Coding & Development

Voice Agent WebRTC + LangGraph is a powerful AI tool developed by NVIDIA, designed for creating interactive voice agents. It leverages WebRTC for real-time communication, LangGraph for agent orchestration, Automatic Speech Recognition (ASR) to convert spoken language into text, and Text-to-Speech (TTS) to vocalize translated text. Users can speak into the application, and it processes their voice by converting it to text, translating it, and then speaking the translated text back. This eliminates the need for manual typing, offering a seamless and intuitive voice interaction experience. It's hosted on Hugging Face Spaces, making it accessible for developers and researchers to experiment with and build advanced voice applications.

ai-tishici is an open-source GitHub repository offering a comprehensive collection of AI prompts for leading models such as ChatGPT, Claude, and Gemini. It serves as a bridge for effective communication with AI, providing a curated list of keywords and resources to enhance AI model performance. The project categorizes prompts into sections like Chinese prompts, ChatGPT guides, AI prompt generators, prompt marketplaces, AI painting prompt generators, and prompt engineering tutorials. It aims to help users quickly find and optimize prompts for various applications, from creative writing to AI art generation, making AI tools more accessible and efficient.

Wan2.2-T2V-A14B is an AI-powered tool available on Hugging Face that allows users to create videos by uploading an image and providing a descriptive text prompt. This tool is designed for efficient video generation, offering adjustable settings such as video duration and resolution to tailor the output to specific needs. It leverages `app_fast.py` for fast API operations and `app_t2v` which is a 14B model, indicating a robust underlying architecture for video synthesis. The platform is accessible via a web interface, making it easy for users to experiment with different inputs and settings to achieve desired video outcomes. It's particularly useful for those looking to quickly transform static images into dynamic video content with minimal effort.

cgft-llm is an open-source GitHub repository dedicated to providing practical learning resources for large language models (LLMs). It offers a comprehensive series of code examples, detailed documentation, and video tutorials covering various aspects of LLM development, including Agent systems, core LLM technologies like fine-tuning and RAG, and integration with open-source projects. The resource is structured into several modules, guiding users through topics such as LLM deployment with tools like vLLM and Ollama, data preparation for fine-tuning, and advanced concepts like function-calling and tool-use. It also includes sections on Python engineering practices for open-source contributions and creative AI projects, making it suitable for developers and researchers looking to deepen their understanding and practical skills in the LLM domain.

Fay is an open-source AI agent framework designed to bridge the gap between digital humans (2.5D, 3D, mobile, PC, web) or large language models (OpenAI compatible, DeepSeek) and business systems. It provides a stable and comprehensive solution for developing digital human applications, allowing for flexible integration of TTS, ASR, and various digital human models. Fay supports both server and standalone modes, offering features like multi-user concurrent access, text and voice interaction interfaces, digital human driving interfaces, and automatic broadcast capabilities. It also includes agent autonomous decision-making, adaptive memory, and a configuration management center, making it suitable for a wide range of applications from embedded devices to websites.

Cornucopia-LLaMA-Fin-Chinese is an open-source project that provides a series of Chinese financial large language models based on the LLaMA architecture. It is specifically designed for financial knowledge question answering, having been instruction fine-tuned with extensive Chinese financial data. The project also offers an efficient and lightweight training framework for developing vertical domain LLMs, covering stages like pretraining, SFT, RLHF, and quantization. It leverages public and crawled Chinese financial Q&A data, including topics such as insurance, wealth management, stocks, funds, loans, credit cards, and social security. The project aims to continuously expand its high-quality instruction dataset using GPT-3.5/4.0 APIs and integrate with Chinese financial knowledge graphs and CFLEB financial datasets, with plans to release new Chinese financial models for various scenarios.

Linly is an open-source project that offers a suite of Chinese large language models, including Chinese-LLaMA (versions 1 and 2), Chinese-Falcon, and Linly-OpenLLaMA. These models are built upon LLaMA and Falcon architectures, enhanced with extensive Chinese and English parallel corpora for incremental pre-training, extending their linguistic capabilities to Chinese. The project also features Linly-ChatFlow, a Chinese conversational model trained on large-scale instruction data. Linly provides comprehensive resources, including data preparation, model training, and evaluation code, ensuring reproducibility. It supports various quantization schemes for deployment on CUDA and edge devices, making it versatile for different applications. The Linly-OpenLLaMA models, available in 3B, 7B, and 13B scales, are trained from scratch on 1TB of mixed English and Chinese data, featuring an optimized tokenizer for Chinese characters and words, and are released under an Apache 2.0 license for commercial use.

LiquidStudio offers a modern and efficient editor specifically designed for Liquid templates. This tool empowers developers to preview their templates in real-time, ensuring immediate feedback on changes. A key differentiator is its integrated AI capabilities, which can refactor existing Liquid code, fix errors, or even generate new code snippets, significantly accelerating the development process. By catching errors early and streamlining code generation, LiquidStudio helps developers iterate faster on critical components like emails, Shopify themes, and various web templates. This focus on live preview and AI-assisted coding makes it an invaluable asset for anyone working with Liquid, enhancing both productivity and code quality.

MemMachine Playground is an official platform by Memverge designed for experimenting with AI memory for large language models (LLMs) and AI agents. This tool allows users to explore various memory configurations and understand their impact on AI performance and capabilities. It serves as a valuable resource for AI developers and researchers who are focused on enhancing the intelligence and efficiency of their AI systems. The playground offers a hands-on environment to test and refine memory strategies, ultimately contributing to the development of more robust and effective AI applications.

AiryChat AI Assistants makes AI accessible and easy to use for both individuals and businesses. It offers a range of AI assistants, from general support to specialized roles like marketing assistant, software developer, and UI designer. For businesses, AiryChat provides AI staff augmentation, enabling employees to draft documents, scan contracts, and utilize voice mode. The platform is built on OpenAI, Meta, and Google services, ensuring up-to-date technology. Key features include PDF, CSV, & DOCX processing, long-term memory, unlimited context length, web search indexing, and built-in image generation. It also offers a cost-saving zero-cost prompt prefetch and voice-to-voice communication.

PaddleNLP is a comprehensive development suite built on the PaddlePaddle deep learning framework, designed for large language models (LLMs). It facilitates efficient training, lossless compression, and high-performance inference of models across diverse hardware, including NVIDIA GPUs, Kunlun XPU, Ascend NPU, and more. The library emphasizes ease of use and extreme performance, aiming to empower developers in creating industrial-grade large model applications. Key features include 4D high-performance training with data, tensor, and pipeline parallelism, efficient fine-tuning algorithms, and a high-performance inference module with dynamic insertion and operator fusion. It also supports a wide range of popular LLM series like LLaMA, Baichuan, Bloom, ChatGLM, Gemma, Mistral, OPT, and Qwen.

gptlink is an open-source project designed to help users quickly build and deploy a commercial AI dialogue site. It offers a straightforward setup process, particularly with Docker, and comes with an out-of-the-box console for managing users, orders, and tasks. The platform is built using PHP (Hyperf) and Vue, making it accessible for developers. Key features include custom payment plans, one-click dialogue export, and full adaptability for mobile devices. It supports both GPTLINK Key and OpenAI official keys for API integration. The project also provides limited permission control and is actively developing new features like an updated admin backend, account/password login, offline payment configuration, and AI image generation.

ML-NLP is an open-source GitHub project designed to be a comprehensive resource for individuals preparing for interviews in Machine Learning, Deep Learning, and Natural Language Processing. It covers frequently tested knowledge points and provides practical code implementations, making it an invaluable theoretical foundation for aspiring algorithm engineers. The project is structured into various modules, offering a clear and organized knowledge system. Each chapter includes potential interview questions and concludes with practical algorithm case studies. It is intended for continuous learning, review, and as a quick reference during interview preparation.

NeuroAPI offers API access to leading text-based neural networks, including ChatGPT 3.5 Turbo, ChatGPT 4o, and Claude-4, bypassing the need for VPNs or international payment methods. Designed for developers and applications, it provides an API-only interface, focusing exclusively on text-based requests. A key differentiator is its cost-effectiveness, with queries being up to 30% cheaper than official rates. The service supports flexible payment options, including cryptocurrencies and MIR cards. While it currently does not support `function_call` or `tool_calls`, and image generation is in closed beta, it provides free access to `gpt-3.5-turbo` via API and an online chat interface. Users need basic API knowledge to integrate the service into their applications.

Prompt Refinery - Text to Image is a free Gradio-based AI tool hosted on Hugging Face, designed to enhance the image generation process. Users start by entering a short, simple text prompt. The tool then processes this input to generate several detailed and expanded prompt suggestions, offering more creative and specific directions for image creation. Once the user selects or is satisfied with the refined prompts, the tool leverages Stable Diffusion to render corresponding images. This iterative refinement process helps users achieve more precise and desired visual outputs, making it a valuable resource for anyone looking to generate high-quality images from text.

SentimentPolarityAnalysis is an open-source project providing various methods for sentiment polarity analysis. It includes implementations for feature extraction and sentiment classification using diverse algorithms such as sentiment dictionaries, k-Nearest Neighbors (k-NN), Naive Bayes, Maximum Entropy, and Support Vector Machines (SVM). The tool allows users to analyze single sentences or entire files, with options for outputting results to files or displaying them in the console. It also provides functionality for evaluating the accuracy of different classification models, making it suitable for research and development in natural language processing.

CLIP Interrogator AI is a web-based application that bridges the gap between visual content and language by interpreting images through natural language descriptions. Developed by pharmapsychotic, it utilizes a multi-step process involving the BLIP model for initial caption generation, followed by enhancement with specific phrases (Flavors) covering objects, styles, and artist names. The CLIP model then matches the image with the most fitting phrases, resulting in rich, detailed text descriptions. This tool is particularly useful for generating effective prompts for AI image generators, allowing users to understand and replicate the style and content of existing images. It also incorporates the OpenCLIP model for robust image-text matching capabilities.

Zhihu is a GitHub repository offering a collection of source code for various Artificial Intelligence projects, primarily focusing on Natural Language Processing (NLP) and Computer Vision (CV). Implemented in Python 3.6, this repository serves as a practical resource for developers and researchers. It features diverse projects such as text generation using RNNs (LSTM), machine translation with Seq2Seq models and attention mechanisms, deep convolutional Generative Adversarial Networks (GANs) for image generation, and sentiment analysis using DNN, LSTM, and CNN. Additionally, it includes implementations for image style transfer and CTR prediction models like DeepFM and xDeepFM. The repository is designed to accompany a personal column, providing hands-on code examples for learning and experimentation in AI.

Ripplica is an AI-powered automation tool designed to streamline browser-based workflows. Users can automate any web application task by simply recording a video of the desired action once. The platform then uses AI agents to interpret on-screen actions, understand the task, and intelligently execute it, even as conditions change. Ripplica eliminates repetitive work by allowing users to schedule or remotely trigger automations, even when offline. It operates in a secure, isolated virtual machine environment and works with any software, including legacy systems, without requiring APIs. Key applications include QA automation, DM management, inbox assistance, and analytics & reporting, significantly improving efficiency and productivity for teams.

yu-ai-agent is a comprehensive AI development project designed for programmers looking to master AI technologies. Built with Spring Boot 3, Java 21, and Spring AI, it guides users through creating an AI 'Love Master' application and a ReAct-mode autonomous intelligent agent named YuManus. The project covers essential AI concepts including large language model integration, Spring AI core features, prompt engineering and optimization, RAG (Retrieval Augmented Generation) for enhanced retrieval, vector databases, and tool calling. It also delves into MCP (Model Context Protocol) and AI Agent development, providing a practical, hands-on approach to becoming proficient in AI for enterprise applications.

GPTs Gallery is a dedicated platform designed to facilitate the exploration and discovery of a wide array of Generative Pre-trained Transformers (GPTs). It serves as a central resource for individuals and organizations interested in harnessing the power of GPT technology for diverse applications. The gallery aims to connect users with innovative GPTs, making it easier to find models that align with specific needs and use cases. While the current website content is minimal, the underlying purpose is to provide a curated space for the GPT ecosystem, enabling users to navigate and select the most suitable AI models for their projects and interests. This platform is ideal for anyone looking to stay updated on the latest advancements and practical applications of GPTs.

Valyfy is a career-building platform designed for students and new graduates to enhance their software engineering skills and portfolios. It provides access to industry-level challenges and real-world projects, allowing users to leverage AI tools and build practical experience without traditional internships. The platform features an AI-powered GitHub analysis for personalized feedback and a smart portfolio builder that automatically highlights technical abilities and adapts to different roles. Users can collaborate on projects, learn technical skills and AI collaboration techniques, and showcase their work to employers. Valyfy also offers challenges with cash prizes and opportunities to connect directly with startups, aiming to bridge the gap between academic learning and industry demands.

NokémonAI is an AI-powered tool designed for generating unique Fakémon creatures. Users can easily create their dream Fakémon by providing simple descriptions or by customizing every detail of their design. The platform offers a free and intuitive way to generate new and imaginative Pokémon-like characters, making it accessible for anyone interested in creative monster design. It's an ideal tool for fans looking to expand the Pokémon universe with their own creations.

Steercode by LangChain is an innovative AI tool designed to empower users to build mobile and web applications without requiring any coding knowledge. The platform allows users to simply describe what they want to create—whether it's a website, app, or game—and watch it take shape in real-time. A key differentiator is its mobile-first approach, enabling development directly from a phone. Steercode aims to make software creation accessible to a broader audience, bridging the gap between ideas and functional applications by leveraging AI to handle the underlying code generation. It provides a user-friendly interface for rapid prototyping and development.