The Great Hall

A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows.

Specialised AI models for logo design — a brand-analysis model turns a business into constraints, typography and symbol models construct the mark, and a composition engine produces real lockups and clear-space rules. Early access open.

Global edition of ARTEX — an LLM multi-agent autonomous penetration-testing framework. English default, switchable to Korean/Chinese/Spanish/Japanese. For authorized, defensive and detection use only. (upstream: Autumn-27/ARTEX, AGPL-3.0)

120 marketing skills as an AI marketing staff — plugin, portable skills, or an 8-bot team across 7 disciplines (narrative, SEO/GEO, social, email, paid, influencer, launch) on one contract, with 8 auditor gates: TALE · CORE-EEAT · CITE · ECHO · SEND · ROAS · STAR · RAMP.

Plugin for JADX to integrate MCP server

Vuesion is a boilerplate that empowers product teams to build faster with modern best practices across engineering and design. It features a full-stack framework, comprehensive design system, robust testing, and seamless internationalization.

Run GLM-5.3 (744B), GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- and Anthropic-compatible API.

3x faster speeds on MLX | Qwen 3.8 27B | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.

BlackBox is a virtual engine, it can clone and run virtual application on Android, users don't have to install APK file to run the application on devices. BlackBox control all virtual applications, so you can do anything you want by using BlackBox.

Render Anything Engine: tell your AI what to make. Videos, motion graphics, 3D and games as React and TypeScript, rendered on your own GPU. Rust + Bevy, macOS, Linux and Windows.

FIT: 企业级AI开发框架，提供多语言函数引擎（FIT）、流式编排引擎（WaterFlow）及Java生态的LangChain替代方案（FEL）。原生/Spring双模运行，支持插件热插拔与智能聚散部署，无缝统一大模型与业务系统。

基于 REA 深度拆解并高保真还原 Claude 官方桌面端 UI。还原 30 个独立 React 组件与 8 项硬核交互物理算法，附带 3000+ 行逆向分析手册。

Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.

Reason Network: your team's coding agents, talking to each other. The engine behind `reason network`.

Local Laya typed decisions on Apple Core ML and Neural Engine. Validated ports, ~5 ms short decisions on M3 Max, reproducible speed and energy benchmarks.

A Claude Code skill that reverse-engineers any animation frame by frame, then proves the copy moves the same.

The open LLM inference engine for AWS Trainium: NKI megakernels, 1M-token context, OpenAI-compatible API. By RunAnywhere.