Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex, Gemini and open models on a full private AI Stack ♾️

Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton

企业级 LLM API 快速集成系统，支持OpenAI、Azure、文心一言、讯飞星火、通义千问、智谱GLM、Gemini、DeepSeek、Anthropic Claude以及OpenAI格式的模型等，简洁的页面风格，轻量高效且稳定，支持Docker一键部署。

企业级 LLM API 快速集成系统，支持OpenAI、Azure、文心一言、讯飞星火、通义千问、智谱GLM、Gemini、DeepSeek、Anthropic Claude以及OpenAI格式的模型等，简洁的页面风格，轻量高效且稳定，支持Docker一键部署。

企业级 LLM API 快速集成系统，支持OpenAI、Azure、文心一言、讯飞星火、通义千问、智谱GLM、Gemini、DeepSeek、Anthropic Claude以及OpenAI格式的模型等，简洁的页面风格，轻量高效且稳定，支持Docker一键部署。

A fully local, GPU-accelerated pipeline to automatically translate manga/comics. Features YOLO detection, MangaOCR, LLM translation (Qwen), and smart typesetting. No external APIs.

Golang based RAG service. Come Brew, build your second brain.

MindTrial: Evaluate and compare AI language models (LLMs) on text-based tasks with optional file/image attachments and tool use. Supports multiple providers (OpenAI, Google, Anthropic, DeepSeek, Mistral AI, xAI, Alibaba, Moonshot AI, OpenRouter), custom tasks in YAML, and HTML/CSV/JSON reports.

An AI agent based on the Ollama large model, capable of executing Linux commands through natural language and invoking kernel hooks to delve into the underlying system.

Production-ready AI for Kubernetes. Run cutting‑edge LLMs on NVIDIA GPUs with vLLM. Use Ollama for embeddings and vision. Access securely through OpenWebUI. Scalable, high‑performance, and fully self‑hosted.

AKasha Whisper提供了一个统一的、用户友好的 API，用于集成多个 AI 模型并与之交互

A high-performance Model Context Protocol (MCP) server. Enables AI Agents to fetch real-time GitHub repository data—including SemVer-sorted tags, file content, and directory trees—without local cloning. Solves the 'outdated dependency knowledge' problem for LLMs.

阿里云百炼大模型 Token 账单解析工具 | Alibaba Cloud Bailian LLM Token Billing Parser - Parse, analyze and summarize daily AI model token costs

AI-powered cryptocurrency trading system for Hyperliquid exchange with DeepSeek/Qwen AI models, technical indicators, and comprehensive risk management

A project named Vibecoding created to help HR understand that tools like Claude Code, OpenCode, pi.dev, and Cline all belong to the Vibecoding workflow paradigm.

阿里巴巴dashscope go语言版本的sdk

OpenAI Go SDK. small and simple but works well, easy to use

Local CLI agent for development powered by Ollama & OpenAI agents. Auto-fixes build/test/lint errors, supports MCP tools, RAG search, and rich TUI.

GoChat is a modern, enterprise-ready Go client SDK for Large Language Models (LLMs).