# whyiyhw/chatgpt-wechat

企业微信/微信 安全使用的 LLM 个人助手/客服, 也支持 dify 工作流

Repository: https://github.com/whyiyhw/chatgpt-wechat
Canonical: https://ross.abutalabs.com/products/chatgpt-wechat
Language: Go
License: Apache-2.0
License Family: permissive
Topics: wecom, wechat, gpt-4, gemini, gpt-4o, dify, dify-services, gpt4o-mini, deepseek
Last push: 2026-05-20T00:55:41+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 83, release rhythm 8, longevity 92
- inputs: {"age_days": 1299, "days_push": 106, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1169, forks 215 (observed 2026-08-28T04:03:51.113439+00:00)

## What it is
A self-hosted Go application that lets users safely use LLM assistants (ChatGPT, Gemini, DeepSeek, Dify workflows) inside WeChat by relaying messages through WeCom (Enterprise WeChat), avoiding account bans. It supports multi-session chat, voice and image messages, streaming replies, prompt role templates, plugins, and a private Milvus vector knowledge base.

## Use cases
- use chatgpt inside wechat without getting banned
- build an llm customer service bot on wecom
- deploy a personal ai assistant in wechat
- connect dify workflows to wechat messaging
- add a private vector knowledge base to a wechat chatbot
- answer voice messages with an llm assistant
- run a self-hosted chatgpt proxy for chinese users

## When to choose
- you want LLM access directly in WeChat/WeCom with no ban risk
- you need a self-hosted assistant with private knowledge base via Milvus
- you want multi-channel customer service bots with voice, image, and streaming replies
- you want to plug Dify workflows or multiple LLM providers into chat apps

## When to avoid
- you need a managed SaaS solution with no server setup
- your users are not on WeChat/WeCom
- you only need a plain web chat UI without messaging platform integration
- you require the latest v1.0.0 features in production (still in development; use v0.6.6)

## Facets
- artifact type: application
- maturity: active
- function: chatbot, llm-inference, rag, agent-framework, speech-recognition, image-processing, plugin-system, self-hosted
- domain: chatbots, artificial-intelligence, large-language-models, messaging-platforms, self-hosted
- platform: self-hosted, go
- tags: wechat, wecom, enterprise-wechat, chatgpt, dify, gemini, deepseek, vector-database, milvus, stable-diffusion, customer-service, voice-messages, prompt-templates, ai-agents, docker, linux, web-server

## Member repositories
- whyiyhw/chatgpt-wechat (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:51.113439+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 2026-08-30T06:28:44.622887+00:00, confidence not recorded.
  - readme: https://github.com/whyiyhw/chatgpt-wechat (fetched 2026-08-28T04:03:51.113439+00:00, sha 42538a31fba8)
- Data as of 2026-08-30T08:39:29.467469+00:00.