Coding & Development

screenshot2code.com is an AI-powered tool designed to streamline the process of turning visual designs into functional code. While currently in a 'COMING SOON' phase, the tool aims to convert UI screenshots directly into HTML code, likely leveraging advanced AI models such as GPT-Vision API, as indicated by its previous description. This functionality would allow developers to quickly generate boilerplate code from design mockups, significantly reducing manual coding effort and accelerating development workflows. The platform is expected to offer a live preview and editing capabilities, enabling users to refine the generated code before implementation.

GPTGame is an innovative AI-powered platform designed to generate fun, small JavaScript games instantly from text descriptions. Leveraging the power of GPT, this tool allows users to create and play games in a snap, eliminating the need for any coding skills. The platform offers a straightforward approach to game creation, enabling users to bring their game ideas to life quickly. It features a variety of game categories, including classics like 2048, Snake, Pong, Mandelbrot, and Tetris, with more games continuously being added. GPTGame simplifies the game development process, making it accessible for anyone interested in game creation, from casual enthusiasts to those looking to rapidly prototype game concepts.

Balkan Tech Solutions is a software development company focused on delivering custom software solutions, AI and automation, and innovative UI/UX design. They aim to transform ideas into intelligent solutions by leveraging AI and advanced software development to drive innovation and growth for businesses. Their services include integrating AI into existing systems or building AI-powered software from scratch, developing tailored software solutions to meet unique business needs, and creating intuitive, user-friendly interfaces that are visually appealing and drive engagement. The company follows a structured AI software development process, starting from problem definition and goal setting, through data exploration, model selection and training, evaluation and iteration, to deployment and maintenance, ensuring scalable and secure solutions.

vibe-coding-prompt-template offers a structured AI workflow for rapidly developing Minimum Viable Products (MVPs). It provides templates and a five-stage process, starting from idea validation and deep research, moving through Product Requirements Document (PRD) and Technical Design creation, to agent-assisted code generation. The workflow is designed to be used with AI IDEs like Cursor or VS Code with Copilot, enabling users to leverage large language models for tasks such as market analysis, stack selection, and iterative code building. It emphasizes upfront thinking and clean context handoffs to AI tools, aiming to streamline the development process for shipping projects efficiently.

LLM2Vec is an open-source project that offers a straightforward method to transform decoder-only Large Language Models (LLMs) into highly effective text encoders. This process involves three key steps: enabling bidirectional attention, training with masked next token prediction (MNTP), and applying unsupervised contrastive learning (SimCSE). The resulting models can be further fine-tuned to achieve state-of-the-art performance in various natural language processing tasks. LLM2Vec supports popular LLMs like Meta-Llama-3, Mistral-7B, and Llama-2-7B, and provides pre-trained checkpoints for both unsupervised and supervised variants. It includes scripts for training, evaluation on benchmarks like MTEB, and integration with HuggingFace models, making it a valuable resource for researchers and developers working with text embeddings.

Devin is the world's first AI Coder, designed to act as an AI software engineer capable of autonomously handling complex software engineering tasks. It integrates seamlessly into existing development workflows, empowering developers to concentrate on innovation rather than repetitive coding. Devin utilizes advanced machine learning and deep understanding of programming languages to generate high-quality, error-free code. The platform is built to collaborate with human developers, adapting to feedback and continuously improving its performance. Recent updates include the ability to schedule and manage multiple Devins for parallel task execution, and new self-serve plans ranging from Free to Enterprise, making it accessible for various team sizes and needs. Devin also offers specialized features like SWE-Check for faster bug detection and Devin Review for AI-augmented code review.

Unity MCP acts as a bridge, allowing AI assistants like Claude and Cursor to interact directly with your Unity Editor via a local Model Context Protocol (MCP) Client. This tool empowers Large Language Models (LLMs) with the capabilities to manage assets, control scenes, edit scripts, and automate various tasks within Unity. It offers a wide range of tools for managing profiler, physics, editor functions, builds, cameras, graphics, and more. Unity MCP also supports multiple Unity Editor instances and provides robust API verification through reflection and official documentation access. It is proudly sponsored and maintained by Coplay, offering a powerful way to integrate AI into game development workflows.

HABB is a Sri Lanka-based digital engineering partner that specializes in designing and building secure, scalable products across web, mobile, cloud, and AI domains. With a strong focus on reliability, performance, and rapid time-to-market, HABB delivers production-ready software solutions to clients worldwide. Their services include HABB DIGI for digital marketing, HABB AI for AI-driven products and integrations like automation and predictive analytics, and HABBGate for secure access control systems. They emphasize engineering exceptional software through proven methodologies and technical excellence, serving both big and small brands globally.

transformers.js is an open-source JavaScript library designed to bring state-of-the-art machine learning capabilities directly to the web browser. It allows developers to run Hugging Face's Transformer models without requiring a server, offering functional equivalence to the Python library. The tool supports a wide range of tasks including text classification, image segmentation, automatic speech recognition, and zero-shot object detection. It leverages ONNX Runtime for browser execution and allows for easy conversion of PyTorch, TensorFlow, or JAX models to ONNX using 🤗 Optimum. Developers can install it via NPM or use it directly in vanilla JS via CDN, with options to run models on CPU (WASM) or GPU (WebGPU) and adjust quantization for performance.

MFTCoder is a high-accuracy and efficiency multi-task fine-tuning framework specifically designed for Code Large Language Models (LLMs). Developed by CodeFuse, an AI Native team within Ant Group, this open-source project facilitates accurate and efficient Multi-task Fine-tuning (MFT) on LLMs, with a particular focus on code-related tasks. It offers two main codebases: MFTCoder-accelerate, which leverages Accelerate and DeepSpeed/FSDP for robust training, and MFTCoder-atorch, based on the ATorch framework for fast distributed training. The framework supports multi-task learning, allowing models to be trained on diverse tasks while maintaining balance and even generalizing to new, unseen tasks. It integrates state-of-the-art open-source models and provides efficient fine-tuning options like LoRA, QLoRA, and full-parameter training, making it suitable for large models with minimal resources. MFTCoder also includes support for SFT (Supervised FineTuning) and releases high-quality code-related instruction datasets.

Minuet-ai.nvim is a Neovim plugin designed to enhance the coding experience by providing AI-powered code completion directly within the editor. It supports a wide range of popular Large Language Models (LLMs) including OpenAI, Gemini, Claude, Ollama, Llama.cpp, and Codestral, offering flexibility in choosing a preferred AI backend. The plugin features dual modes for completion, specialized prompts for chat-based LLMs, and fill-in-the-middle (FIM) completion for compatible models. It supports streaming for faster delivery of suggestions, even with slower LLMs, and operates without proprietary background binaries. Minuet-ai.nvim integrates with various frontends like virtual-text, nvim-cmp, blink-cmp, and can act as an in-process LSP server, providing multi-line suggestion acceptance and next-edit prediction.

SQLtroughAI is an AI-powered tool designed to streamline data management and SQL query generation. It aims to automate complex data tasks, making SQL more accessible for users regardless of their technical proficiency. By leveraging artificial intelligence, SQLtroughAI helps to reduce the time spent on writing and optimizing queries, while also minimizing errors in database management. This tool is particularly beneficial for businesses and individuals looking to enhance their database efficiency and simplify their data interaction processes. It provides a user-friendly interface to interact with databases, abstracting away much of the complexity typically associated with SQL.

Yack is a MacOS application designed to provide seamless and private access to ChatGPT directly from your menu bar. Built with Rust, it emphasizes a lightweight footprint and user privacy by storing all data locally on your device. The app offers various customization options, including different themes, and supports markdown for enhanced text formatting. It also integrates productivity features such as keyboard shortcuts, allowing users to quickly interact with ChatGPT without leaving their current workflow. Yack aims to be a discreet yet powerful companion for MacOS users who frequently utilize AI for various tasks.

OpenAIKit is a Swift package designed to facilitate seamless communication with the OpenAI API. It empowers Swift developers to integrate a wide range of OpenAI's functionalities, including Chat Models, Completions, Edits, Images, Embeddings, Files, Moderations, Fine-tunes, Speech to text, and Function calling, directly into their iOS and macOS applications. The package simplifies the process of making API calls and handling responses, offering flexibility by supporting both SwiftNIO's HTTPClient and URLSession for network requests. It also provides robust error handling, ensuring developers can gracefully manage API failures within their applications.

Privy is an open-source alternative to GitHub Copilot designed for local execution, ensuring privacy and control over your code. It provides real-time code completion and allows developers to chat with AI about their code directly within their development environment. Privy supports various local LLM platforms, including Ollama (highly recommended), llamafile, and llama.cpp, giving users flexibility in choosing their preferred model. Key features include auto code completion, a Copilot-style chat interface, and threaded conversations. It also supports advanced functionalities like code explanation, unit test generation, bug finding, and error diagnosis. Users can configure Privy with recommended LLMs such as DeepSeek Coder, CodeLlama, and Mistral, tailoring the model size to their hardware capabilities.

Axflow is a comprehensive TypeScript framework designed for AI development, offering a modular and scalable approach to building natural language powered applications. It includes core modules like `@axflow/models` for robust natural language applications with React hooks and streaming utilities, `axgen` for connecting data to large language models, and `axeval` for evaluating LLM output quality. The framework is actively expanding with planned modules such as `extract` for efficient data processing and document chunking, `serve` for LLM model serving with middleware options, and `finetune` for model fine-tuning. Axflow emphasizes a code-first approach, providing developers with flexibility and control to build higher-level TypeScript AI features and products seamlessly.

OptiSol Business Solutions leverages generative AI to empower businesses across various industries, focusing on accelerating innovation, scaling efficiently, and creating future-ready products. Their services encompass building digital products faster with GenAI-driven teams, modernizing legacy applications and infrastructure, and harnessing GenAI and analytics for data unification and insights. OptiSol also specializes in Global Capability Centers (GCCs) in India, offering GenAI engineers and agentic AI capabilities. They provide a suite of GenAI accelerators like elsAi for AI app development, Unicus AI for due diligence and compliance, Scanflow for vision intelligence in quality control, and elsai ESG for simplified ESG data management and reporting. Additionally, they offer modernization tools like iBEAM for converting Oracle Reports to Jasper and migrating Oracle databases to PostgreSQL.

Refact.ai is an open-source AI coding agent designed to enhance software development workflows. It acts as an autonomous AI agent, capable of planning, executing, and deploying coding tasks end-to-end, integrating with various tools like GitHub and databases. The platform offers context-aware chat, accurate autocompletions powered by Qwen2.5-Coder and RAG, and supports over 25 programming languages. A key differentiator is its on-premise deployment option, ensuring data privacy and control. Refact.ai learns and evolves with user interaction, adapting to specific workflows and codebases, making it a powerful and customizable solution for individual developers and enterprise teams alike.

Sentient.io offers a comprehensive AI & Data platform designed to empower enterprises with intelligent solutions. The platform provides ready-made AI models for easy adoption, allowing businesses to quickly integrate AI capabilities into their operations. Additionally, Sentient.io delivers turnkey AI solutions, catering to the specific needs of enterprises embarking on their digitalization journey. The platform emphasizes security and aims to simplify the process of leveraging artificial intelligence for various business applications, making advanced AI accessible for enhanced decision-making and operational efficiency.

Bezi AI is an advanced AI assistant specifically designed for Unity developers, offering comprehensive support for debugging, code generation, shader creation, and prototyping. Unlike generic AI tools, Bezi integrates directly with the Unity engine and indexes your project in real-time, including scripts, assets, scenes, and external documentation like GDDs. This deep contextual understanding allows it to provide tailored assistance without requiring additional explanation, ensuring responses are consistent with your codebase and architecture. It helps automate repetitive workflows, generate functional prototypes, and debug issues that IDEs might miss by tracing interactions between scripts, scene objects, and components. Bezi also enforces project standards, acting as a structured knowledge layer for coding standards and design specs, which compounds knowledge across teams and streamlines onboarding.

STTech GmbH offers the STTech AI Core, an AI Application Platform designed to generate complete, production-ready enterprise applications. This includes everything from backend workflows to the user interface, significantly reducing development time to weeks. The platform is highly customizable, allowing it to cover nearly all business processes and integrate AI into daily work. It emphasizes reliability and safety, being TISAX-certified, GDPR compliant, and DORA ready. Key advantages include its agnostic nature, allowing flexible choice of LLM and hosting, and a pay-as-you-go model based on AI workload and customization. STTech aims to empower workforces with AI, drive efficiency, and provide actionable insights for better decision-making.

Emdash is an open-source desktop application designed as an agentic development environment (ADE) for software developers and AI engineers. It enables users to run multiple coding agents simultaneously, with each agent operating within its own isolated Git worktree to prevent interference. The platform supports over 23 CLI-based agents, including Claude Code, Codex, and Gemini, allowing for flexible agent selection. Key features include a Kanban view for task management, integration with issue trackers like Linear, Jira, and GitHub, and a built-in diff view for reviewing code changes. Emdash also supports remote development via SSH, MCP server connections, and offers a file editor, making it a comprehensive tool for accelerating the coding, review, and deployment process.

Butterfly Decisions is a specialized platform for AI-Assisted Decision Making, designed to enhance organizational processes and decisions. It leverages a proprietary platform that combines Artificial Intelligence, scientific methodologies, and epistemic intelligence to support complex decision-making scenarios such as Advisory Boards, Delphi Panels, and structured Consensus. Initially validated in the pharmaceutical sector with leading healthcare companies, the platform is modular, scalable, and adaptable for use in defense, energy, and industrial sectors. It features a multi-agent AI architecture for structured analysis, simulations, and automated report generation, helping organizations track every process phase, qualify decisions with data-driven insights, and accelerate decision-making through algorithms and vertical solutions.

TFTS (TensorFlow Time Series) is an open-source Python package designed for time series deep learning models, built on TensorFlow and Keras. It offers a comprehensive suite of classical and state-of-the-art deep learning methods for time series tasks, including prediction, classification, and anomaly detection. The tool is highly flexible, allowing users to train models with their own 3D data inputs, whether as NumPy arrays, TensorFlow datasets, or Keras sequences. It supports a variety of models such as seq2seq, wavenet, transformer, rnn, tcn, bert, dlinear, nbeats, informer, and autoformer. TFTS also enables customization, allowing users to build custom models by adding embeddings for categorical variables or custom head layers for specific tasks. It has demonstrated strong performance in competitions, with TFTS-Bert winning 3rd place in KDD Cup 2022 wind power forecasting and TFTS-Seq2seq securing 4th place in Tianchi-ENSO index prediction 2021.