Havuz

TokenSpeed, agentic workloads için LLM inference sunumunu hızlandırmayı ve istek yönetimini daha güvenli hale getirmeyi amaçlayan bir inference engine’dir.

Neden yükseliyor · 144 günde 2.178 yıldız ve son 28 günde 385 commit ile 20 farklı yazar, hem ilgi hem de yakın dönem geliştirme faaliyeti gösteriyor. README ayrıca PyTorch Ecosystem’e katılımı ve yeni model desteğini vurguluyor; performans iddiaları ise proje tarafından sunulan kıyaslamalara dayanıyor.

Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU

Go AI SDK, the Go way. One unified API across 21+ providers. Streaming, structured output, MCP support, stdlib only. Go AI SDK for AI appli

Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

Multi-agent AI pipeline that turns one line of text into a finished short-form drama: script, cinematic storyboards, character-consistent vi

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,

dsh游戏素材大师插件。接入seedream生图模型和minimax视频生成模型，可生成各种游戏素材。

Open-source AI pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with

AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable deliv

Long Horizon Terminal Benchmark with Dense Reward Grading

ChengOS is a visual AI data processing and agent workflow system. This directory contains deployment scripts, infrastructure configs, and ru

Suno-style web UI for a self-hosted MiniMax-Music3 inference server

Локальная студия генерации кинематографичных видео со звуком на MiniMax H3 — Windows, NVIDIA GPU, полностью offline.

Open-source local implementation of MiniMax H3 Context-IR. Turn simple prompts into structured, validated H3 video briefs.

Reference-first Codex workflow for edit planning, keyframe approval, and MiniMax H3 prompts.

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 scatt

A native Rust CLI for orchestrating AI agents across projects, with persistent sessions, worktrees, and local-first control.

Your smart, reliable, and friendly personal AI assistant.

助力搭建你的数字 AI 员工军团 — 多 Agent 一行命令组网协作。Claude Code / Claude Agent SDK / Codex / Grok Build 4 runtime + 8+ 家 LLM（Anthropic / OpenAI / xAI / Mini

Litefuse - Agent Observability and Evaluation Platform

MCore-Bridge: Providing Megatron-Core model definitions for state-of-the-art large models and making Megatron training as simple as Transfor

🐹OFFICE ZOO · 班味剧场 — 让 9 名 AI 鼠人替你狠狠去下班味精神倍增!AI 自演的职场狼人杀模拟器,3 种玩法 / 真人 TTS / 可玩可学的劳动法闯关

Complete Production Environment for professional MiniMax Music 3 audio generation, including Prompt Generation, Metadata generation includin

Illusion-Agent: Where fantasy meets functionality — an AI agent platform for terminal, browser, any model, any OS.

AI-powered screen recording with auto-captions, smart trimming, narration, and one-click professional output. Free and open source.

Inference engine for large language models on consumer GPUs, with deep optimization for older hardware

One-click knowledge system for documents, internal bots, and AI agents

Open-source AI coding agent. Desktop app, bring your own model. Writes code, browses the web, verifies its work. Apache 2.0.

ComfyUI nodes for MiniMax-H3 multi-segment video: seamless continuation via a latent bridge (previous segment's AV latent pinned into the ne

AI求职操作系统 — 岗位采集→10维评分→定制简历(LaTeX PDF)→面试资料生成→投递指南，一条龙服务

A browser-native Tic-Tac-Toe game with configurable minimax AI, local statistics, replay sharing, themes, and responsive UI.

Any Model for VS Code Copilot

MiniMax H3 video + Qwen Image 2.1. Native

A unified Model Context Protocol server for MiniMax CLI (mmx)

让 Codex 白嫖 NVIDIA 免费顶级模型，一键接入 | Transparent proxy between Codex and NVIDIA NIM — use NVIDIA's free hosted top-tier models with Codex

Production-grade screenplay studio: converts bullet points & images into strict single-line, timecoded video prompts for MiniMax H3, Maestro

Stream Deck plugin to monitor AI coding usage limits and reset times for Claude, Codex, Antigravity, Gemini CLI, and MiniMax, right on your

A local AI film studio for one Windows PC with an 8 GB NVIDIA card. Write the story, cast the people and render the shots with LTX-2.5, Mini

AI 短剧生成平台｜AI Short-Drama Video Generator — 从剧本到成片一站式生产：LLM 剧本解析、智能分镜、@引用提示词、多模型视频生成（MiniMax-H3 r2va 多模态参考）、React-Flow 节点画布、剪映式三轨道在线剪辑、团队协作与积

MiniMax H3 视频提示词生成 skill（纯文档型）

Jev RAG (Jev-RAG / JevRAG): open-source local knowledge search with BM25 + Jev reranking, agentic and hybrid retrieval, cited answers, and r

Local web UI for h3.c — native Metal video/audio generation with MiniMax-H3 on Apple Silicon, no PyTorch or MLX required.

Use third-party and Chinese model APIs as bounded Codex subagents while keeping Codex as the main agent.

无需 VS Code 的 Sentaurus TCAD 远程桥接｜Editor-independent SSH + MCP bridge for Sentaurus TCAD. Codex, CodeBuddy, MiniMax, Kimi Code & DeepSeek Har

Official MCP server for OrcaRouter — the LLM gateway with auto-routing and fallback chains. Browse models and chat from Claude Desktop, Curs

Generate videos with sound using MiniMax H3 inside Stable Diffusion WebUI Forge Neo: text to video, first/last frame, reference pictures, vi

Bilingual community prompting Skill for MiniMax H3 / 海螺 H3

Restores reasoning content dropped from multi-turn OpenCode conversations (DeepSeek, Kimi, GLM, MiMo, MiniMax, InclusionAI/Ling, OpenRouter)

AI reasoning skills distilled from 4,665 real Claude Fable 5 chain-of-thought traces. Mathematically tuned. Grade A (100%) emulation accurac

一个工具 = MiniMax 全部多模态能力：DSH 纯文本模型看图/画图/生视频/说话/唱歌/翻唱/搜索/查额度 | One mmx_bridge tool = all MiniMax multimodal (VLM/image/video/speech/music/cover