relayAPI:开源、本地化的 AI 模型质量检测与 API 兼容性评测平台 #1
kkddytd
announced in
Announcements
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
relayAPI 现已公开发布:https://github.com/kkddytd/relayAPI
relayAPI 是一个开源、自托管的 AI 模型质量检测、LLM 评测和 API 兼容性测试平台。它适用于 Claude、GPT、Gemini、GLM,以及任意自定义模型 ID 或模型中转接口。
核心能力
为什么做它
很多模型检测页面无法审计、题库过时,或者要求把 API Key 交给第三方服务。relayAPI 可以部署在自己的机器或服务器中,检测过程、数据和网络出口均由使用者控制。
快速开始
git clone https://github.com/kkddytd/relayAPI.git cd relayAPI bash scripts/deploy.sh也支持本地 Node.js 部署:
完整 API、部署方式、自定义模型配置与截图示例见 README:https://github.com/kkddytd/relayAPI#readme
relayAPI 基于 https://github.com/zzsting88/relayAPI 二次开发。欢迎提交模型渠道样例、协议差异、复现结果和功能建议。
English
relayAPI is an open-source, self-hosted platform for AI model quality testing, LLM evaluation, and API compatibility testing. It supports Claude, GPT, Gemini, GLM, custom model IDs, model gateways, REST API workflows, SQLite history, Docker Compose, and local Node.js deployment.
Repository: https://github.com/kkddytd/relayAPI
界面预览
All reactions