# SMNETSTUDIO/WeChat-AI

WeChat AI - 自托管微信角色扮演对话服务

Repository: https://github.com/SMNETSTUDIO/WeChat-AI
Canonical: https://ross.abutalabs.com/products/wechat-ai
Language: TypeScript
License: Apache-2.0
License Family: permissive
Last push: 2026-08-26T04:56:01+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 65, longevity 1
- inputs: {"age_days": 23, "days_push": 7, "days_rel": 20, "gap_med": null, "n_releases_24m": 1}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1857, forks 1281 (observed 2026-08-28T04:05:45.061902+00:00)

## What it is
A self-hosted WeChat roleplay chatbot service written in TypeScript that connects directly to Tencent iLink, stores data in remote Redis, and authenticates users via LINUX DO OAuth. It supports persona assignment, P2P chat relaying, sticker replies, voice transcription, OpenAI-compatible LLMs, visual Chatflow orchestration, and multi-node deployment behind a Cloudflare Worker load balancer.

## Use cases
- run a self-hosted AI roleplay chatbot on WeChat
- connect WeChat bots to OpenAI-compatible LLMs
- manage multiple WeChat bot personas with an admin dashboard
- relay messages between WeChat users and AI personas
- deploy a multi-node chatbot service with load balancing
- add sticker and image replies to a WeChat AI bot
- track daily token usage for LLM chatbots

## When to choose
- you want a self-hosted WeChat AI chatbot with persona/roleplay support
- you need multi-node deployment with shared Redis state and load balancing
- you want admin tooling for bots, users, token usage, and sticker moderation
- you rely on LINUX DO OAuth for user identity

## When to avoid
- you need a general-purpose WeChat customer-service bot without roleplay features
- you cannot use LINUX DO OAuth or a remote Redis instance
- you need official WeChat API integration rather than direct iLink connectivity
- you want a simple single-file bot script instead of a full service

## Facets
- artifact type: service
- maturity: active
- function: chatbot, agent-framework, llm-inference, self-hosted, web-framework, caching
- domain: chatbots, artificial-intelligence, large-language-models, messaging-platforms, self-hosted, web-development
- platform: self-hosted, cloud
- tags: wechat, roleplay, ilink, redis, oauth, linuxdo, persona, sticker, multi-node, cloudflare-worker, nodejs, docker, web-server

## Member repositories
- SMNETSTUDIO/WeChat-AI (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:45.061902+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 2026-08-30T03:16:14.768556+00:00, confidence not recorded.
  - readme: https://github.com/SMNETSTUDIO/WeChat-AI (fetched 2026-08-28T04:05:45.061902+00:00, sha 474f75a1c273)
- Data as of 2026-08-30T08:39:29.467469+00:00.