The WeChat Reading MCP Server is a lightweight server that bridges WeChat Reading data and Claude Desktop, aiming to achieve in-depth interaction between reading notes and AI. This product utilizes the MCP protocol to seamlessly integrate reading data, providing real-time access and significantly improving users' reading efficiency and information management capabilities.

Search-R1 is a reinforcement learning framework designed to train large language models (LLMs) capable of reasoning and calling search engines. Built upon veRL, it supports various reinforcement learning methods and different LLM architectures, enabling efficiency and scalability in tool-augmented reasoning research and development.

LeoMoon Wiki-Go is a fast, modern flat-file Wiki built using Go. It focuses on simplicity and performance, supports Markdown formatting, is completely database-free, and requires zero maintenance. Suitable for personal knowledge management, team collaboration, and internal documentation.

Arthur Engine is a tool designed to monitor and govern AI/ML workloads, leveraging popular open-source technologies and frameworks. The enterprise version of this product offers enhanced performance and additional features such as customized enterprise-grade safeguards and metrics, aiming to maximize AI's potential for organizations. It effectively evaluates and optimizes models, ensuring data security and compliance.

Factorio Learning Environment (FLE) is a novel framework built on the game Factorio, used to evaluate the capabilities of large language models (LLMs) in long-term planning, program synthesis, and resource optimization. As LLMs gradually saturate existing benchmark tests, FLE provides a new open-ended evaluation approach. Its importance lies in enabling researchers to gain a more comprehensive and in-depth understanding of the strengths and weaknesses of LLMs. Key advantages include open-ended challenges with exponentially increasing difficulty, and two evaluation protocols: structured tasks and open-ended tasks. This project was developed by Jack Hopkins et al., released as open source, free to use, and aims to promote research by AI researchers on the capabilities of agents in complex, open-ended domains.

Light-R1 is an open-source project developed by Qihoo360, aiming to train long-chain reasoning models through curriculum-style supervised fine-tuning (SFT), direct preference optimization (DPO), and reinforcement learning (RL). This project achieves long-chain reasoning capabilities from scratch through decontaminated datasets and efficient training methods. Its main advantages include open-source training data, low-cost training, and excellent performance in mathematical reasoning. The project background is based on the current training needs of long-chain reasoning models, aiming to provide a transparent and reproducible training method. The project is currently free and open-source, suitable for research institutions and developers.

Awesome-LLM-Post-training is a repository focusing on large language model (LLM) post-training methods. It provides in-depth research on LLM post-training, including tutorials, surveys, and guides. This repository is based on the paper "LLM Post-Training: A Deep Dive into Reasoning Large Language Models" and aims to help researchers and developers better understand and apply LLM post-training techniques. This repository is freely available and suitable for both academic research and industrial applications.

Flux is a high-performance communication overlap library developed by ByteDance, designed for tensor and expert parallelism on GPUs. Through efficient kernels and compatibility with PyTorch, it supports various parallelization strategies and is suitable for large-scale model training and inference. Flux's main advantages include high performance, ease of integration, and support for multiple NVIDIA GPU architectures. It excels in large-scale distributed training, particularly with Mixture-of-Experts (MoE) models, significantly improving computational efficiency.

Atom of Thoughts (AoT) is a novel reasoning framework that transforms the reasoning process into a Markov process by representing solutions as a combination of atomic problems. This framework significantly improves the performance of large language models on reasoning tasks through decomposition and contraction mechanisms, while reducing wasted computing resources. AoT can be used as an independent reasoning method or as a plugin for existing test-time augmentation methods, flexibly combining the advantages of different methods. This framework is open-source and implemented in Python, making it suitable for researchers and developers to experiment with and apply in the fields of natural language processing and large language models.

HoverNotes is a tool that converts videos into local Obsidian notes. It captures code snippets, charts, and visual elements, generating structured markdown notes with screenshots, closely integrating with Obsidian.

Docaroo is an intelligent document management tool that helps users organize, access, and protect digital documents through AI technology. Its secure cloud storage and intelligent reminder functions make it easier for users to manage important files.

SigmaNote is an AI memory tool that can convert various files, links into editable AI notes, helping users search, communicate and organize information anytime, anywhere. Its AI technology provides fast conversion, intelligent editing and convenient chat functions to improve work efficiency.

TeraBox is a platform that offers 1TB of free cloud storage and online file transfer services. It provides professional solutions for papers and online presentations through advanced algorithms and natural language processing technologies, improving work and study efficiency. The product targets individual users and small teams, offering 1TB of free cloud storage space.

ScatterNote is a tool that transforms scattered ideas into structured documents. It leverages AI technology to help users quickly capture and organize their ideas, improving work efficiency and organizational skills.

The WeChat Reading MCP Server is a lightweight server that bridges WeChat Reading data and Claude Desktop, aiming to achieve in-depth interaction between reading notes and AI. This product utilizes the MCP protocol to seamlessly integrate reading data, providing real-time access and significantly improving users' reading efficiency and information management capabilities.

Search-R1 is a reinforcement learning framework designed to train large language models (LLMs) capable of reasoning and calling search engines. Built upon veRL, it supports various reinforcement learning methods and different LLM architectures, enabling efficiency and scalability in tool-augmented reasoning research and development.

LeoMoon Wiki-Go is a fast, modern flat-file Wiki built using Go. It focuses on simplicity and performance, supports Markdown formatting, is completely database-free, and requires zero maintenance. Suitable for personal knowledge management, team collaboration, and internal documentation.

Supermemory MCP is a personal general-purpose memory platform designed to help users access and store their memory information anytime, anywhere. It supports access through different clients, allowing users to easily add and manage memories. This product emphasizes portability and privacy protection, making it suitable for a variety of user groups. It is free to use.