# open source

DeepSeek R1-0528 is the latest version released by the well-known open-source large model platform DeepSeek, which has high-performance natural language processing and programming capabilities. Its release has attracted widespread attention due to its excellent performance in programming tasks, enabling it to accurately answer complex questions. The model supports various application scenarios and is an important tool for developers and AI researchers. It is expected that more detailed model information and user guides will be released subsequently to enhance its functionality and applicability.

Unmute is an innovative tool for speech recognition and synthesis, designed to enable users to interact efficiently with AI through natural language. Its low-latency technology ensures a smooth user experience, suitable for scenarios requiring real-time feedback. The product will be released as open source to promote participation from more developers and users. The price has not yet been announced and is expected to adopt a combined free and paid model.

DMind-1 and DMind-1-mini are domain-specific large language models for Web3 tasks, providing higher domain accuracy, instruction-following capability, and professional understanding than other general models. DMind-1 has been fine-tuned with expert-curated Web3 data and aligned through reinforcement learning and human feedback, making it suitable for complex instructions and multi-turn dialogues, applicable in areas such as blockchain, DeFi, and smart contracts. DMind-1-mini, as a lighter version, aims to meet real-time and resource-efficient application scenarios, particularly for proxy deployment and chain tools. Product pricing and specific information require further confirmation.

OpenMemory is an open-source personal memory layer that provides private, portable memory management for large language models (LLMs). It ensures users have full control over their data, maintaining its security when building AI applications. This project supports Docker, Python, and Node.js, making it suitable for developers seeking personalized AI experiences. OpenMemory is particularly suited for users who wish to use AI without revealing personal information.

AgentCPM-GUI is an open-source mobile large language model (LLM) agent designed to operate on Chinese and English applications, capable of automatically executing tasks based on user screen captures. Its main advantages lie in efficient GUI element understanding, enhanced reasoning ability, and precise support for Chinese applications. The development background of this technology is to enhance the user experience of intelligent agents on mobile devices, especially in handling complex tasks. This product is positioned to improve productivity on mobile devices and is suitable for all types of users.

DeepSeek-R1-Distill-Llama-8B is a high-performance language model developed by the DeepSeek team, based on the Llama architecture and optimized through reinforcement learning and distillation techniques. This model excels in reasoning, code generation, and multilingual tasks, and is the first model in the open-source community to enhance inference capabilities through pure reinforcement learning. It supports commercial use, allows modifications and derivative works, making it suitable for academic research and enterprise applications.

Audiblez is a tool that leverages Kokoro's high-quality speech synthesis technology to convert standard eBooks (in .epub format) into .m4b format audiobooks. It supports multiple languages and voices, allowing users to complete the conversion through simple command-line operations, greatly enriching the eBook reading experience, especially in situations where reading isn't convenient, such as while driving or exercising. This tool was developed by Claudio Santini in 2025 and is open-source under the MIT License.

An open-source npm library that offers free usage of Llama 3.2 Vision for OCR, supporting both local and remote images, with plans to support PDF files. Inspired by Zerox, it provides both free and paid interfaces.

JavaVision is a comprehensive visual intelligent recognition project based on Java development. It not only achieves core functions such as PaddleOCR-V4 text recognition, YoloV8 object recognition, face recognition, and image search by image, but also can easily expand to other fields such as voice recognition, animal recognition, and security checks. The features of the project include the use of the SpringBoot framework, multifunctionality, high performance, reliability, easy integration, and flexibility. JavaVision aims to provide Java developers with a comprehensive visual intelligent recognition solution, allowing them to build advanced, reliable, and easily integrated AI applications with the familiar and beloved programming language.