Coding & Development

OnsetLab is an open-source framework designed for developers to run tool-calling AI agents locally. This platform empowers users to transform small language models into powerful agents capable of interacting with real tools and operating within their local environments. A key advantage of OnsetLab is its flexibility, offering no cloud lock-in, which ensures data privacy and control. Developers can deploy their agents using various methods, including Python, Docker, or vLLM, providing versatility in integration and deployment strategies. This framework is ideal for those who require robust, locally-run AI solutions without relying on external cloud infrastructure.

LanceDB is a developer-friendly, open-source embedded retrieval library designed for multimodal AI applications. Built on the Lance columnar format, it provides fast, scalable, and production-ready vector search capabilities, allowing users to store, index, and search petabytes of multimodal data and vectors. It supports comprehensive search including vector similarity, full-text, and SQL, along with advanced features like zero-copy and automatic versioning. LanceDB runs locally or in the cloud, offering complete data sovereignty. It integrates seamlessly with popular AI/ML frameworks like LangChain and LlamaIndex, and provides SDKs for Python, Node.js, and Rust, making it a central platform for building, training, and analyzing AI workloads.

aiXbrain GmbH specializes in developing, integrating, and monitoring AI agents for complex industrial applications. As an RWTH Aachen spin-off, the company provides a robust AI platform designed to ensure reliable, secure, and controlled AI operations. Their solutions, including MachineGPT for industrial dialogues and Dataray for domain-specific data intelligence, address common challenges in real-world AI deployment such as unpredictable behavior and integration issues. aiXbrain emphasizes continuous monitoring and optimization to deliver consistent performance, reduce errors, and provide predictable AI behavior, ensuring quality and accountability in operational settings.

DeepXi is a deep learning framework implemented in TensorFlow 2/Keras, designed for a priori Signal-to-Noise Ratio (SNR) estimation. This tool is primarily used for speech enhancement, noise estimation, and mask estimation, and can also serve as a front-end for robust Automatic Speech Recognition (ASR). It supports various deep neural network architectures, including MHANet, RDLNet, ResNet, ResLSTM, and ResBiLSTM, to efficiently model noisy speech. DeepXi offers both causal and non-causal versions of its models, providing flexibility for different application requirements. It operates on mono/single-channel audio at a standard sampling frequency of 16000 Hz, with configurable window duration and shift. The tool supports common audio codecs like .wav, .mp3, and .flac, and provides pre-trained models and datasets for research and development.

Dev-GPT is an open-source AI tool designed to automate the microservice development process, acting as a virtual development team. Users provide a description of the microservice they want to build, and Dev-GPT, comprising a Product Manager, Developer, and DevOps AI, handles the entire lifecycle from concept to deployment. It iteratively builds and tests the microservice, generating code, tests, and Dockerfiles. The tool supports both gpt-3.5-turbo and gpt-4 models, allowing for cost-effective or more complex microservice generation. It can run microservices locally in Docker or deploy them to the cloud via Jina AI, and even generates a Streamlit playground for testing.

Mini-SGLang is a compact and high-performance inference framework specifically designed for Large Language Models (LLMs). It serves as a lightweight implementation of SGLang, aiming to simplify the complexities of modern LLM serving systems. With a codebase of approximately 5,000 lines of Python, it functions as both a capable inference engine and a transparent reference for researchers and developers. Key features include advanced optimizations such as Radix Cache for KV cache reuse, Chunked Prefill to reduce peak memory usage, Overlap Scheduling to hide CPU overhead, Tensor Parallelism for multi-GPU scaling, and optimized kernels like FlashAttention and FlashInfer for maximum efficiency. It supports online serving with an OpenAI-compatible API and an interactive shell mode for direct model interaction.

deepdow is a Python package designed for portfolio optimization using deep learning techniques. It aims to bridge the gap between forecasting market evolution and solving optimization problems by constructing a pipeline of differentiable layers. The tool allows for the creation of networks where the final layer performs asset allocation, with preceding layers acting as feature extractors. The entire network is fully differentiable, enabling optimization via gradient descent algorithms. deepdow is not focused on active trading strategies but rather on finding allocations to be held over a specific horizon. It integrates differentiable convex optimization via `cvxpylayers`, offers various dataloading strategies, and supports integration with MLflow and TensorBoard. It also provides a range of loss functions, including Sharpe ratio and maximum drawdown, and is extensible for customization with both CPU and GPU support.

Superagent offers red team testing for AI agents, designed to identify and prevent data leaks, harmful outputs, and unwanted actions in production systems. It employs specialized attack agents to probe for failures through black-box testing, providing findings, evidence, and remediation guidance. The platform includes Guardrail models to prevent failures at runtime, continuous tests to measure system safety, and a Safety Page to demonstrate compliance and test results to customers. This comprehensive approach helps teams building or deploying AI agents, especially those selling to enterprises or regulated industries, to prove safety and compliance.

DeepSite v4 is an AI-powered web development tool designed to help users build, design, and deploy stunning websites quickly and without requiring code. It features multi-page capabilities for creating complex websites with dynamic routing and navigation, suitable for everything from simple landing pages to full web applications. The platform offers instant auto-deployment and free hosting with a global CDN for fast performance. DeepSite leverages cutting-edge open-source AI models like DeepSeek, MiniMax, and Kimi, ensuring transparency and customization. Its intuitive interface caters to both developers and non-developers, and it integrates seamlessly with Hugging Face models and datasets for advanced AI capabilities. Optimized for speed, DeepSite utilizes edge computing and smart caching.

DeepLearnToolbox is a Matlab/Octave toolbox designed for deep learning research and development. It includes various deep learning models such as Deep Belief Nets (DBN), Stacked Autoencoders (SAE), Convolutional Neural Nets (CNN), Convolutional Autoencoders (CAE), and vanilla Neural Nets (NN). Each model comes with practical examples to guide users through implementation and experimentation. While the toolbox was a valuable resource, it is no longer maintained and is considered outdated. The creator recommends using more modern and actively developed deep learning frameworks like Theano, Torch, or TensorFlow for current projects.

dLLM is an open-source library designed to bring transparency and reproducibility to the development pipeline of diffusion language models. It offers scalable training pipelines, supporting advanced features like LoRA, DeepSpeed, and FSDP, based on the transformers Trainer. The library also provides unified evaluation pipelines built on lm-evaluation-harness, simplifying inference and customization. dLLM includes minimal training, inference, and evaluation recipes for open-weight models such as LLaDA and Dream, and implements various training algorithms like MDLM (masked diffusion) and BD3LM (block diffusion). It also supports accelerated inference and evaluation with Fast-dLLM, offering cache and confidence-threshold decoding.

DD-AIM has developed a patented digital circuit (chip) designed to accelerate predictive AI inference at massive scale. This technology supports thousands of simultaneous models and millions of inference runs in real-time. The chip focuses on the inference side of deep learning, allowing for continuous monitoring, evaluation, and forecasting of real-world systems. It features self-learning, self-optimizing, and self-correcting capabilities for hardware and model errors, with dynamic memory management and computational techniques. The architecture is simplified for lower manufacturing and deployment costs, emphasizing low energy consumption, small size, and minimal heat generation (SWaP-C2). DD-AIM targets applications in defense, healthcare, finance, and retail sectors.

MBATS is an open-source, Docker-based platform designed for quantitative analysts and algorithmic traders to develop, test, and deploy trading strategies, with a strong emphasis on machine learning. It simplifies the process of bringing trading ideas to production by integrating various open-source tools like Backtrader for strategy development, MLflow for managing machine learning models, and PostgreSQL for market data storage. The platform also includes Apache Airflow for orchestrating jobs and Apache Superset for visualizing backtested and live strategy performance. MBATS offers a modular architecture, making it easy to scale and migrate components to cloud environments like GCP, and supports multiple symbol and strategy types for both backtesting and live trading.

DiffusionCLIP is an official PyTorch implementation for text-guided image manipulation using diffusion models, as presented in the CVPR 2022 paper. It addresses limitations of GAN-inversion methods by leveraging the full inversion capability and high-quality image generation of diffusion models. The tool allows for zero-shot image manipulation guided by text prompts, even for diverse real images from datasets like ImageNet. Key features include novel sampling strategies for fine-tuning, accurate in- and out-of-domain manipulation, and a unique noise combination method for straightforward multi-attribute manipulation. It supports fine-tuning for various image types like human faces, churches, bedrooms, and dog faces, and provides a Colab notebook for inference and application.

nn_vis is an open-source project designed for processing and rendering neural networks to visualize their architecture and parameters. Developed as part of a master's thesis, it introduces a novel 3D visualization technique that declutters complex models. The tool estimates attributes for trained neural networks using established optimization methods like batch normalization, fine-tuning, and feature extraction to determine the importance of different network parts. It combines these importance values with techniques such as edge bundling, ray tracing, 3D impostors, and special transparency to create a comprehensive 3D model. nn_vis supports both 2D and VR visualization, allowing users to gain insights into model behavior, especially regarding generalization based on edge proximity. It also provides a GUI for controlling shader parameters and processing settings, enabling customization of the visualization.

draw-a-ui is an innovative application that leverages tldraw and the GPT-4 Vision API to transform hand-drawn mockups into HTML code. Users can sketch a wireframe, and the tool converts the canvas SVG into a PNG image, which is then sent to GPT-4 Vision. The AI processes the image and generates a single HTML file, styled with Tailwind CSS. This tool is presented as a demo for rapid UI prototyping, allowing designers and developers to quickly visualize and implement their ideas. It's important to note that this is a demo project and not intended for production use, lacking authentication features.

NeuralNetwork.NET is a .NET Standard 2.0 library for building neural networks, inspired by TensorFlow and developed entirely in C# 7.3. It enables developers to create sequential and computation graph neural networks with customizable layers. The library offers simple APIs for rapid prototyping, allowing users to define and train models using stochastic gradient descent, as well as save and load network models. A key feature is its GPU support via cuDNN, which significantly enhances performance for training and using neural networks. While no longer actively maintained, it serves as a robust foundation for .NET developers looking to implement machine learning models and custom AI applications, particularly those familiar with C# and .NET environments.

YubHub is an AI-powered platform designed to automate the scraping and enrichment of live job listings directly from company career pages. It provides a comprehensive solution for job boards, programmatic buyers, and recruitment tooling by offering structured data on salary, skills, location, and work arrangements. The platform updates daily, ensuring fresh inventory and eliminating the need for manual intervention. YubHub offers various plans, including a free tier for testing, and supports XML and JSON feeds, making it highly adaptable for integration into existing systems. It's built for the AI era of hiring, providing valuable insights for job seekers, developers, and businesses looking to analyze hiring trends or build custom job feeds.

Novel is an open-source, Notion-style WYSIWYG editor designed to streamline the writing process with AI-powered autocompletion. It allows users to create and edit content within a familiar and intuitive interface, similar to Notion. The tool integrates OpenAI for AI completions and is built on a modern tech stack including Next.js, Tiptap, and Vercel AI SDK. Novel is suitable for developers looking to integrate a powerful editor into their applications, as well as writers and content creators seeking an enhanced writing experience with intelligent suggestions.

FastPhotoStyle is an open-source photo editing tool developed by NVIDIA, designed for photorealistic image stylization. It allows users to transfer the artistic style from a 'style photo' to a 'content photo' using deep learning techniques. The underlying algorithm is detailed in an ECCV 2018 paper, offering a closed-form solution for image stylization. The tool is licensed under CC BY-NC-SA 4.0, making it suitable for research and development in computer vision and graphics. It provides various scripts for demonstration, model downloading, and processing stylization, including options for segmentation-aware stylization.

Federated-Learning-PyTorch provides an open-source implementation of the vanilla federated learning paradigm, as described in the paper 'Communication-Efficient Learning of Deep Networks from Decentralized Data'. This tool is built using PyTorch and allows researchers and developers to conduct experiments on popular datasets such as MNIST, Fashion MNIST, and CIFAR10. It supports both independent and identically distributed (IID) and non-IID data distributions, with options for equal or unequal data splits among users. The implementation focuses on simple models like MLP and CNN to illustrate the effectiveness of federated learning, making it a valuable resource for understanding and experimenting with this distributed machine learning approach.

Alfred AI is an intelligent API assistant designed to transform developer portals by automating workflows and accelerating API operations. It can generate integration code and data models in any language and framework, simplifying the integration process for customers and speeding up onboarding. Users can ask Alfred anything about their API using natural language, and it will instantly provide answers, discover endpoints, and understand API structures. This tool aims to reduce integration support requests by 15x and accelerate API integrations, discovery, and adoption by 10x. Alfred AI can be easily embedded into any developer portal with a single line of code and an OpenAPI Specification, making it a powerful addition for enhancing developer experience and boosting revenue.

facenet offers a TensorFlow-based implementation for face recognition, drawing inspiration from the "FaceNet: A Unified Embedding for Face Recognition and Clustering" paper and ideas from Oxford's "Deep Face Recognition." The project is open-source and available on GitHub, providing a robust framework for developers and researchers. It includes pre-trained models, supports various training datasets like CASIA-WebFace and VGGFace2, and incorporates face alignment using MTCNN for improved accuracy. The tool is compatible with TensorFlow r1.7 and Python 2.7/3.5, making it accessible for those working with these environments. It also features a flexible input pipeline and continuous integration for reliable development.

Alegria.group is a European leader in AI, NoCode, and Automation, providing extensive training and consulting services for both individuals and businesses. For individuals, Alegria.academy offers programs to develop new skills, launch activities, and improve productivity, including specialized training in AI & NoCode, Expert Airtable, and Lowcode Product Builder. Businesses, from scale-ups to large enterprises, can leverage Alegria.Solutions for AI strategy consulting, team training, and solution deployment to boost operations and reduce costs. Recognized by the French government as an AI Ambassador, Alegria.group combines expertise with partnerships with leading tools like Make, Notion, and Airtable to maximize impact and productivity.