Coding & Development

Minded, previously known as AgentsForce, is an innovative AI agent platform designed to empower users to build and deploy AI agents by simply recording their work. This approach eliminates the need for complex API integrations, allowing agents to operate like humans across existing tools and systems. The platform offers an intuitive drag-and-drop AI editor for agent creation and customization, alongside an AI Recorder that captures screen actions to train agents. Minded is built for regulated industries, providing full audit trails, SSO, and robust permission management, ensuring data security and compliance. It supports processing documents in any format with human-level accuracy and allows for management of AI agents using natural language.

Open-Claude-Cowork is an open-source desktop AI assistant designed to streamline programming, file management, and a wide array of other tasks. It serves as a genuine AI collaboration partner, moving beyond simple GUIs to offer a more interactive experience. Unlike terminal-only solutions, Agent Cowork runs as a native desktop application, providing visual feedback and convenient session management across projects. It reuses existing Claude settings, eliminating the need for a separate development environment or Claude Code installation. This tool is particularly beneficial for users seeking a persistent desktop AI assistant with visual insights into AI operations and efficient project organization.

facial-expression-recognition-using-cnn is an open-source project designed for deep facial expression recognition using Convolutional Neural Networks (CNN) with OpenCV and TensorFlow. It can analyze facial expressions from both static images and real-time camera streams, categorizing them into emotions like Angry, Disgust, Fear, Happy, Sad, Surprise, and Neutral. The tool allows for training models on datasets like Fer2013, optimizing hyperparameters, and evaluating performance. It supports the integration of additional features such as face landmarks and HOG features to improve accuracy, providing a robust framework for researchers and developers interested in emotion detection and facial analysis.

Sciloop specializes in creating high-quality, expert-crafted evaluation and training data for advanced AI models, particularly focusing on reasoning capabilities. Their network comprises Olympiad medalists and top researchers across mathematics, physics, chemistry, biology, and computer science, ensuring the data is built to challenge frontier models. Sciloop offers various data types including benchmark sets, Supervised Fine-Tuning (SFT) data, Reinforcement Learning from Human Feedback (RLHF) data, and reward modeling data. The platform also allows domain experts to contribute by solving complex problems, earning compensation for their submissions, and provides a continuous data streaming service for AI labs.

opcode is a robust desktop application built with Tauri 2, designed to enhance interaction with Claude Code. It offers a visual interface for managing Claude Code sessions, creating custom AI agents with specific system prompts and behaviors, and tracking usage analytics including API costs and token breakdowns. The tool features a visual project browser, session history, smart search, and a timeline with checkpoints for session versioning and instant restore. Additionally, opcode includes an MCP Server Manager for configuring Model Context Protocol servers and a built-in editor for CLAUDE.md files with live preview and syntax highlighting, making AI-assisted development more intuitive and productive.

garak is an open-source LLM vulnerability scanner designed to identify and assess weaknesses in large language models. It probes for a wide range of issues including hallucination, data leakage, prompt injection, misinformation, toxicity generation, and jailbreaks. Inspired by tools like nmap and Metasploit Framework, garak focuses on making LLMs or dialog systems fail through static, dynamic, and adaptive probes. It supports various LLM platforms such as Hugging Face, OpenAI, AWS Bedrock, Replicate, Cohere, and Groq, and can be installed via pip or cloned from source. The tool provides detailed logging and reporting in JSONL format, helping developers and researchers understand and mitigate risks in their AI models.

PlotNeuralNet is an open-source library that provides Latex code for generating neural network diagrams. This tool is designed to help researchers, students, and professionals create high-quality visualizations of deep neural network architectures for academic papers, presentations, and reports. It supports various network representations, including FCN-8, FCN-32, and Holistically-Nested Edge Detection, with examples provided for easy understanding. Users can install necessary packages on Ubuntu or Windows (via MikTeX and Git Bash/Cygwin) and utilize either Latex or Python interfaces to define and generate their network diagrams. The project encourages community contributions for improvements and bug fixes, making it a collaborative effort for better visualization tools.

Pose-Transfer is an open-source project providing the code for person image generation, implementing the Progressive Pose Attention method detailed in a CVPR19 paper. This tool allows users to transfer poses from one image to another, and also supports generating videos from a single input image. It offers functionalities for data preparation, including dataset splitting and keypoint annotation for datasets like Market1501 and DeepFashion. Users can train and test models, and evaluate performance using metrics such as SSIM, IS, DS, and PCKh. The project is built on PyTorch and provides pre-trained models for convenience.

rq-vae-transformer is the official open-source implementation of "Autoregressive Image Generation using Residual Quantization" (CVPR 2022). This framework, consisting of RQ-VAE and RQ-Transformer, is designed for autoregressive modeling of high-resolution images. It precisely approximates feature maps and represents images as stacks of discrete codes, facilitating the generation of high-quality images. The tool supports image generation using both class and text conditions, with pretrained checkpoints available for various datasets including FFHQ, LSUN, ImageNet, and CC-3M. It also includes a large-scale RQ-Transformer for text-to-image generation, trained on millions of text-image pairs. The repository provides code for training and evaluation pipelines, as well as Jupyter notebooks for easy text-to-image generation.

Pod Genie transforms your existing written content, such as articles and blog posts, into engaging audio podcasts using AI. It automates the entire process, from sourcing content to adapting it for an audio experience and converting it into a polished, high-quality podcast. The platform offers natural-sounding AI voices, ensuring a human-like listening experience. Users can choose between individual article podcasts or weekly summaries and select from multiple podcast templates or create their own. Pod Genie also distributes podcasts to major platforms like Spotify and Apple Podcasts and offers translation services for global reach. Additionally, it can convert written content into short-form video shorts for social media platforms like TikTok and Instagram Reels.

Self-attention-cv is an open-source repository offering implementations of diverse self-attention mechanisms specifically tailored for computer vision applications. Built in PyTorch, it leverages `einsum` and `einops` for efficient and flexible module creation. The repository serves as an ongoing collection of building blocks, enabling developers to integrate advanced attention models into their projects. It supports a range of computer vision tasks, including image recognition and segmentation, with examples for Multi-head attention, Axial attention, Vision Transformers (ViT), and TransUnet. It also includes various positional embedding implementations.

jetson-containers is an open-source, modular container build system designed for NVIDIA Jetson and JetPack-L4T platforms. It provides a comprehensive collection of the latest AI/ML packages, facilitating the deployment of CUDA containers for edge AI and robotics applications. Users can easily combine various packages like PyTorch, TensorFlow, and ROS2 to create custom containers. The tool includes helper scripts for building and running containers, with features like `autotag` to find compatible images and a Pip server for caching wheels to accelerate builds. It supports different CUDA versions and offers detailed documentation for system setup, building, and running containers, making it a robust solution for developers working with NVIDIA Jetson devices.

On-Call Health is an open-source tool designed to proactively identify early warning signs of overload in on-call engineers, aiming to prevent burnout. It integrates with popular incident management and project tracking tools like Rootly, PagerDuty, GitHub, Linear, and Jira to gather relevant data. The tool combines this data with self-reported check-ins from engineers and tracks various metrics against both personal and team baselines. By providing insights into potential overwork, On-Call Health helps organizations maintain a sustainable on-call rotation and improve engineer well-being. Its open-source nature allows for transparency and community contributions.

StyleSwin is an official implementation of a transformer-based Generative Adversarial Network (GAN) designed for high-resolution image generation, as presented at CVPR 2022. It leverages a Swin transformer within a style-based architecture, incorporating local and shifted window attention for computational efficiency and modeling capacity. A key innovation is the double attention mechanism, which combines local and shifted window contexts to enhance generation quality. StyleSwin also addresses the challenge of spatial coherency in high-resolution synthesis by employing a wavelet discriminator to suppress blocking artifacts. The tool demonstrates superior performance over prior transformer-based GANs, particularly at resolutions like 1024x1024, achieving competitive results with StyleGAN on datasets such as CelebA-HQ and FFHQ.

MergeFund is a platform designed to change how work gets done, particularly in the open-source and project-based work economy. It connects companies with a vetted network of developers, designers, and researchers, enabling outcome-based work where payment is made only upon validated completion of deliverables. The platform supports both open-source and closed-source projects, offering features like bounty posting, a vetted contributor network, project dashboards for management, and flexible payment options including fiat and cryptocurrency. MergeFund aims to address the open-source funding crisis by allowing communities to fund repositories and maintainers to create bounties, ensuring contributors are compensated for their work without hourly tracking.

Tennis_analysis is an open-source project designed to analyze tennis players and ball movements within video footage. It leverages advanced computer vision techniques, including YOLO v8 for player detection and a fine-tuned YOLO model for tennis ball detection. Additionally, the tool utilizes Convolutional Neural Networks (CNNs) to accurately extract court keypoints, providing a comprehensive understanding of on-court activity. This project is ideal for individuals looking to enhance their machine learning and computer vision skills through a practical, hands-on application. It measures player speed, ball shot speed, and the total number of shots, offering valuable insights for performance analysis.

keras2cpp is an open-source project designed to facilitate the porting of Keras neural network models into pure C++ code. This tool is particularly useful for developers who need to deploy Keras models in environments where C++ is the preferred or required language. It stores both the neural network's weights and architecture in plain text files, ensuring transparency and ease of inspection. While initially prepared to support simple Convolutional networks, such as those found in MNIST examples, its design allows for easy extension to accommodate more complex architectures. The current implementation includes ReLU and Softmax activations and is compatible with the Theano backend, providing a robust solution for integrating Keras models into C++ applications.

torchMoji is an open-source PyTorch implementation of the DeepMoji model, designed for advanced sentiment, emotion, and sarcasm analysis in text. Trained on 1.2 billion tweets with emojis, it excels at understanding nuanced emotional content. The tool provides capabilities for extracting emoji predictions, converting text into 2304-dimensional emotional feature vectors, and fine-tuning the model for transfer learning on new datasets. It's ideal for researchers and developers looking to integrate sophisticated emotional intelligence into their applications, offering a robust foundation for various text modeling tasks. The project includes examples and scripts to facilitate easy adoption and experimentation.

Lingua is a natural language detection library specifically designed for Java and JVM environments. Its primary function is to accurately identify the language of provided textual data, serving as a crucial preprocessing step for natural language processing applications like text classification and spell checking. Unlike other libraries that struggle with short text snippets, Lingua excels in detecting languages even from single words or phrases, leveraging n-grams of sizes 1 to 5. It combines a rule-based engine, which filters languages based on unique characters and alphabets, with a probabilistic n-gram model. This dual approach ensures high accuracy without relying on external APIs or dictionaries, making it suitable for offline use. Lingua currently supports 75 languages, prioritizing quality and accuracy over sheer quantity.

LIBXSMM is an open-source library designed to accelerate specialized dense and sparse matrix operations, as well as deep learning primitives like small convolutions. It specifically targets Intel Architecture, including Intel SSE, AVX, AVX2, AVX-512 (with VNNI and Bfloat16), and Intel AMX. The library achieves high performance through Just-In-Time (JIT) code specialization, making it compiler-independent and suitable for a "build once and deploy everywhere" approach. It supports various GEMM datatypes including FP64, FP32, bfloat16, int16, and int8. LIBXSMM provides interfaces for Matrix Multiplication (MM), Tensor Processing Primitives (TPP), Deep Neural Networks (DNN), and auxiliary service functions, offering both C/C++ and Fortran interfaces for integration into diverse projects.

TurboTransformers is an open-source, fast, and user-friendly runtime environment designed for transformer inference on both CPU and GPU. Developed by WeChat AI, it supports various transformer models including BERT, ALBERT, GPT2, and Decoders. A key feature is its ability to handle variable length inputs without requiring time-consuming offline tuning, allowing for real-time changes in batch size and sequence length. It offers excellent CPU/GPU performance and includes smart batching to minimize zero-padding overhead for requests of different lengths. TurboTransformers provides both Python and C++ APIs, and can be integrated as a plugin for PyTorch, enabling end-to-end acceleration with just a few lines of code. It has been successfully applied in Tencent's online BERT service scenarios, demonstrating significant acceleration for services like WeChat FAQ and QQ recommendation systems.

Lowdefy is an open-source, config-first web stack designed to bridge the gap between AI-generated code and human maintainability. It enables users to build applications where AI can quickly generate concise, schema-validated configurations, which are then easily reviewable and maintainable by human teams. This approach addresses the challenges of scaling AI-generated code, such as inconsistency and hidden vulnerabilities. Lowdefy provides a full-stack, production-ready environment built on Next.js and Auth.js, offering over 70 UI components, 50 logic operators, and 10 data connectors for various databases and APIs. It also includes robust authentication and role-based access control, with extensibility through npm plugins for custom blocks, connections, and operators.

TransUNet is an official open-source project designed for medical image segmentation, utilizing a Transformer encoder and decoder architecture. This innovative approach allows for robust analysis of both 2D and 3D medical data, surpassing traditional methods like nn-UNet in certain benchmarks. The project provides pre-trained ViT models and readily available datasets, simplifying setup for researchers and developers. It is particularly effective for tasks such as segmenting organs in CT scans (Synapse dataset) and brain tumors (BraTs challenges). The repository includes detailed instructions for environment setup, training, and testing, making it accessible for those working on AI-powered diagnostic tools and medical image analysis.

machine-learning-samples is an open-source repository offering various sample applications developed with AWS' Amazon Machine Learning (AML). It includes practical code examples for diverse use cases such as targeted marketing, social media filtering, and mobile prediction. Developers can find samples for targeted marketing in Java, Python, and Scala, demonstrating how to use the AML API. Additionally, there's a sample for social media filtering that integrates Amazon Mechanical Turk for data labeling and AWS Lambda for automated tweet monitoring. Mobile prediction samples are available for both iOS and Android, showcasing real-time ML predictions from mobile devices. The repository also features a k-fold cross-validation sample in Python for model evaluation and a collection of utility scripts.