Coding & Development

Torch-Pruning (TP) is a comprehensive open-source framework designed for structural pruning of deep neural networks. Unlike traditional methods that zeroize parameters via masking, TP employs an innovative algorithm called DepGraph to group and remove coupled parameters, ensuring efficient model compression. It supports a diverse array of models, including Large Language Models (LLMs), Segment Anything Model (SAM), Diffusion Models, Vision Transformers, and various CNN architectures like ConvNext and Yolov7/v8. The framework offers general-purpose pruning capabilities, high-level pruners for automated channel pruning based on importance criteria, and options for global or isomorphic pruning. It also provides functionalities for sparse training, interactive pruning, and customized layer handling, making it a versatile tool for researchers and developers aiming to optimize model size and performance.

simple-local-rag is a comprehensive tool designed for building Retrieval Augmented Generation (RAG) pipelines from the ground up, with a strong emphasis on local execution. It supports the entire RAG workflow, from ingesting PDF documents to enabling "chat with PDF" style features. The tool is built to run on NVIDIA GPUs and leverages open-source technologies, making it a flexible and powerful solution for developers and data scientists. A key example is NutriChat, a RAG workflow that allows users to query a 1200-page nutrition textbook and receive LLM-generated responses based on relevant passages. This tool is particularly valuable for those who prioritize privacy, speed, and cost-effectiveness by running AI models on their own hardware.

Unsloth AI provides an open-source, no-code web UI for training, running, and exporting open models locally on Mac and Windows devices. It supports GGUF and Safetensors models with features like tool-calling, web search, and OpenAI compatible API. Users can compare models side-by-side and upload various file types for analysis. The platform offers no-code training with auto-creation of datasets from PDF, CSV, and JSON documents, along with real-time observability. Unsloth's custom kernels optimize training for LoRA, FP8, FFT, PT, and over 500 models, including text, vision, audio, and embeddings. Models can be exported to safetensors or GGUF for use with llama.cpp, vLLM, and Ollama.

Starmoon is a fully open-source, compact, conversational AI device and software framework designed for a variety of applications including companionship, entertainment, education, healthcare, IoT, and DIY robotics. Users can assemble the device with affordable off-the-shelf components and converse with custom AI characters. It features voice-enabled emotional intelligence, allowing it to understand and analyze emotions in real-time conversations. Built with Python, NextJS, Arduino, ESP32, and integrating LLMs like GPT-4o, Deepgram STT, and Azure TTS, Starmoon offers a versatile platform for personalized learning assistance and supportive conversations. The project is currently deprecated, with development continuing under ElatoAI for improved reliability and production-ready architecture.

stable-diffusion-webui-two-shot is an extension for Stable Diffusion WebUI, specifically designed to enhance image generation through its Latent Couple feature. This tool extends the built-in Composable Diffusion capabilities, allowing users to precisely determine the region of the latent space that reflects their subprompts. The effect of Latent Couple is only active when enabled, and regions are created based on user-defined divisions, positions, and weights. This provides a granular level of control over how different elements of a prompt are rendered within specific areas of the generated image, making it ideal for complex compositions and detailed scene creation.

Savart Motors, operating as GEN Motorcycles Indonesia, specializes in the development of electric minimobility solutions, focusing on smart electric scooters. Their approach integrates machine learning and AI to create scooters that intelligently adapt to individual riding styles. The company emphasizes innovation and local expertise, designing and developing their products entirely in-house to meet market needs and rider preferences. Savart offers the S-Series electric scooter, along with battery packs and a Battery Swapping Station (BSS) network, aiming to transform urban minimobility with energy-efficient and modern transportation.

Safe Intelligence offers a comprehensive platform for ensuring the robustness and reliability of AI systems. It provides advanced capabilities for validating machine learning models, allowing users to access deeper analysis of model performance and identify fragilities and counter-examples. The platform formally verifies regions against broad classes of perturbations and can analyze deep neural networks, decision trees, and random forests. Beyond validation, Safe Intelligence helps robustify models by analyzing whole regions of input space and checking performance under domain shift, aiming to remove fragilities, improve fairness, and lower variance. It also includes continuous monitoring alerts to track standard model metrics and watch for emerging issues, automating the build and verification process.

Thinc is a lightweight, open-source deep learning library developed by the creators of spaCy and Prodigy. It provides a functional programming API for composing neural network models, offering flexibility and efficiency in AI development. A key differentiator is its ability to support layers defined in popular frameworks like PyTorch, TensorFlow, and MXNet, allowing developers to integrate and combine models from various ecosystems. Thinc is designed for developers who need to build custom, high-performance machine learning models, particularly for natural language processing tasks, and offers a robust foundation for advanced AI applications.

Tools-to-Design-or-Visualize-Architecture-of-Neural-Network is a comprehensive GitHub repository offering various open-source tools designed to help users visualize and design neural network architectures. Key tools include Net2Vis, which automatically generates abstract visualizations for convolutional neural networks directly from Keras code, and Visualkeras, a Python package specifically for visualizing Keras neural network architectures with customizable styling options. The collection also features tools like PlotNeuralNet for LaTeX code generation, TensorBoard for examining TensorFlow models, and TensorSpace for 3D visualizations. This resource is invaluable for data scientists and researchers looking to better understand, present, and debug their deep learning models.

Techwink Services is a leading software development company based in the USA, offering custom web and mobile application solutions. They specialize in leveraging AI technologies, including OpenAI ChatGPT, Google Gemini, and VertexAI, to build intelligent AI-driven applications. Their services encompass a wide range of development needs, from mobile app development for iOS and Android to web development using various frameworks like PHP/Laravel, Node.js, and Python. Techwink also provides enterprise services, NFT marketplace development, API integration, and MVP services, catering to diverse industries such as healthcare, education, and legal. They focus on delivering high-quality solutions to help businesses increase sales and reduce costs.

unreal-mcp is an open-source project designed to bridge the gap between AI assistants and the Unreal Engine, allowing for natural language control over game development environments. By implementing the Model Context Protocol (MCP), it facilitates interaction between AI clients like Cursor and Claude Desktop and the Unreal Engine. This integration enables developers to automate workflows, generate content, and manage project elements through AI commands, significantly enhancing productivity and opening new avenues for AI-driven game development. The tool aims to streamline complex tasks and provide a more intuitive interface for AI interaction within the Unreal ecosystem.

Theatech is an AI development company dedicated to providing advanced AI solutions for global e-commerce and mobile application development. The company aims to drive innovation in artificial intelligence, delivering cutting-edge AI solutions worldwide. Theatech assists businesses in leveraging the power of AI to enhance their e-commerce platforms and mobile applications, optimizing operations, improving user experience, and fostering growth. While specific features are not detailed on the provided website, the company's core focus is on developing and implementing AI technologies tailored for these critical digital sectors.

Refiner is an AI-powered, open-source tool designed to assist developers with code refactoring and generation. It aims to enhance code quality and structure by providing intelligent suggestions and automated processes. The tool streamlines the refactoring workflow, allowing developers to maintain cleaner and more efficient codebases. Additionally, Refiner can generate new code snippets, accelerating development cycles and reducing manual coding efforts. Its open-source nature fosters community contributions and transparency, making it a flexible solution for various development environments.

AI Code Translator is an AI-powered online tool designed for seamless code translation and generation. It allows developers to transform natural language descriptions into functional code or convert code between over 25 programming languages, including Python, JavaScript, TypeScript, and Java. The platform emphasizes high accuracy, context-aware translations, and the preservation of code quality and best practices. It's completely free to use, requires no registration, and offers real-time results, making it suitable for rapid prototyping, code migration, learning new languages, and modernizing legacy codebases. Advanced features like batch processing and version control integration are also available for professional development teams.

RegexBot is an AI-powered tool designed to streamline the process of generating regular expressions. By allowing users to input plain English descriptions, it automatically creates the corresponding regex patterns, eliminating the need for deep expertise in regex syntax. This makes it particularly valuable for developers and data scientists who frequently work with text processing and data extraction but may not be regex specialists. The tool aims to enhance productivity and reduce errors associated with manually crafting intricate regex patterns, providing a user-friendly solution for a common programming challenge.

Checkpoints for Claude Code, also known as Claude Diff, is an essential companion application for developers utilizing Claude AI for coding. It offers robust automatic version control and checkpoint management specifically tailored for Claude Code projects. Users can effortlessly track changes, create instant snapshots of their project's state, and restore to any previous version with confidence. The tool continuously monitors projects for file modifications, provides a visual diff viewer to highlight changes, and integrates seamlessly with Claude Desktop via the Model Context Protocol (MCP). This integration ensures that developers never lose their work, enabling them to experiment freely and recover from mistakes during AI-assisted coding sessions.

The GitHub Repository AI Assistant is a Chrome extension designed to enhance your GitHub experience by integrating an AI assistant directly into a side panel. This tool allows users to ask questions about any GitHub repository, whether it's an open-source project or a private one. It's particularly useful for quickly assessing the suitability of an open-source repository for specific needs or for understanding recent changes within your own private repositories. The extension aims to streamline the process of code comprehension and project evaluation, making it easier for developers to navigate and utilize GitHub resources. It is important to note that this is not an official GitHub product.

weav.ai is an AI-native decisioning platform purpose-built for the insurance industry, designed to provide accurate, consistent, and faster insurance decisions. The platform unifies knowledge, decisions, and actions across an organization at scale. It's easy to configure, combining a company’s data, guidelines, and best practices into a comprehensive centralized knowledge framework. AI Agents then rapidly interpret and generate recommendations optimizing underwriting, premium audit, and claims. Insurers leverage this platform to quote faster, resolve claims easier, and audit more policies, improving combined ratios and allowing them to focus on building stronger relationships. Key features include pre-configured knowledge graphs, an agentic decision engine, an API-first architecture for enhanced intelligence within existing systems, and no-code platform configuration for improved product control and speed to market. It also offers full control with humans in the loop to review and approve critical decisions.

Scriptio AI is an AI-powered tool designed to accelerate the development process by providing coding solutions for fast and easy code generation. It supports a variety of programming languages, allowing developers to quickly create code snippets and complete projects with enhanced efficiency. This platform aims to reduce coding time and streamline workflows, making it easier for users to manage their development tasks. By leveraging artificial intelligence, Scriptio AI helps users overcome common coding challenges and improve productivity, ultimately leading to faster project delivery and reduced development costs. Its focus on ease of use and multi-language support makes it a versatile assistant for various coding needs.

Dream is a 7B diffusion large language model designed for research and development in language modeling. It offers competitive performance against leading autoregressive models of similar size. The project provides comprehensive training and evaluation code, including specific implementations for Dream-Coder (a 7B dLLM for code) and DreamOn (which addresses variable-length generation and infilling). Dream's implementation is based on the Huggingface transformers library, requiring specific versions of transformers and PyTorch. It supports various diffusion sampling strategies like `maskgit_plus` and `entropy` for controlling token generation order, and includes options for fine-tuning on custom datasets.

Docyrus is an AI Native B2B SaaS platform designed for building intelligent web and mobile applications, AI agents, and customer portals. It integrates data modeling, workflows, permissions, API access, and publishing into a single system, enabling teams to develop and launch operational software rapidly using either code or visual builders. The platform supports the creation of internal tools, customer portals, AI-assisted workflows, and vertical SaaS experiences built on real business data. Docyrus differentiates itself with a usage-based pricing model, allowing free deployment and charging only for infrastructure consumption like storage, automation runs, API requests, and AI credits, making it cost-effective for launching and scaling applications.

Kritisi is an AI-powered security audit explorer specifically designed for Solidity smart contracts. It provides a comprehensive solution for identifying vulnerabilities and potential security risks within blockchain applications. The tool supports multiple blockchains, offering developers and auditors a robust platform for in-depth security analysis. By leveraging artificial intelligence, Kritisi aims to streamline the auditing process, enhance the security posture of smart contracts, and mitigate risks associated with blockchain development. Its focus on Solidity contracts makes it a specialized tool for the Web3 ecosystem.

Accelate AI Labs specializes in custom AI development and integration, offering solutions designed to transform businesses across finance, healthcare, and manufacturing. Their expert team builds enterprise-grade AI applications that aim to increase operational efficiency by 30%, enhance decision-making, and create sustainable competitive advantages. Accelate partners with clients to bring their ideas to life, providing robust and scalable technologies that simplify complex software. They emphasize a collaborative approach, grounded in integrity, to empower businesses and ensure solutions drive growth, efficiency, and long-term success. Their services include revolutionizing real estate operations with RAG and LLMs, multilingual customer support with real-time speech-to-speech AI, and personalized marketing engines.

void is an open-source alternative to Cursor, providing robust AI code assistance for developers. It enables users to leverage AI agents directly on their codebase, facilitating tasks like code generation, refactoring, and debugging. A key feature is the ability to checkpoint and visualize changes, offering better control and understanding of AI-driven modifications. Furthermore, void supports hosting any model locally, which is crucial for privacy-conscious development or for utilizing custom models. The tool is designed to send messages directly to providers without retaining user data, ensuring a high level of privacy and security for proprietary code. This makes it an ideal solution for developers seeking powerful AI coding tools with strong data protection.