Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

SGLang is a high-performance serving framework for large language models and multimodal models.

OpenGL Mathematics (GLM)

GLM-OCR: Accurate × Fast × Comprehensive

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

Costrict - strict AI coder for enterprises, quality first, including AI Agent, AI CodeReview, AI Completion.

仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理

Command Code AI

和国产大模型相关的免费工具集

TokenSpeed is a speed-of-light LLM inference engine.

Custom nodes that extend the capabilities of Comfyui

A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.

Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere

Open Source Continuous Inference Benchmark Research Platform — Kimi K2.7-Code, MiniMax M3, DeepSeekv4, GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 & soon™ TPUv6e/v7/Trainium2/3 | 开源持续推理基准研究平台 — Kimi K2.7-Code、MiniMax M3、DeepSeekv4、GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72，即将推出™ TPUv6e/v7/Trainium2/3

An open-sourced end-to-end VLM-based GUI Agent

Unvanquished is a free and open source FPS/RTS hybrid game powered by the Daemon game engine. Historically based on Tremulous as a continuation with decades of work over it.

♾️ 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 ♾️