StructAI offers a robust toolkit for LLM interaction—such as structured outputs, context management, and parallel execution.

中文高压复杂任务Benchmark。主要是测模型会不会在真实工作里误事。This is a Chinese-language high-pressure complex task benchmark. The main purpose is to test whether the model will cause problems in real-world applications.

Tron-style multiplayer light-cycle game for LLMs via MCP

Offline LLM evaluation pipeline for Kazakh: run local HF models, auto-judge, export JSON for the Arena leaderboard: https://huggingface.co/spaces/kz-transformers/kaz-offline-arena

Open Cyber LLM Arena | A transparent, crowdsourced benchmarking platform for evaluating Large Language Models (LLMs) on cybersecurity tasks.

Run several LLM agents on the same task in parallel docker sandboxes, then have other LLMs judge them. Uses your Claude Pro / ChatGPT Plus / Gemini Advanced subscriptions — no API keys.

Open-source mirror of 4 flagship MAYA AI Hugging Face Spaces (all-leaderboard, QWEN-3_5-CHAT, openclaw-moltbot, fish-s2-pro-zero) ? each folder is a deployable Space

A AI comparison chatroom base on AI-web,NOT API. Send one message, get simultaneous responses from ChatGPT, DeepSeek, Gemini, GLM and more. Local-first, FREE,saves conversations as Markdown files.一款跨平台 AI 对比聊天室，自动且免费操作AI网页，不使用API。一次发送，获取多个AI平台输出

Generate side-by-side LLM coding battle videos with your own API keys — free, local, open source.

Cortex is a hyper-efficient, local, multi-model AI reasoning engine with support for RAG, Tree of Thought, Arena mode, and persistent memory.