Coding & Development

PromptLeo is a GDPR-compliant AI workspace developed and hosted in Germany, designed for teams to collaborate on prompts, projects, and tasks. It allows users to automate workflows, connect various business tools, and deploy AI agents trained specifically on their company's data. Going beyond simple chat interfaces, PromptLeo focuses on building specialized AI agents that can access databases, files, APIs, and business systems to provide accurate, data-grounded responses. The platform emphasizes privacy and GDPR compliance, offering features like workspace isolation, robust RAG infrastructure to reduce hallucinations, and the ability to bring your own API keys for AI providers like OpenAI and Anthropic.

KoAlpaca is an open-source language model designed to understand Korean instructions, building upon the Stanford Alpaca model's training methodology. It offers several models, including those based on Polyglot-ko (5.8B and 12.8B) for enhanced Korean performance and LLAMA (7B, 13B, 30B, 65B) for broader language capabilities. The project provides code examples for running the models via Huggingface Pipeline and Gradio, along with detailed instructions for dataset creation (v1.0 and v1.1), which involved translating Stanford Alpaca data and generating new data from Naver Q&A using ChatGPT. KoAlpaca aims to improve upon the original Alpaca's tendencies for short answers and lack of context understanding, particularly for Korean language tasks.

EVI Safety Technology offers AI-powered CCTV analytics and comprehensive investigation tools designed to enhance maritime safety and operational efficiency. The system continuously monitors vessel activity and crew movement, using AI to recognize unsafe behaviors, near-miss situations, and operational risks in real-time. It integrates with existing CCTV infrastructure, including IP cameras and NVRs, and operates fully offline at sea, syncing compressed data when connectivity is available. EVI supports a full investigation path by combining video evidence, crew input, and incident data, facilitating structured reporting for HSE performance reviews and fleet-wide safety improvements. It is suitable for various vessel types, including tankers, bulk carriers, and container ships, and helps meet maritime compliance and reporting standards like ISM, ISPS, and IMO requirements.

Presight is a leading AI and big data analytics company headquartered in Abu Dhabi, operating across four continents. It specializes in delivering high-impact solutions that integrate data, analytics, and AI to address complex challenges such as energy efficiency, crisis management, digital sovereignty, and public safety. Presight offers a range of products including the end-to-end data and AI platform Presight Synergy, the secure GenAI and Agentic AI Platform Presight Vitruvian, and the unified AI and IoT engine Presight IntelliPlatform for smart cities. The company focuses on transforming industries through mission-critical AI, with applications in public safety, finance, smart cities, energy, and education. Presight emphasizes sustainable AI designed with ESG principles and has developed ENERGYai, an agentic AI platform for energy optimization.

CodeCopilot AI functions as an AI pair programmer, assisting developers in enhancing their coding efficiency and quality. The tool is equipped with capabilities for code debugging, providing explanations for complex code segments, and optimizing code for better performance. It also automates aspects of code review, offers intelligent suggestions during the coding process, and supports multiple programming languages. The primary goal of CodeCopilot AI is to boost developer productivity and streamline various stages of the coding workflow, making it easier to manage and improve code.

Deepdrive is an open-source simulator designed to facilitate experimentation and advancement in self-driving AI. It enables anyone with a PC to develop and test state-of-the-art autonomous driving systems within a realistic simulated environment. The simulator supports various AI agent types, including forward-agents, remote agents, and baseline agents like Mnet2 and C++ FSM/PID. Users can record training data for imitation learning, convert data to TFRecords, and train models using provided datasets or their own. Deepdrive offers detailed observation data, including vehicle dynamics, camera feeds (image, depth), and environmental information, all adhering to Unreal Engine conventions for units and rotations. It requires Linux, Python 3.6+, 10GB disk space, and 8GB RAM, with optional GPU requirements for baseline agents.

DeepExplain offers a comprehensive framework for understanding the behavior of deep neural networks through various attribution methods. It enables researchers and practitioners to interpret existing models and benchmark new attribution techniques. The tool supports both gradient-based methods like Saliency maps, Gradient * Input, Integrated Gradients, DeepLIFT, and epsilon-LRP, as well as perturbation-based methods such as Occlusion and Shapley Value sampling. DeepExplain is compatible with TensorFlow (V1) and Keras with a TensorFlow backend, providing flexibility for different development environments. Its capabilities help in identifying which input features contribute most to a network's output, aiding in debugging and model transparency.

Meshed-Memory Transformer (M²) is an open-source project that provides the reference code for the paper "Meshed-Memory Transformer for Image Captioning" presented at CVPR 2020. This tool is designed for researchers and developers working in computer vision and natural language processing. It allows users to set up a conda environment, download necessary data like COCO annotations and detection features, and then evaluate or train their own image captioning models. The repository includes scripts for both testing and training, with configurable arguments for batch size, number of memory vectors, and learning rate scheduling. It requires Python 3.6 and specific data preparation steps to function correctly.

DeepSite v2 is an innovative AI-powered platform designed to simplify website creation for users without coding knowledge. By leveraging artificial intelligence, it allows individuals to generate complete websites based on their ideas or requirements. The tool aims to streamline the development process, enabling users to quickly bring their web projects to life. While currently paused, its core functionality focuses on transforming user input into functional website designs, offering a preview and saving mechanism for generated projects. This makes it an accessible solution for rapid prototyping and web development.

dl_tutorials is an open-source GitHub repository offering a comprehensive set of deep learning tutorials, structured into weekly modules. It guides users through fundamental concepts such as Python basics, logistic regression, and optimization methods, progressing to advanced topics like Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and their applications in image detection, semantic segmentation, and handwriting generation. The tutorials include practical exercises, such as implementing MLPs and CNNs on custom datasets, and cover modern architectures like AlexNet, GoogLeNet, and Residual Networks. It also delves into advanced concepts like deep reinforcement learning, adversarial attacks, and generative adversarial networks, making it a valuable resource for those looking to understand and implement deep learning techniques.

nucleotide-transformer is an open-source repository from InstaDeep AI, dedicated to advancing genomics and transcriptomics through cutting-edge deep learning models. It features a collection of transformer-based genomic language models and innovative downstream applications, including the Nucleotide Transformer (NT), Agro Nucleotide Transformer (AgroNT), SegmentNT, and ChatNT. The platform provides powerful, reproducible, and accessible tools for unlocking new insights from biological sequences, offering pre-trained weights, inference code, and research contributions. It supports various tasks such as functional-track prediction, genome annotation, controllable sequence generation, and single-cell transcriptomics, making it a central hub for AI-driven genomic research.

Erasing is an open-source project designed to remove specific concepts from diffusion models, offering a powerful way to fine-tune AI image generation. The tool provides updated code with diffusers support, significantly reducing GPU memory usage and increasing training speed by 5-8 times compared to older versions. It supports various diffusion models including SDv1.4, SDXL, FLUX, and FLUX.2 Klein, allowing users to erase entire concepts or precise attributes from concepts (e.g., removing hats from cowboys). The project includes installation guides, training instructions, and scripts for generating images and running a local Gradio demo, making it valuable for AI researchers and developers working with generative models.

OctNet is an open-source framework designed for deep learning with sparse 3D data, utilizing efficient space partitioning structures known as octrees. This approach significantly reduces the memory and compute requirements of 3D convolutional neural networks, allowing for the development of deep networks at high resolutions. By hierarchically partitioning space and storing pooled feature representations in leaf nodes, OctNet focuses memory allocation and computation on relevant dense regions. This enables deeper networks without sacrificing resolution, making it suitable for tasks such as 3D object classification, orientation estimation, and point cloud labeling. The framework includes core CPU and GPU code for network operations, data pre-processing tools, and a Torch wrapper for full network integration.

e3nn is an open-source, modular framework designed to facilitate the development of neural networks with Euclidean symmetry. It provides fundamental mathematical operations such as tensor products and spherical harmonics, essential for building E(3) equivariant neural networks. The library is under active development, with breaking changes indicated by version number increments. It is recommended to install using pip, and users can contribute to its development or seek help through discussions and bug reports on GitHub. The framework is backed by research papers on Euclidean Neural Networks and e3nn itself, with BibTeX entries available for citation.

mPLUG-Owl is a family of multi-modal large language models (MLLMs) designed to enhance language models with multimodality through a modular approach. The project includes several iterations: mPLUG-Owl, mPLUG-Owl2, and mPLUG-Owl3, each building upon the previous version to offer improved capabilities. mPLUG-Owl2, for instance, was accepted by CVPR 2024 as a Highlight, and mPLUG-Owl2.1 provides a Chinese-enhanced version. The latest iteration, mPLUG-Owl3, focuses on long image-sequence understanding. The source code and weights for these models are available on HuggingFace, making them accessible for researchers and developers to integrate and experiment with.

mteb (Massive Text Embedding Benchmark) is an open-source Python library designed for comprehensive evaluation of text and multimodal embeddings. It offers a standardized framework to benchmark the performance of different embedding models across a wide array of tasks, including classification, clustering, semantic textual similarity (STS), retrieval, and reranking. The tool supports both monolingual and multilingual evaluations, with a focus on reproducibility and ease of use. Developers and researchers can use mteb to select models, define custom models, run evaluations, and analyze results, contributing to an interactive leaderboard that tracks the state-of-the-art in embedding performance. Its modular design allows for easy integration of new models, datasets, and benchmarks.

finetrainers is a work-in-progress library from Hugging Face designed for scalable and memory-optimized training of diffusion models. It provides support for various commonly used training algorithms, including DDP, FSDP-2, HSDP, and CP. Key features include LoRA and full-rank finetuning, conditional control training, and memory-efficient single-GPU training. The library also supports multiple attention backends like flash, flex, sage, and xformers, along with auto-detection of common dataset formats. It's built to handle combined image/video datasets, multi-resolution bucketing, and offers memory-efficient precomputation. finetrainers is recommended for use with PyTorch 2.5.1 or above for optimal performance and reproducibility.

FlexFlow Train is an open-source deep learning framework designed to accelerate distributed deep neural network (DNN) training. It achieves this by automatically searching for and implementing efficient parallelization strategies. The tool helps optimize the training process, reducing the time required for model development and improving overall efficiency. It supports various deep learning models and hardware configurations, making it a versatile solution for researchers and developers working with large-scale DNNs. The project is developed and maintained by teams from several prominent institutions, including CMU, Facebook, Los Alamos National Lab, MIT, Stanford, and UCSD.

Gemma is an open-weight Large Language Model (LLM) library developed by Google DeepMind, leveraging research and technology from the Gemini models. This repository offers the implementation of the gemma PyPI package, providing a JAX library for both using and fine-tuning Gemma models. It supports multi-turn, multi-modal conversations and offers various versions of Gemma. The library is designed to run on CPU, GPU, and TPU, with specific RAM recommendations for GPU usage (8GB+ for 2B checkpoint, 24GB+ for 7B checkpoint). Extensive documentation, Colabs, and tutorials are available for sampling, multi-modal fine-tuning, and LoRA.

FunASR is a fundamental end-to-end speech recognition toolkit designed to bridge the gap between academic research and industrial applications. It offers a comprehensive suite of features including speech recognition (ASR), Voice Activity Detection (VAD), Punctuation Restoration, Language Models, Speaker Verification, Speaker Diarization, and multi-talker ASR. The toolkit provides convenient scripts and tutorials for both inference and fine-tuning of pre-trained models. FunASR boasts a vast collection of academic and industrial pre-trained models available on ModelScope and Hugging Face, including the highly accurate and efficient Paraformer-large. Recent updates include support for large models like Fun-ASR-Nano-2512 (31 languages), Whisper-large-v3-turbo, and Qwen-Audio multimodal models, alongside continuous improvements in real-time and offline transcription services, memory optimization, and multi-platform support.

PromptWizard is an open-source, task-aware, agent-driven framework designed for optimizing prompts used with Large Language Models (LLMs). It features a self-evolving mechanism where the LLM itself generates, critiques, and refines its own prompts and in-context learning examples. This iterative feedback loop ensures continuous improvement in task performance. The framework focuses on holistic optimization by evolving both instructions and examples, generating synthetic, diverse, and task-aware examples. It also supports self-generated Chain of Thought (CoT) steps and offers various scenarios for prompt optimization, including with and without training data, and the generation of synthetic examples. Users can configure hyperparameters and integrate with custom datasets, making it a flexible tool for developers and researchers working with LLMs.

Midjourney Prompts Generator is an AI tool designed to assist users in creating compelling and varied prompts specifically for AI art generation platforms like Midjourney. It aims to alleviate creative blocks by offering a wide array of styles, themes, and conceptual suggestions. The generator simplifies the ideation phase, enabling creators to efficiently produce distinctive visual content. By providing a structured approach to prompt creation, it helps users explore new artistic directions and achieve more precise and imaginative results from their AI art models. This tool is particularly useful for those looking to enhance their AI art workflow and generate unique outputs.

PointNet is a novel deep learning architecture specifically designed for processing point clouds, which are an important type of geometric data structure. Unlike traditional methods that convert point clouds into regular 3D voxel grids or image collections, PointNet directly consumes unordered point sets, respecting their permutation invariance. This approach makes it highly efficient and effective for a range of applications, including object classification, part segmentation, and scene semantic parsing in 3D. Developed by researchers at Stanford University, PointNet is available as an open-source project on GitHub, providing code and data for training classification and part segmentation networks. It has also served as a foundational work for subsequent advancements like PointNet++.

gpt-macro is a Rust procedural macro that leverages ChatGPT to generate code during the compilation process. Developers can use natural language prompts within their Rust code to instruct ChatGPT to fill in incomplete functions or generate test cases. This tool streamlines development by automating repetitive coding tasks and enabling rapid prototyping. It integrates directly into the Rust build system, parsing prompts and target code, then replacing the target with code extracted from ChatGPT's response. This allows the Rust compiler to continue with the generated code, making it a powerful assistant for Rust developers.