Coding & Development

PrivacyPal is a browser extension designed to safeguard sensitive data during interactions with AI tools like ChatGPT and Claude. It ensures private AI interactions by preventing the exposure of personal or confidential information. The tool offers a straightforward, one-click installation process with zero configuration required, making it accessible for immediate use. Users can sign up via traditional methods with credit card payment for a standard subscription, or through Web3 signup by connecting an EVM-compatible crypto wallet for decentralized identity and crypto payment support. PrivacyPal aims to provide a secure environment for both Web2 and Web3 users engaging with AI technologies.

LLaDA (Large Language Diffusion with Masking) offers the official PyTorch implementation for Large Language Diffusion Models, providing a robust framework for developing and training diffusion models for natural language processing tasks. This open-source tool introduces an unprecedented 8B scale diffusion model, trained from scratch, demonstrating performance comparable to LLaMA3 8B. Key features include support for conditional likelihood evaluation and conditional generation, with pre-trained models available on Huggingface. LLaDA also offers guidelines for pre-training and Supervised Fine-Tuning, making it adaptable for researchers and developers. It explores a theoretically complete language modeling approach, distinguishing itself from BERT by using a varying masking ratio and serving as a generative model capable of in-context learning and instruction-following.

langchain-ui is an open-source chat-AI toolkit designed to simplify the creation and hosting of chatbots with a no-code interface, built on top of LangChain. It enables users to develop custom ChatGPT-like chatbots, providing them with context from external data sources, ChatGPT plugins, and prompts. Each chatbot comes with a dedicated API endpoint, and the platform supports bringing your own database and authentication provider. While the repository is currently unmaintained, with development shifting to Superagent for more granular access to LLM-powered Agents, it still offers features like usage quotas, chatbot embedding, and themes.

Mamba-Chat is a groundbreaking chat language model that leverages a state-space model architecture, distinguishing it from traditional transformer-based LLMs. Developed by redotvideo, it is based on Albert Gu's and Tri Dao's Mamba work and offers training and fine-tuning capabilities. The model, specifically Mamba-2.8B, has been fine-tuned on 16,000 samples from the HuggingFaceH4/ultrachat_200k dataset. This open-source project provides developers with the necessary code to run a CLI chatbot, a Gradio app, and fine-tune the base Mamba model, making it an excellent resource for experimenting with novel LLM architectures.

Mastra is a comprehensive framework designed for building AI-powered applications and agents with a modern TypeScript stack. Developed by the team behind Gatsby, it offers everything needed to go from early prototypes to production-ready applications. Key features include model routing, which connects to over 40 providers like OpenAI, Anthropic, and Gemini through a single interface. It enables the creation of autonomous agents that use LLMs and tools to solve open-ended tasks, and a graph-based workflow engine for orchestrating complex multi-step processes. Mastra also supports human-in-the-loop interactions, context management for agents, and integrations with existing React, Next.js, or Node.js apps. It emphasizes production essentials with built-in evals and observability for continuous refinement of AI products.

Promptsion is a Chrome extension designed to offer instant AI assistance, streamlining the process of optimizing AI prompts and managing ChatGPT conversations. This tool is built to enhance productivity for a wide range of tasks involving AI interaction and content creation. By providing quick access to AI capabilities directly within the browser, Promptsion aims to simplify prompt engineering and organization. It helps users refine their inputs to AI models, ensuring more effective and relevant outputs. The extension also facilitates better management of past interactions, making it easier to revisit and utilize previous conversations. This makes Promptsion a valuable asset for anyone frequently engaging with AI for various professional or creative endeavors.

Snowflake is a comprehensive AI Data Cloud platform designed to mobilize data, applications, and AI. It offers a fully managed platform for developing AI products, apps, and more, securely connecting businesses across any type or scale of data. Key capabilities include Cortex Code for AI coding, Cortex AI for instant access to LLMs, and a Marketplace for third-party data. Snowflake supports analytics, AI, data engineering, and applications & collaboration, featuring tools like Snowpark, Streamlit, and Snowflake ML for streamlined model development. It also provides Snowflake Intelligence for enterprise agents and Postgres for running open-source databases. The platform aims to simplify enterprise data and AI strategies, offering a connected ecosystem and trusted security, governance, and disaster recovery.

Allus AI offers a Vision Foundation Model specifically designed for manufacturing, providing a universal AI solution for quality inspection and process monitoring across various industries. The platform allows users to define manufacturing vision problems using natural language and generates production-ready AI solutions. It boasts rapid solution delivery, deploying industrial-grade vision solutions in 30 minutes with high detection and compliance rates. Allus AI supports deployment to cameras, industrial PCs, or robots for real-time inspection and monitoring, and provides access to real-time production analytics and AI-driven insights to optimize quality and efficiency. The state-of-the-art transformer model is trained on billions of data points, ensuring unmatched performance for diverse applications.

The MATLAB-Deep-Learning-Model-Hub is an open-source repository on GitHub offering a comprehensive collection of pretrained deep learning models specifically designed for use within the MATLAB environment. It covers a wide array of applications including computer vision tasks such as image classification, object detection, semantic segmentation, instance segmentation, image translation, pose estimation, 3D reconstruction, and video classification. Beyond vision, it also includes models for natural language processing (Transformers), audio analysis (embeddings, sound classification, pitch estimation, speech-to-text), and Lidar point cloud processing. This hub is ideal for researchers and developers looking to accelerate their deep learning projects by utilizing pre-trained models and applying transfer learning techniques.

ASC27 s.r.l. specializes in developing advanced artificial intelligence and cybersecurity solutions. The company focuses on creating software that leverages its proprietary AI engines to deliver value across various domains, including cognitive intelligence, video, audio, music, and media. Their AI innovation process leads in cognitive intelligence and analytic fields, aiming to bridge the gap between human and machine learning. Additionally, ASC27 develops robust cybersecurity solutions designed to provide peace of mind by protecting organizations from threats. They emphasize leading the CyberSec innovation process in strong and top security fields, offering a portfolio of products and solutions built on their expertise.

Rapture Parser is a powerful web scraping API designed to transform any website into structured data quickly and efficiently. It simplifies the process of collecting information by allowing users to input a link and receive parsed results in a structured format. The tool is capable of extracting various types of information, including titles, text summaries, authors, publication dates, tags, languages, and images. Rapture Parser offers both a user-friendly web interface and a REST API for seamless integration with existing applications. A key differentiator is its advanced technology that bypasses common anti-scraping protections like Cloudflare barriers, CAPTCHA challenges, and IP address blocking. Leveraging artificial intelligence, it accurately extracts insights from raw HTML, making it easier to obtain valuable information that might be difficult to acquire manually or with other scraping tools. Additionally, it supports parsing existing HTML content and will soon handle PDF and other file types, as well as content behind paywalls.

WriteDocs is an AI-powered tool designed to streamline the creation of documentation content. It allows users to generate the initial version of their documentation in under a minute, significantly accelerating the development process. Users can choose from predefined starting points, such as API documentation for payment gateways or user guides for mobile apps, or write their own prompts from scratch to generate detailed content. The tool can create various types of documentation, including API specifications, user guides, FAQs, and even legal documents like Terms of Service and Privacy Policies. It aims to make shipping products with comprehensive documentation easier and faster, leveraging AI to produce content that can then be refined and deployed.

DeepTeam is a simple-to-use, open-source framework designed for red teaming large language models (LLMs) and LLM systems. It functions like penetration testing for AI, simulating various attacks such as jailbreaking, prompt injection, and multi-turn exploitation. The framework helps uncover vulnerabilities like bias, PII leakage, and SQL injection in AI agents, RAG pipelines, and chatbots. DeepTeam also provides production-ready guardrails to prevent these issues in real-time. It runs locally on your machine and is built on DeepEval, an open-source LLM evaluation framework. Users can define custom vulnerabilities and attacks, run red teaming from the CLI or programmatically in Python, and access risk assessments.

Deep_learning_cookbook is an open-source repository featuring 35 Python notebooks that illustrate fundamental machine learning techniques using the Keras framework. These notebooks are designed to accompany the book "Deep Learning Cookbook" but are fully functional as standalone educational resources. The collection covers a wide range of topics, from using pre-trained word embeddings and building recommender systems to generating text, classifying sentiments, and working with image recognition networks. It also includes examples for productionizing embeddings and preparing Keras models for deployment on platforms like TensorFlow Serving and iOS. While a GPU is not strictly required, its use is recommended for faster processing.

Video AIditor offers a comprehensive programmatic video editing API designed for developers and AI platforms to automate video generation. Users can create reusable video templates and customize them via API, replacing media sources, text, and styling through simple JSON payloads. The platform supports auto caption generation in multiple languages, with control over timing, appearance, and word highlighting. It also provides redirect URLs for post-creation editing, allowing for user review and adjustments without rebuilding. With webhook integration, users stay updated on render status and completion. The tool is built for scalability, offering advanced composition capabilities to layer multiple video streams, images, and text with precise control. It also features a browser-based editor for client-side rendering with complete privacy.

Devspace is an innovative agent-driven development platform that streamlines the product creation process. It leverages "Astroagents" – AI entities that function as a full-stack product team within the user's browser. Users can simply articulate their product idea, and the Astroagents will manage the entire development lifecycle, including generating specifications, writing code, designing the UI, handling backend development, and deployment. This approach significantly accelerates development, enabling users to build and deploy applications in minutes rather than traditional months-long cycles. The platform is designed to support iterative workflows, making it suitable for product managers, developers, and designers looking to rapidly prototype and build.

DeepQA is an open-source project that provides a TensorFlow implementation of "A neural conversational model," also known as the Google chatbot. This tool enables developers and researchers to build and experiment with deep learning-based conversational agents using a recurrent neural network (RNN) seq2seq model for sentence predictions. It supports various dialogue corpora, including Cornell Movie Dialogs, OpenSubtitles, Supreme Court Conversation Data, and Ubuntu Dialogue Corpus, with options to integrate custom datasets. DeepQA offers functionalities for training models, testing predictions, and visualizing computational graphs with TensorBoard. It also includes a web interface for user interaction, making it suitable for both development and demonstration purposes.

Podaki is an AI-powered backend code generator designed to streamline and accelerate development workflows. By leveraging natural language processing, it allows developers to quickly generate backend code, reducing manual coding effort and speeding up deployment. The tool focuses on making backend development more efficient and accessible, enabling faster iteration and delivery of projects. Its core functionality aims to simplify complex coding tasks, allowing users to focus on higher-level architectural design and business logic rather than repetitive boilerplate code. This approach helps teams ship products faster and maintain a competitive edge.

CAELUS is a comprehensive software platform designed to accelerate nuclear innovation by digitalizing the entire nuclear sector. It provides a secure digital ecosystem that unifies design, licensing, and operation of nuclear systems, leveraging the power of Artificial Intelligence. The platform's modular architecture supports private AI and interoperable tools, transforming complex processes into connected, intelligent workflows. CAELUS offers tailored solutions for various stakeholders including nuclear project developers, reactor designers, supply chain, EPCs, and utilities, enhancing engineering insight with physics-based simulations and strengthening operational safety with real-time monitoring and predictive maintenance. Key modules like NuclearIDE, RegDock, Horizon, and Engine address specific needs from advanced reactor development to authorization management and lifecycle optimization.

ml-diffucoder is an open-source research project accompanying the paper "DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation." It explores how diffusion LLMs (dLLMs) differ from autoregressive models in code generation, investigates data modality differences (code vs. math), and examines diversity and post-training strategies for dLLMs. The project introduces Coupled-GRPO, a novel post-training method designed to enhance DiffuCoder's performance by improving the efficiency and accuracy of log-probability computations during training. The repository provides the implementation of Coupled-GRPO, built upon open-r1, along with scripts for training, data preparation, and inference. It also offers pre-trained DiffuCoder models (Base, Instruct, and cpGRPO) on HuggingFace, complete with usage examples for both base code completion and chat-based instruction following.

GitCase is an innovative platform designed for developers to securely showcase their code. It leverages AI-powered transformations to adapt and protect sensitive parts of your code, ensuring that intellectual property remains confidential while still allowing potential employers or clients to review your work. The tool supports importing GitHub repositories, enabling users to select specific files for transformation. GitCase operates on a flexible, usage-based pricing model, meaning you only pay for the credits you use, with no subscriptions required. It also offers complimentary credits to new users to explore its features, making it an accessible solution for building a secure developer portfolio.

JsonLLM is an AI-powered tool designed to streamline API creation and data extraction processes. It allows users to generate APIs directly from JSON schemas, significantly reducing the manual coding effort typically required for backend development. Beyond API generation, JsonLLM also excels at extracting structured data from various documents, transforming unstructured information into usable formats. This dual capability makes it a valuable asset for developers and data scientists looking to accelerate their workflows. By simplifying both API development and data processing, JsonLLM helps users build robust applications and manage data more efficiently, ultimately enhancing productivity and reducing development time.

ML-University is a comprehensive, open-source platform designed for free learning in the field of machine learning. Curated by an ML enthusiast for the global community, it serves as a continuously updated repository of educational resources. The platform covers a wide array of topics, including Mathematics for ML, Machine Learning, Deep Learning, Natural Language Processing, Reinforcement Learning, Large Language Models, ML in Production, Quantum ML, and provides access to datasets, useful websites, and research papers. Users can contribute to its growth by suggesting improvements or sharing valuable resources through pull requests, fostering a collaborative learning environment for ML practitioners at all levels.

SoyHuCe, a JAKALA company, operates as a Center of Excellence in France, focusing on data, artificial intelligence, and the development of applications powered by algorithms. They provide comprehensive services including data factory solutions, algorithm laboratories for machine learning and R&D, and a digital factory for UX/UI, e-commerce, and custom development. SoyHuCe aims to support clients through every stage of their digital projects, from data storage and analysis to security and value creation, ensuring technological excellence and strategic digital transformation. They emphasize a global vision for digital development, combining strategic, technical, and controlled approaches.