#open source

AppFlowy is an open-source Notion alternative focused on data security and AI tools. It supports macOS, Windows, Linux, iOS, and Android, offering customizable tools for individuals and enterprises to create secure, cross-platform environments. Join the community driving workspace innovation.

LLM Guard is a security toolkit designed to protect large language model interactions by detecting harmful language, preventing data leaks, and resisting prompt injections. It offers seamless integration into production settings and provides regularly updated features. A variety of input and output scanners enhance its versatility in safeguarding LLM systems.

Access the Chinese version of 'Machine Learning Yearning' online to gain insights into machine learning practices. Contributions to translation quality are encouraged via discussions and suggestions. The draft is available for non-commercial use under the CC BY-NC-SA 4.0 license, permitting free distribution and adaptation with proper attribution.

Explore a language model with 1.9 billion parameters and 32K context support, designed for efficient long-document processing. It excels in multilingual translation, particularly in East Asian languages, and offers role-playing capabilities. Recent updates include adaptations for llamacpp and Ollama, with open-source checkpoints available. Evaluation results demonstrate its competitiveness with larger models, making it ideal for chat, translation, and fine-tuning applications.

MindForger serves as a personal knowledge management tool tailored for those dealing with vast and scattered information. The tool includes a privacy-oriented Markdown editor that aids in managing a variety of personal insights, including ideas and strategies. It features an outliner, spell-check, and a knowledge graph navigator, along with support for diagrams and tables, which facilitates the efficient organization of thoughts. MindForger is accessible for multiple platforms like macOS, Windows, and Linux, offering customization options that enhance its functionality and maintain information integrity.

OpenFace is an open-source project providing face recognition capabilities via deep neural networks. It serves as a comprehensive platform for image processing, real-time web demonstration, image comparison, and classifier training. Supported by research and tech industry contributions, the project promotes academic and development dialogues. OpenFace offers valuable Python libraries and models for mobile app development and performance assessment, serving as a resourceful tool for both developers and researchers.

Explore an open source medical language model utilizing diverse datasets and efficient deployment methods. Features include ChatGPT fine-tuning, Gradio deployment, and LLaMA model support, integrating AI techniques with comprehensive medical knowledge. Access tools for GPT-4/ChatGPT model distillation, benefiting from resources for constructing medical knowledge bases. Ideal for developers and researchers, the platform provides extensive data on over 60 medical departments and performs well on benchmarks such as CMB-IvyGPT. Engage with advanced medical AI through downloadable models and online interaction.

WPPConnect is an open-source project that exports WhatsApp Web functions to Node.js, enabling applications in customer service, media management, and phrase recognition. It supports sending text, images, and videos and offers features like automatic QR refresh and multiple sessions management, facilitating interaction without requiring frequent code updates. As a community-supported project, it invites contributions for ongoing development.

Discover an open-source platform that effortlessly integrates digital and language models. Designed for flexibility, it supports offline use and rapid response, with applications spanning microcontrollers, apps, and websites. Key features include automatic broadcast mode, multi-user support, and customizable voice commands. Optimize diverse environments with server and standalone modes tailored for home devices and large systems alike.

This project aims to build an open-source financial model using AI for more efficient analysis of financial data. It emphasizes simplifying the interpretation of financial reports by offering tools that deliver expert-level insights. The project focuses on using community-driven improvements and comprehensive datasets to refine its analytical capabilities. Resources such as tutorials and model fine-tuning are available to foster learning and collaboration. Collaboration and sponsorship are welcome to further enhance the AI's application in financial reporting.

The Aquila2 series includes open-source language models like AquilaChat2, known for its advanced long-text processing, surpassing other models on various benchmarks. With options such as Aquila2-7B and Aquila2-34B, alongside the experimental Aquila2-70B-Expr, the project facilitates finetuning and quantization, accompanied by comprehensive deployment guides for platforms like Hugging Face and ModelHub. This project provides significant improvements in reasoning tasks and long-context comprehension, ideal for complex language application development, with regular updates promoting continuous progress.

ChainFury is an open-source engine empowering AI tools like Tune Chat and Tune Studio. It offers advanced capabilities such as Retrieval Augmented Generation (RAG), image generation, and secure data storage. The platform includes modular engine packages and a GUI server for easy deployment via Docker, allowing customization through environment variables. Extensive documentation and active community support on Discord assist in integration and development for production use.

This project offers access to enhanced Chinese LLaMA and Alpaca models, designed to improve language understanding and execution of instructional tasks. By integrating additional Chinese vocabulary, these models enhance semantic comprehension and decoding efficiency over the original LLaMA. Instruction tuning further refines Alpaca models' performance. The project includes pre-training tools and supports various platforms such as 🤗transformers and LlamaChat, facilitating seamless integration and deployment on personal systems. A range of models, including 7B, 13B, and 33B versions, are available to address diverse requirements.

LabelImg, an open source image annotation tool, is designed in Python with a Qt interface. It supports PASCAL VOC, YOLO, and CreateML formats, aiding machine learning through efficient image labeling. Despite LabelImg's development integration with Label Studio, it remains a fundamental tool for image annotation, available on PyPI for Python 3+. It includes features for annotation visualization, class pre-definition, and hotkey usage, and supports Docker deployments. Compatible with multiple platforms, it requires minimal setup with Python and PyQt.

Label Studio is an open-source tool simplifying data labeling for audio, text, images, videos, and more. It provides multi-user collaboration and project management, integrates with machine learning workflows via REST API and SDK, and supports data import from various sources, enhancing data accuracy through pre-labeling and active learning. Deployable locally or on the cloud, it supports Docker, pip, and Anaconda for flexible operations.

SillyTavern functions as a versatile platform for AI enthusiasts by providing a locally-installed interface to access LLM APIs like OpenAI, KoboldAI, and others. It includes a mobile-friendly design, Visual Novel Mode, and TTS features while offering enhanced prompt options. As an open-source, community-driven project, SillyTavern prioritizes user privacy with no data tracking. Its functionality extends through third-party extensions such as Automatic1111 & ComfyUI for image generation. With minimal hardware requirements, it supports both local and cloud-based LLMs, catering to a broad range of users.

The project delivers structured and clear tutorials with optimized code for TensorFlow, assisting both novices and seasoned developers in mastering complex deep learning tasks. The repository supplies source code and documentation that clarifies model complexities, fostering an expanding community through tutorials from fundamental operations to sophisticated neural networks, all designed to enhance effective TensorFlow use.

PaddlePaddle's extensive library, featuring over 600 official and 260 ecosystem models, supports sectors such as energy, finance, and agriculture by providing tailored solutions for semantic tasks and rapid integrations. Regular updates cater to evolving industry demands and significant academic advancements, ensuring optimal performance with PaddlePaddle's core framework.

Chinese Llama 2 7B offers an open-source version of the LLaMA2 model, fully commercializable and featuring bilingual text-to-speech and text-to-vision datasets. Optimized for LLaMA-2-chat integration, it supports advanced multimodal applications. Regular updates provide new model resources, quantized versions, GGML models, and deployment solutions like Docker and API. Resources are accessible on HuggingFace, Baidu, and Colab for both CPU and GPU users.

GPT4All offers a seamless solution for using large language models (LLMs) on personal computers without APIs or GPUs. It supports Windows, macOS, and Linux, with detailed system requirements for performance optimization. Integration with Langchain, Weaviate, and OpenLIT enhances its functionality. Regular updates ensure a cutting-edge experience while promoting open-source collaboration for broad accessibility.

VoTT is an open-source resource designed for annotating and labeling image and video assets, perfect for machine learning workflows. This React and Redux-based web application, written in TypeScript, supports extensible models for importing and exporting data from local or cloud storage, enhancing project flexibility. It offers features such as image and video labeling, integration with Azure Blob Storage and local file systems, and exporting capabilities to formats like TensorFlow and CSV. Ideal for 'Bring Your Own Data' projects, VoTT simplifies the process of training machine learning models.

The AIdea-server, an open-source backend developed with Golang, integrates major language and image processing models such as OpenAI's GPT, Anthropic's Claude, and Google's Gemini Pro. It supports domestic models like Tongyi Qianwen and Baichuan 53B, as well as open-source alternatives like Yi 34B and Llama2. Features include text-to-image conversion, super-resolution, and artistic QR code creation. Available for private deployment, it provides options outside of cloud services. The server's modular development is streamlined by the self-developed Glacier and Eloquent ORM frameworks.

TensorFlow is a leading open-source framework for machine learning, recognized for its comprehensive suite of tools and libraries. Initially developed by Google Brain, it facilitates cutting-edge ML research and application development. With stable Python and C++ APIs, it supports multiple languages and offers diverse installation options, including GPU capabilities. Engage with the TensorFlow community for collaborative advancement in machine learning.

Explore an extensive directory of OpenAI GPT-related resources and applications. This project offers tools to enhance creativity and productivity with AI-driven solutions. Navigate through structured generators, intelligent assistants, and creative tools, and stay updated with the latest AI advancements. A collaborative platform to refine and expand your AI capabilities.

MTrans offers a lightweight, open-source solution for online translation and TTS services, supporting multiple languages such as Chinese, English, Japanese, Korean, and more. Developers can easily send HTTP requests to obtain and process translation results from providers like Baidu, Youdao, and Google. MTrans is ideal for secondary development and seamless integration into applications requiring diverse language support.

Discover a powerful open source alternative to Firebase, providing essential tools for developers. Features include a Hosted Postgres Database, authentication, real-time updates, and AI integration. Offers well-documented REST and GraphQL APIs and a modular library system for both hosted and self-hosted environments.

TiDB is an open-source SQL database designed for high availability and scalability, leveraging cloud-native solutions. It supports horizontal scaling through independent compute and storage operations and integrates smoothly with Kubernetes. The database ensures data integrity with ACID compliance via distributed transactions and MySQL compatibility for straightforward migrations without code overhauls. Its HTAP features use both row and columnar storage to maximize performance, accompanied by community-driven innovation.

Korvus is an open-source search SDK leveraging Postgres to merge RAG functionalities in a single query, supporting Python, JavaScript, and Rust. It incorporates LLMs, vector memory, and text generation, ensuring efficient, scalable search processes with minimal infrastructure, all while simplifying operations by eliminating external services or API requirements.

Rubix ML is a machine learning and deep learning library for PHP, offering over 40 algorithms in supervised and unsupervised learning. It facilitates complete ML lifecycle processes including ETL, preprocessing, and cross-validation. It is an open-source library, usable for commercial purposes. Requires PHP 7.4+, with optional extensions for additional functionality. Comprehensive tutorials and resources support integration into various projects. Community interaction is available via the Telegram channel.

OpenKore is a cross-platform, open-source bot designed for automating tasks in Ragnarok Online. It supports Linux, Windows, and macOS, providing users with easy setup via GitHub downloads or clones, and comprehensive guidance. OpenKore offers extensive resources like FAQs, forums, and community support for troubleshooting, while its customizable features cater to a global user base. Although some servers present limitations, OpenKore maintains its position as a popular tool for Ragnarok Online players, ensuring compliance with the GNU General Public License.

Pyro, developed on PyTorch, is a universal probabilistic programming library that supports scaling with minimal overhead. Designed for both automation and expert control, it provides composable abstractions for generative and inference models. Originally an Uber AI project, Pyro now thrives under the Linux Foundation, maintained by community and Broad Institute contributors, fostering open-source collaboration.

This project provides an extensive open-source resource focused on deep learning, combining theory with practical coding applications. It supports the translation of complex formulas into functional code, promoting experiential learning and collaboration within the community. Accessible online without cost, it ensures users remain informed on the rapidly advancing topics in deep learning. The platform includes forums, encouraging robust discussions for both individual learners and educational institutions, receiving notable support from academia and industry professionals.

The Krita plugin leverages cutting-edge generative AI to improve image creation and editing precision. By enabling image generation from text and refinement of existing designs, it offers flexible control through sketches and depth maps. The project supports open-source models for customization and local execution, with cloud options available for rapid setup. Its features, such as inpainting, live painting, and upscaling, enhance creative processes while maintaining high-quality outputs.

Based on the latest Meta Llama-3 model, this project provides an open-source platform for crafting high-efficiency Chinese language models. The releases feature the Llama-3-Chinese base and Llama-3-Chinese-Instruct models, extensively fine-tuned on Chinese dataset, boosting semantic and instruction processing. Key enhancements include a larger vocabulary, extended context length, and efficient group query attention. Users have the flexibility to train or fine-tune with provided scripts compatible with popular frameworks like transformers. Discover next-level Chinese NLP with these cutting-edge models.

Discover a versatile open-source voice assistant known for its extensive customization options and skill installations. Although Mycroft-core is no longer actively maintained, it is a customizable solution that paved the way for successors like Open Voice OS and Neon-core. Users can install skills from a community-driven repository and manage devices across different networks.

This open-source language model utilizes 2.6 trillion high-quality tokens to deliver top performance in Chinese, English, and multilingual benchmarks. With Baichuan2-13B-Chat v2, it excels in mathematical and logical reasoning. Available in 7B and 13B, both Base and Chat editions are offered for academic research and free commercial use upon official approval. Access detailed technical insights and download links for the latest versions.

Discover an extensive range of software and resources for the Stable Diffusion AI model, including GUIs, CLI installations, and maintained forks. This collection embraces official releases, complementary models, and training guides across various platforms, facilitating easy installation and operation. Enhancements like inpainting, outpainting, and task chaining are supported, with guidance on prompt building to fully leverage the model's capabilities.

PhaseLLM is an open-source framework that simplifies the integration and evaluation of large language models such as OpenAI's GPT-3.5, Anthropic's Claude, and Cohere. It offers standardized API interactions, evaluation tools, and automation to optimize model performance in applications like chatbots, with a focus on efficiency and cost-effectiveness for developers and data scientists.

gpt-engineer enables software development with natural language inputs, allowing AI to autonomously generate and enhance code. Compatible with Python 3.10 to 3.12, it supports local and alternative models such as WizardCoder. It integrates with popular datasets for agent benchmarking and offers seamless project creation and enhancement through prompts. The open-source community invites collaboration and supports non-technical users with a dedicated UI linked to a version-controlled codebase.

Explore an unofficial open-source Chat AI desktop app using Tauri and Rust for superior performance. This cross-platform application integrates smoothly with popular Chat AI services and provides API Key management through OpenAI, enhancing user customization. Prioritizing privacy, it ensures no data is transferred externally. Comprehensive setup guidance and troubleshooting tips are available, promising an optimal experience on all platforms, including menubar use. Perfect for users seeking a flexible and secure desktop AI chat solution.

MING is an open-source Chinese medical model that provides detailed answers for medical inquiries, featuring intelligent diagnostics. Developed by Shanghai Jiao Tong University, it supports diverse applications from 1.8B to 14B parameters, using state-aware simulations and decoupled clinical alignments. Just 15GB GPU is needed for straightforward setup and usage, ensuring smooth user interaction.

Discover the First Order Motion Model, a deep learning project focused on animating images by transferring motion from driving videos. This repository features example animations across datasets such as VoxCeleb and Fashion, along with step-by-step guides for installation, training, and evaluation. It includes tools for video editing and animation, with applications in face-swap and creative media.

AudioGPT is an open-source initiative providing tools for analyzing and creating speech, music, and other audio forms. The project supports tasks such as text-to-speech, style transfer, and speech recognition through models like FastSpeech and whisper. For audio manipulation, it includes tasks like text-to-audio and image-to-audio using models such as Make-An-Audio. It also offers talking head synthesis with GeneFace. As some features are being refined, AudioGPT continuously broadens its functionality for varied audio projects.

FiftyOne enhances machine learning by enabling efficient dataset visualization and error analysis, improving data quality and model accuracy. This open-source tool supports detailed exploration of data and the evaluation of computer vision models. Users can identify errors and optimize models with greater precision. Participate in its Slack community, read informative articles, and access tutorials to leverage its capabilities. For easy installation, use pip to access its comprehensive features.

Openv0 is a generative UI framework offering AI-powered design iterations and live previews. It leverages open-source libraries in a modular setup using independent plugin pipelines, supporting React, Next.js, Svelte, NextUI, and Shadcn. Openv0 facilitates the integration of new frameworks and plugins, with future updates including a public web app and improved validation. Discover demos and simple setup processes for a transformative UI design experience.

MediaPipe provides adaptable machine learning solutions for various platforms, including mobile, web, desktop, edge devices, and IoT. It features comprehensive libraries and resources such as ready-to-use models and cross-platform APIs for easy customization and deployment. With tools like MediaPipe Model Maker and MediaPipe Studio, developers can efficiently tailor and assess solutions. As an open-source initiative, it supports additional customization and community collaboration, facilitating artificial intelligence and machine learning integration into diverse applications.

ScreenPipe is an open-source tool that facilitates 24/7 screen and voice recording, essential for AI's evolving needs. Available as a CLI tool, a desktop app, and a Rust or WASM library, it supports Chinese and native OCR for Apple & Windows. Its plugin system enables sandboxed code execution, offering extensive customization. Regular updates and active community involvement ensure its continuous relevance.

Apache TVM, a robust open-source deep learning compiler stack, enhances the synergy between productivity-centric frameworks and performance-focused hardware. It delivers comprehensive end-to-end compilation for diverse platforms, optimizing deep learning efficiency. Licensed under Apache-2.0, TVM fosters community-based advancement and follows the Apache committer model. Extensive resources for installation, tutorials, and examples are available to assist users. Inspired by projects such as Halide, Loopy, and Theano, TVM creates a cohesive environment to facilitate integration and performance improvements for developers and hardware vendors alike.

Activepieces is a robust open source automation alternative to Zapier, designed for intuitive use with a TypeScript-based framework. It supports both developers and non-technical users in creating custom automation flows. The platform includes over 200 integrations with services like Google Sheets and Discord, promoting a strong community-driven ecosystem. Its features cater to enterprise requirements with secure, self-hosted deployments and native AI capabilities. Regular updates ensure the inclusion of the latest features for optimal automation processes.

Quaternion is a cross-platform desktop client designed to work with the Matrix protocol, providing extensive configuration options for a personalized user experience. Compatible with major operating systems including GNU/Linux, macOS, and Windows, Quaternion offers stable integration and tailored set-up through varied methods such as Flatpak and Homebrew. Utilizing Qt version 6.2 or higher, it addresses integration concerns across different Linux distributions. The software supports multiple languages and offers a robust configuration system aimed at enhancing user engagement. Although still in beta, Quaternion continues to support End-to-End Encryption (E2EE) and efficient caching for improved performance. Community-driven translations strive to ensure a wide-reaching applicability.