Enterprise-grade LLM automated deployment tool that makes AI servers truly "plug-and-play".

A modern CLI tool for generating production-ready Model Context Protocol (MCP) servers

Deploy intelligence. Open-source infrastructure for AI agents in production.

Semester Project WS 2017/2018 - A chrome extension for twitch and a python-flask backend to analyse the emotion of streamers to find which one are raging.

Ollama toCloud 是一个第三方Ollama服务器 & 云端模型协议转换器

The AI Application Server: Websites have web servers. APIs have application servers. Agents finally have their own.

Run Hermes Agent autonomously on your Linux server using systemd and native cron scheduler. Production-ready, headless setup with Nous Portal integration.

HomeServer Automation Script ⚡ Build your own home server in minutes! Automated deployment and configuration for Docker, CasaOS, Jellyfin, Immich, Ollama, n8n, and Tailscale. One-command script to transform any Linux machine into a powerful self-hosted home server.

GPU-ready FastAPI AI inference server with plugin system, supporting CUDA, ROCm, CPU, and macOS MPS.

AI server for the FolioFusion portfolio builder web app

AWS_AI_Cloudflare_workshop, Kaosiung 20240606

LLM FOR OpenVINO 多模型管理伺服器 (for Intel NPU/GPU)

Server for Thunderbird AI Compose Extension

GPU-Ready FastAPI AI Inference Server with plugin system (CUDA/CPU/MPS/ROCm)

Deploy and run Hermes Agent autonomously on Linux servers using systemd and native cron for stable, headless AI task scheduling.