# cixingguangming55555/wechat-bot

和国产大模型相关的免费工具集

Repository: https://github.com/cixingguangming55555/wechat-bot
Canonical: https://ross.abutalabs.com/products/cixingguangming55555-wechat-bot
Language: JavaScript
License: MIT
License Family: permissive
Topics: claude, glm, kimi-k2, minimax, proxy
Last push: 2026-02-09T06:38:04+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 66, release rhythm 35, longevity 100
- inputs: {"age_days": 2389, "days_push": 205, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2523, forks 661 (observed 2026-08-28T04:06:58.435606+00:00)

## What it is
A free toolset (funtool) providing proxy executables that let the Claude Code CLI use free NVIDIA-hosted large models such as Kimi K2.5, GLM 4.7, Qwen3 Coder, DeepSeek v3.2, and Step 3.5 Flash. It acts as a local API proxy translating Claude Code requests to these models.

## Use cases
- use claude code cli with free nvidia-hosted models
- run kimi k2.5 as a backend for claude code
- proxy claude code to glm 4.7 or deepseek v3.2
- code with qwen3 coder through claude code
- avoid paying for anthropic api by using free model proxies

## When to choose
- you want to use Claude Code CLI without an Anthropic subscription
- you want to try Chinese open models like GLM, Kimi, or DeepSeek as coding assistants
- you need a drop-in proxy for the Claude Code CLI

## When to avoid
- you need official Anthropic model quality and support
- you require Linux or macOS support and cannot run Windows executables
- you need a fully auditable open-source proxy rather than prebuilt binaries

## Facets
- artifact type: cli-tool
- maturity: active
- function: proxy, llm-inference, developer-tools, cli
- domain: large-language-models, developer-tools
- platform: windows, cli
- tags: claude-code-proxy, nvidia-nim, free-models, api-proxy, chinese-llms, command-line

## Member repositories
- cixingguangming55555/wechat-bot (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:58.435606+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 2026-08-30T02:25:39.718584+00:00, confidence not recorded.
  - readme: https://github.com/cixingguangming55555/wechat-bot (fetched 2026-08-28T04:06:58.435606+00:00, sha 9defba151d8a)
- Data as of 2026-08-30T08:39:29.467469+00:00.