MAD (Multi-Agents-Debate) is an open-source framework exploring the collective debating capabilities of LLMs. It addresses the 'Degeneration of Thoughts' (DoT) issue—where self-reflection leads to biased or rigid outputs—by implementing a tit-for-tat interaction between multiple agents. By assigning roles like 'devil' and 'angel' to provide mutual external feedback, MAD corrects distorted thinking and breaks cognitive rigidity. It achieves significant performance gains in Counterintuitive QA and Commonsense Machine Translation tasks.
prompts.chat is the world's largest open-source AI prompt library, offering a curated collection of prompt examples for various AI chat models like ChatGPT, Claude, Gemini, and more. It provides an online platform for browsing and contributing prompts, along with interactive learning resources for prompt engineering and a game-based adventure for kids. The platform also supports self-hosting and various integrations including a CLI and Claude Code Plugin.
Dify is an open-source, production-ready LLM application development platform engineered to significantly accelerate the entire development cycle from prototype to production. It offers an intuitive visual workflow canvas, integrating a powerful Retrieval Augmented Generation (RAG) pipeline for efficient document ingestion and retrieval. Dify also features advanced agent capabilities based on LLM Function Calling or ReAct, configurable with pre-built or custom tools. It provides comprehensive support for hundreds of mainstream proprietary and open-source LLMs, a robust Prompt IDE for prompt engineering and model performance comparison, and built-in observability features (e.g., Opik, Langfuse, Arize Phoenix). This empowers developers to rapidly build, deploy, and monitor complex AI applications and agents.