immortal-skill

♾️ 开源数字永生框架 — 从聊天记录蒸馏任何人的七维数字分身。支持微信/飞书/iMessage/Telegram等12+平台，7种角色模板，对齐 OpenClaw Soul Spec 标准。一行指令让你的AI学会蒸馏。

Repository: https://github.com/agenmod/immortal-skill
Canonical: https://ross.abutalabs.com/products/immortal-skill
Homepage: https://agenworld.com
Language: Python
License: MIT
License Family: permissive
Topics: agent-skills, ai-agent, chatbot, cursor, digital-immortality, digital-twin, distillation, feishu, llm, openclaw, persona, soul-spec, wechat
Last push: 2026-04-15T03:21:58+00:00

## Health v2 (maintenance only)
Score: 49/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 77, release rhythm 35, longevity 11
- inputs: {"age_days": 154, "days_push": 140, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1002, forks 88 (observed 2026-08-28T04:03:11.025984+00:00)

## What it is
An open-source 'digital immortality' framework that distills a person's persona from chat logs and documents across 12+ platforms (WeChat, Feishu, iMessage, Telegram, etc.) into a structured seven-dimension digital twin compatible with the OpenClaw Soul Spec. It ships as an agent skill (SKILL.md) plus companion skills for distilling public figures, protecting against unwanted distillation, and consent-based distillation protocols.

## Use cases
- create an AI persona of myself from my chat history
- distill a departing colleague's knowledge into an AI advisor
- preserve a grandparent's way of talking as a chatbot
- extract a public figure's methodology from interviews into a reusable prompt
- build a digital twin compatible with OpenClaw Soul Spec
- turn chat exports from WeChat or Feishu into a persona prompt
- teach any LLM a persona-distillation method with one instruction

## When to choose
- you want a structured, standards-aligned persona extraction pipeline rather than dumping chat logs into a vector store
- you need multi-platform chat import (WeChat, Feishu, iMessage, Telegram) and role-specific distillation templates
- you want MIT-licensed, agent-skill-based tooling usable directly inside Cursor or other AI agents

## When to avoid
- you need rigorous privacy, consent, or legal guarantees when modeling real people - the framework is playful and ethics are left to the user
- you want a production-grade fine-tuned model rather than prompt-based persona emulation
- you need a mature project with long-term support - it is a young, meme-flavored project with ~1k stars

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, prompt-engineering, chatbot, nlp, rag
- domain: artificial-intelligence, large-language-models, chatbots, developer-tools
- platform: python, cli, cross-platform
- tags: digital-immortality, digital-twin, persona-distillation, soul-spec, agent-skills, wechat, feishu, telegram, imessage, persona-market, ai-agents, natural-language-processing, web

## Member repositories
- agenmod/immortal-skill (main) score 49

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:11.025984+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 2026-08-30T07:13:57.173414+00:00, confidence not recorded.
  - readme: https://github.com/agenmod/immortal-skill (fetched 2026-08-28T04:03:11.025984+00:00, sha 2d1e98e17726)
  - homepage: https://agenworld.com (fetched 2026-08-29T13:13:53.176820+00:00, sha 7730713b2dc0)
- Data as of 2026-08-30T08:39:29.467469+00:00.