sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
- 39k
- Python
- Apache-2.0
- 19 min ago
SGLang is a high-performance serving framework for large language models and multimodal models.
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.
Costrict - strict AI coder for enterprises, quality first, including AI Agent, AI CodeReview, AI Completion.
Run GLM-5.3 (744B), DeepSeek-V4.1-Flash (748B), MiniMax-M3.1-Flash (428B), GLM-5.3-Flash (321B) and Hy4-Flash (220B) on your own GPUs - from 8 GB of VRAM, NVIDIA and AMD, one dashboard, OpenAI- and Anthropic-compatible API.
A minimal yet professional single agent demo project that showcases the core execution pipeline and production-grade features of agents.
🎬 Evidence-led Seedance 2.5 / 2.0 prompt library: 1000+ cases traced to original posts, 490+ cross-model retest runs, 27 copy-ready templates, 80+ installable AI-video Skills. Synced daily from goodcase.ai. EN / 中文 / 日本語.
An open-source coding agent for your terminal, powered by MiniMax.
AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax.
[GenAI Application Development Framework] 🚀 Build GenAI application quick and easy 💬 Easy to interact with GenAI agent in code using structure data and chained-calls syntax 🧩 Use Event-Driven Flow *TriggerFlow* to manage complex GenAI working logic 🔀 Switch to any model without rewrite application code
Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere
Clip chaining for MiniMax H3 in ComfyUI - motion and audio genuinely continue across joins
Fizgig — LoRA & Fine-tune Studio for Klein 9B, Krea 2, MiniMax H3, Qwen Image 2.1, Anima & Z-Image Turbo and Ace-Step XL: train, fine-tune, profile, repair and extract LoRAs & LoKR for Image, Video & Music Models
A browser-based desktop where AI Agent operates every app through natural language.
Multi-agent AI pipeline that turns one line of text into a finished short-form drama: script, cinematic storyboards, character-consistent video. Provider-agnostic (OpenAI/Claude, MJ, Minimax, Veo/Sora, fal, ComfyUI). MIT.
让最新版 OpenAI Codex CLI / Codex 桌面端接入主流大模型的本地代理(新增mac/win包支持,后台运行,开机自动重启)。内置 小米 MiMo V2.5/DeepSeek V4 Pro,并提供通用 provider 机制,**OpenAI Chat Completions 兼容**(Qwen / GLM / Kimi / 本地 vLLM / Ollama / LM Studio …)或**原生 Responses API**(OpenAI 自家)的上游接到新版 Codex。把 Codex 的 Responses API 实时翻译成上游的 Chat Completions API,按客户端发的 `model` 字段在 provider 之间自动路由.
A Collection of Google Colab Notebooks for various projects
Native macOS app for local AI video on Apple Silicon — LTX-2, LTX-2.3, LTX-2.5, and MiniMax H3
A timeline editor for MiniMax H3 inside ComfyUI - storyboard prompts, first/last keyframes, image/video/audio references, joint audio, live sampling preview, retakes and shot chaining.
本地运行的大模型聚合网关,GUI桌面端app,零代码部署,把Coding Plan、大模型 API 额度聚合成一个虚拟 Plan,一键接入 Claude Code、Claude Desktop App、OpenClaw、OpenCode 等工具。Bundle your scattered Token Plan, Coding Plan, and LLM API quotas into a single virtual Plan, and plug it into Claude Code, Claude Desktop App, OpenClaw, OpenCode, and more.
Akcio is a demonstration project for Retrieval Augmented Generation (RAG). It leverages the power of LLM to generate responses and uses vector databases to fetch relevant documents to enhance the quality and relevance of the output.
古人说唱 Battle:一句话做一期 AI 历史人物说唱对决视频的 Claude Code Skill(Suno + Midjourney + MiniMax H3 对口型)
Go AI SDK, the Go way. One unified API across 21+ providers. Streaming, structured output, MCP support, stdlib only. Go AI SDK for AI applications inspired by Vercel AI SDK.
AI 短剧生产总控 / 短剧skill:专业导演与分镜、MiniMax H3、CompShare、声音资产、粗剪与 QC,默认 16:9。
A native (really fast!!) cross-platform client for OpenCode. Codewalk V2 is now OPEN BETA as "pre-release" on gh. It's fast, and usable, but needs some UI. 2027 only.
ComfyUI long-video controller for MiniMax H3 Ref2VA singing and speaking workflows
Complete TypeScript chess engine with zero dependencies for Node.js >=24 and browsers. Features configurable AI (5 predefined difficulty levels), stateful/stateless APIs, and supports JSON and FEN formats.
Direct MiniMax H3 like a pro: Idea in, finished video out. A complete MiniMax H3 studio that lives in your ComfyUI.
Turbo & FlashGen 4-step video/audio + P-H3 image studio
Runs in the browser on Hugging Face
MiniMax H3 video prompts via CPU GGUF
Runs in the browser on Hugging Face
MiniMax H3 prompts · LFM2.5-2.6B · ZeroGPU llama.cpp
Runs in the browser on Hugging Face
2026 models under load - 1, 25 and 100 concurrent users
Runs in the browser on Hugging Face
Weekly archive - 2026 models at 1, 25 and 100 users
Runs in the browser on Hugging Face
Online playground for MiniMax-Music3 text-to-music
Runs in the browser on Hugging Face