Coding & Development

Guardrails Arena is an open-source platform designed to help users jailbreak Large Language Models (LLMs) and test their privacy guardrails. Developed by Lighthouz AI, this tool facilitates the stress testing of LLMs to identify vulnerabilities and evaluate data privacy within AI systems. It promotes community-driven AI testing, allowing users to collaborate in uncovering weaknesses in AI chatbot security. The platform is hosted on Hugging Face, making it accessible for developers and researchers interested in AI safety and security. While the current status shows a build error, its core purpose is to provide a sandbox for ethical hacking and security assessment of AI models.

Gradio Canvas 🤗 is a web application designed to assist users in generating and refining Python code. Inspired by ChatGPT's Canvas, this tool aims to provide a seamless coding experience by offering feedback and suggestions based on user input. Users can enter their coding requests, and the application will generate the corresponding code. While the current live website indicates a runtime error and workload eviction, the underlying concept focuses on leveraging AI for structured code generation, potentially utilizing models like Llama 3.1 405B via Fireworks AI and Instructor for its capabilities.

Aixia AB is a leading partner for AI infrastructure in the Nordics, specializing in providing advanced AI and IT solutions. They offer a comprehensive suite of services including NVIDIA DGX SuperPOD, datacenter solutions, ML Ops, and customized AI solutions. Aixia focuses on simplifying complex IT challenges to help businesses achieve their full potential, offering services like backup and recovery, hyperconverged datacenters, network and security, and server hosting. They are ISO27001-certified and committed to climate-neutral operations, ensuring responsible growth and innovation for their clients.

The tensorflow_cookbook is a comprehensive GitHub repository that serves as a practical guide for implementing machine learning algorithms with TensorFlow. It accompanies the Tensorflow Machine Learning Cookbook by Nick McClure, offering code examples across a wide range of topics. Users can explore chapters dedicated to linear regression, support vector machines, nearest neighbor methods, neural networks, natural language processing, and convolutional neural networks. The repository details how to set up TensorFlow, work with tensors, variables, and operations, implement activation functions, and handle various data sources. It also covers advanced topics like computational graphs, loss functions, backpropagation, and taking TensorFlow models to production, making it an invaluable resource for both learning and applying TensorFlow in real-world scenarios.

trashnet offers a comprehensive dataset of trash images, categorized into six classes: glass, paper, cardboard, plastic, metal, and general trash. This dataset, comprising 2527 images, was collected using various iPhone models under natural lighting conditions and is available for download via Google Drive. Alongside the dataset, trashnet provides the code for a Torch-based convolutional neural network (CNN) designed for garbage image classification. The CNN, developed as a final project for Stanford's CS 229, has achieved approximately 75% test accuracy. The repository includes installation instructions for Lua and Python dependencies, as well as guidance for setting up CUDA for GPU acceleration, making it a valuable resource for students and researchers in machine learning and environmental studies.

tt-metal offers a comprehensive platform for developing and optimizing neural networks on Tenstorrent hardware. It includes TT-NN, a Python & C++ Neural Network OP library, and TT-Metalium, a low-level programming model for kernel development. The platform provides tools like TT-NN Visualizer for analyzing model execution, TT-Exalens for low-level debugging, and TT-SMI for device management. It supports various models including Llama 3.3, Qwen 2.5, Whisper, and Mixtral, with detailed performance metrics. tt-metal is designed for AI developers and hardware engineers looking to leverage Tenstorrent's specialized accelerators for high-performance AI applications, offering extensive documentation and programming examples.

TTRL (Test-Time Reinforcement Learning) is an open-source research project focused on advancing Reinforcement Learning (RL) techniques, particularly for scenarios where ground-truth labels are unavailable during inference. The project investigates how common practices in Test-Time Scaling (TTS), such as majority voting, can generate effective rewards to drive RL training. TTRL has demonstrated significant performance improvements, such as boosting the pass@1 performance of Qwen-2.5-Math-7B by approximately 211% on AIME 2024 using only unlabeled test data. The project provides code and experimental logs, with an implementation based on the 'verl' framework, making it accessible for researchers and developers to reproduce results and further explore test-time reinforcement learning.

unofficial-chatgpt-api offers an unofficial API for ChatGPT, built upon Daniel Gross's WhatsApp GPT package. This tool is designed for developers who need to integrate ChatGPT functionalities into their projects. It operates by using playwright and chromium to simulate browser interactions and parse HTML, effectively creating an API layer over the ChatGPT web interface. The project emphasizes its unofficial nature and is intended strictly for development purposes, providing a flexible way to experiment with ChatGPT's capabilities without direct access to an official API. The repository includes clear instructions for installation and running the server, along with basic API documentation for its single endpoint.

TinyZero offers a minimal reproduction of DeepSeek R1-Zero, focusing on reinforcement learning tasks. Built upon the veRL library, this tool allows 3B base Large Language Models (LLMs) to independently develop self-verification and search capabilities. The project provides scripts and instructions for data preparation and training, including configurations for single GPU and multi-GPU setups, and supports instruct ablation experiments. While the repository is no longer actively maintained, it serves as a valuable resource for understanding and replicating the core concepts of DeepSeek R1-Zero, particularly for researchers and developers exploring advanced RL techniques for LLMs.

TNN is a high-performance, lightweight neural network inference framework developed by Tencent Youtu Lab and Guangying Lab. It provides a uniform deep learning inference solution for mobile, desktop, and server environments. Key features include cross-platform compatibility, high performance, model compression, and code pruning. Building upon the foundations of ncnn and Rapidnet, TNN enhances support and optimizes performance specifically for mobile devices, while also incorporating the extensibility and high-performance characteristics of other open-source frameworks. It has been deployed in various Tencent applications like Mobile QQ, Weishi, and Pitu, and serves as a core acceleration framework for Tencent Cloud AI. TNN supports models from TensorFlow, PyTorch, MxNet, and Caffe via ONNX, and runs on Android, iOS, embedded Linux, Windows, and Linux, compatible with ARM CPU, X86 GPU, and NPU hardware.

tiny-llm provides a comprehensive course for system engineers focused on learning LLM inference serving, specifically tailored for Apple Silicon. The curriculum guides users through building a tiny vLLM using MLX and Qwen, with a codebase primarily utilizing MLX array/matrix APIs. This approach allows participants to construct model serving infrastructure from scratch, gaining deep insights into optimizations. The course covers essential components like attention, RoPE, KV cache, and continuous batching, with a roadmap extending to advanced topics such as Paged Attention and Speculative Decoding. It's designed for those who want to understand the underlying techniques for efficiently serving large language models.

Video-MME is the first-ever comprehensive evaluation benchmark designed to assess the capabilities of Multi-modal Large Language Models (MLLMs) in video analysis. It covers a wide range of visual domains, temporal durations, and data modalities, including short, medium, and long-term videos (from 11 seconds to 1 hour). The benchmark comprises 900 videos totaling 254 hours and 2,700 human-annotated question-answer pairs. It integrates multi-modal inputs beyond video frames, such as subtitles and audios, to provide a full-spectrum evaluation. Video-MME is suitable for both image MLLMs and video MLLMs, offering a robust framework for evaluating model performance in understanding and processing sequential visual data.

vosk-browser is a speech recognition library designed to run efficiently in web browsers, leveraging a WebAssembly build of Vosk. It provides real-time speech-to-text conversion capabilities, making it suitable for integrating voice control and accessibility features into web applications. The library is built to be easy to use, offering installation via npm or CDN. It explicitly compiles Vosk for use in a WebWorker context, ensuring smooth performance without blocking the main thread. Developers can utilize it for microphone input or audio file processing, with support for 13 languages, and access a live demo to see its functionality.

Formless by Typeform is an AI-powered no-code platform designed to create intelligent, conversational forms. It enables users to build forms that can naturally ask and answer questions, engaging respondents more effectively than traditional forms. The tool offers a variety of templates for common use cases such as inbound lead generation, contact sales, feedback collection, quizzes, quote generators, and job applications. Users can train the AI with their own data or by crawling websites to enhance its ability to answer specific questions. Formless supports over 120 languages, allowing for broad international reach, and forms can be embedded across various platforms. It integrates with popular tools like HubSpot, Google Sheets, Mailchimp, Slack, and Pipedrive, streamlining workflows and data management.

WebLLM is a high-performance, in-browser LLM inference engine designed to bring language model inference directly onto web browsers with hardware acceleration. It operates entirely within the browser, eliminating the need for server support and leveraging WebGPU for enhanced performance. The engine is fully compatible with OpenAI API, allowing users to apply the same API functionalities, including streaming, JSON-mode, and function-calling, to open-source models locally. WebLLM supports a wide range of models like Llama 3, Phi 3, Gemma, and Mistral, and allows for custom model integration in MLC format. It offers structured JSON generation, real-time interactions, and supports Web Worker and Service Worker for optimized performance and offline capabilities.

WeightWatcher (WW) is an open-source, diagnostic tool designed to analyze Deep Neural Networks (DNNs) and predict their accuracy. It operates without requiring access to training or even test data, leveraging theoretical research into Heavy-Tailed Self-Regularization (HT-SR), Random Matrix Theory (RMT), Statistical Mechanics, and Strongly Correlated Systems. Users can analyze pre/trained pyTorch, Keras, and other DNN models (Conv2D and Dense layers), monitor model layers for over-training or over-parameterization, and predict test accuracies across different models. The tool also helps detect potential problems when compressing or fine-tuning pretrained models and provides layer warning labels like 'over-trained' or 'under-trained'. It offers various generalization metrics and advanced diagnostics like correlation trap analysis and experimental early stopping detection.

Agent Leaderboard is a Hugging Face Space designed to rank Large Language Models (LLMs) based on their performance in agentic tasks. This tool provides a dynamic platform for users to browse and filter performance leaderboards across various categories, methodologies, and metrics. Users can select specific criteria to instantly update the displayed tables and charts, offering a comprehensive overview of different models' capabilities. It's an essential resource for developers and data scientists looking to compare and evaluate LLMs for their agentic applications, ensuring they can make informed decisions based on up-to-date performance data.

hackingBuddyGPT is an open-source framework designed to empower ethical hackers and security researchers to leverage Large Language Models (LLMs) for discovering new attack vectors and performing security testing. It allows users to build AI hacking agents with minimal code, often in 50 lines or less. The tool supports both SSH connections to remote targets and local shell execution, providing flexibility for testing and development. It aims to become a leading framework for security professionals interested in using LLMs or LLM-based autonomous agents for tasks like privilege escalation, web penetration testing, and API testing. The project also offers reusable Linux privilege escalation benchmarks and publishes open-access reports to aid experimentation.

Hyperparameter-Optimization-of-Machine-Learning-Algorithms is an open-source GitHub repository offering practical implementations of hyperparameter optimization and tuning methods for machine learning and deep learning models. It aims to be easy and clear for users, providing sample code for both regression and classification problems using benchmark datasets like Boston-Housing and MNIST. The repository covers various HPO algorithms such as Grid Search, Random Search, Hyperband, Bayesian Optimization (with GP and TPE), Particle Swarm Optimization, and Genetic Algorithms. It also details the hyperparameter configuration spaces for common ML models like Random Forest, SVM, KNN, and ANN. This resource is ideal for industrial users, data analysts, and researchers looking to effectively tune their machine learning models.

fastn is an embedded integration and automation platform designed for SaaS companies and AI agent builders. It streamlines the process of integrating various tools and systems, eliminating the need for manual development and maintenance of integrations. The platform leverages AI agents to power these integrations, ensuring reliable and efficient workflows. Key features include adaptive context for agents, tool orchestration to reduce context bloat and token usage, and tool composition for lower latency and API costs. fastn also offers performance optimization through caching and schema adaptation, along with comprehensive tracking for auditability. It enforces enterprise-grade security, including RBAC, compliance, and prompt safety, and provides access to over 1000 tools with the ability to build infinite more. The platform is SOC 2 Type II, ISO-Certified, GDPR Compliant, and HIPAA- and PCI-Ready.

WizModel is a platform designed to streamline the deployment and management of machine learning models. It aims to simplify the often complex process of getting ML models into production, allowing users to focus on model development rather than infrastructure. The platform supports model scaling and inference, providing a unified API for seamless integration into existing applications. While specific features are not detailed on the provided website, the core offering revolves around making ML model deployment more accessible and efficient for developers and data scientists.

TheGreatRoadmap offers a streamlined backend solution, enabling users to create database tables and instantly generate REST and GraphQL APIs. It eliminates the need for server setup, deployments, or complex configurations, making it accessible for both technical and non-technical teams. Key features include instant table and schema creation, auto-generated APIs with configurable rate limits and caching, role-based access control, and real-time updates. The platform supports various use cases such as building waitlists, contact forms, internal tools, MVP backends, and AI agent storage, allowing users to focus on their product rather than infrastructure management. It also boasts auto-scaling, low-latency APIs, and reliable data storage with automatic indexing and backups.

MatX specializes in developing high-throughput chips optimized for the demanding requirements of large language models (LLMs). Their MatX One chip is engineered to provide higher throughput than competing products, while also achieving low latencies crucial for various AI workloads. It excels in FLOPS for training and prefill, and offers exceptional latency, FLOPS, and long-context support for decode and reinforcement learning. Key features include the highest FLOPS/mm², efficient handling of weights in SRAM for low latency, and support for over 2000 output tokens/second for large MoE models. The chips also boast robust scale-up and scale-out interconnects, enabling clusters with hundreds of thousands of chips. MatX targets workloads such as training, RL, inference prefill, and inference decode, supporting both large MoE and dense models without an upper limit on model size.

İNKSEN is a technology and consulting company specializing in digital transformation solutions. They offer high-performance services to help businesses navigate the evolving digital world, focusing on business development, efficiency, and strategic management. Their expertise includes mobile application and platform development, Big Data & Analytics, AI & Robotics, DevOps, and UI/UX Design. İNKSEN serves various industries such as Logistics & Transportation, Retail, Wholesale, Customs, and Foreign Trade, providing tailored software and mobile application solutions, including their SPEETTA - TMS product. They emphasize a flexible and scalable project approach, leveraging advanced software engineering experience to meet business needs.