A Next-Generation Training Engine Built for Ultra-Large MoE Models

🔍大模型应用开发实战一：RAG 技术全栈指南，在线阅读地址：https://datawhalechina.github.io/all-in-rag/

和国产大模型相关的免费工具集

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

Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

Extracted artifacts from Kimi OK-Computer (and other agents) system for AI studies in agentic architecture.

vibecheck is a lightweight, cross-platform command line AI-tool that automatically generates meaningful and consistent Git Commit Messages by analyzing your code changes — ship faster with vibecheck

An adaptive multi-agent system that extracts your literary DNA through conversation and generates actionable reading profiles.

大模型API网关-全新AI大模型接口管理与API聚合分发系统 , 支持将多种大模型转换成统一的OpenAI兼容接口,Claude接口,Gemini接口，可供个人或者企业内部大模型API 统一管理和渠道分发使用(key管理与二次分发)，支持国际国内所有主流大模型，gemini,claude,qwen3,kimi-k2,豆包等，提供单可执行文件， docker镜像，一键部署，开箱即用，完全开源，自主可控！本项目基于New-API和One-API，整合了NewAPI,OneAPI所有功能及众多第三方插件为一身，功能超强！

Chat2API enables zero-cost access to leading AI models by leveraging official web UIs. It supports providers such as DeepSeek, GLM, Kimi, MiniMax, Qwen, and Z.ai, and seamlessly integrates with tools like openlcaw, Cline, and Roo-Code.

⚡️ Blazing fast LLMs API Gateway written in Go

Auto-review and iterate until quality work is delivered - a better alternative to ralph-claude-code. Switch between multiple Claude Code providers (Kimi, GLM, MiniMax, etc.) with a single command.

GPT-5.3-powered multi-model Discord bot to interact with powerful LLMs and explore capabilities. This repo also serves as reference implementation how AI agents are hosted

Adaptive Reasoning Engine for Efficient and Context-Aware Intelligence

vue3 + AI Skills实现的aippt项目

MCP server for Claude Code × Kimi K2.5 (256K context) — delegate bulk codebase analysis to Kimi, save 90% on token costs. Session caching, parallel agents, TypeScript.

Documents the style side of the short-story Creative Writing LLM benchmark: we generated many short stories with a range of LLMs, then analyzed those stories for stylistic fingerprints and within-model diversity. This study focuses on how models write, how their outputs differ, and how varied each model is across its own stories.

让 GLM-4.5 完美适配 Agent TARS 系统的高性能适配器 - 解决 toolcall 兼容性，提供智能 fallback，极低成本享受顶级 AI Agent 体验

Complete guide and pricing comparison for using alternative AI models with Claude Code - including DeepSeek, Qwen, Kimi K2, MiniMax, and GLM 4.6

When a model translates out of English and then back to English, how much meaning and voice does it keep? Each model does both steps (English → target language → English).