machine-learning Tools

Prompts.chat is a social platform and library for generative AI prompts. It solves the problem of prompt discovery and management by providing a community-driven space to share, find, and organize effective prompts. It's designed for AI enthusiasts, developers, teams, and organizations who want to leverage collective knowledge while maintaining the option for complete privacy through self-hosting.

AI Engineering from Scratch is a comprehensive, open-source curriculum that provides the missing spine for AI education. It solves the problem of scattered, framework-first learning by having you implement every core algorithm—from backprop to transformers—using only math and code, before any libraries are introduced. It's designed for engineers and students who want deep, foundational understanding and the ability to build, debug, and ship AI systems with confidence.

ONNX Runtime is a high-performance inference and training engine for machine learning models. It solves the problem of deploying and running models efficiently across diverse hardware (CPU, GPU, NPU) and software environments (Python, C#, Java, etc.). It's for developers and organizations who need a cross-platform, production-grade solution to speed up AI in their applications.

Modular is a unified AI inference platform built on the open-source MAX serving framework and Mojo programming language. It solves the problem of fragmented AI infrastructure by providing a single, optimized stack that runs efficiently across NVIDIA, AMD, and other hardware, giving developers more deployment options. It's for AI developers and teams who need a simple, powerful, and cost-effective solution for deploying and serving models.

NautilusTrader is a production-grade, open-source trading engine built in Rust. It provides a deterministic, event-driven core with nanosecond resolution to solve the problem of strategy divergence between backtesting and live trading. It is designed for quantitative traders, hedge funds, and institutions who need a reliable, multi-asset, multi-venue platform with shared semantics from research to production.

Soup is a CLI tool that automates the entire fine-tuning stack for large language models. It solves the complexity of configuring training runs by automatically generating optimal settings, handling data preparation, and enabling training of large models on limited hardware through layer streaming. It's for ML engineers and researchers who want to fine-tune models efficiently without vendor lock-in or manual hyperparameter tuning.

Transformers is a comprehensive library providing thousands of pre-trained models for Natural Language Processing (NLP), computer vision, audio, and multimodal tasks. It solves the problem of implementing and deploying cutting-edge machine learning models by offering a unified, easy-to-use API for both inference and training. It is designed for researchers, developers, and practitioners who want to leverage state-of-the-art models without building them from scratch, enabling rapid prototyping and production deployment.

Supervision is a Python library providing a comprehensive set of ready-to-use tools for building and deploying computer vision applications. It solves the problem of repetitive boilerplate code in tasks like object detection, tracking, and annotation, accelerating development. It's designed for AI engineers, researchers, and developers who need reliable, modular components to streamline their computer vision pipelines.

This is a comprehensive, beginner-friendly curriculum designed to demystify Artificial Intelligence. It solves the problem of AI seeming inaccessible by providing a structured, 24-lesson learning path that breaks down complex concepts. It's for absolute beginners, students, or professionals from any field who want to build a solid foundation in AI without a technical background.

Faceswap is a free, open-source software application powered by TensorFlow, Keras, and Python, designed for creating deepfake videos and images. It solves the problem of accessing advanced face-swapping technology by providing a powerful, community-supported tool that runs on Windows, macOS, and Linux. It is for digital artists, video editors, researchers, and enthusiasts who want to explore or utilize deepfake technology in an accessible and ethical framework, supported by comprehensive guides and an active forum.

Speech-to-speech is a platform for creating local voice agents using open-source models. It solves the problem of privacy and vendor lock-in by enabling fully offline, self-hosted voice interactions. It's designed for developers, researchers, and businesses who need to build customizable, private voice assistants and agents without relying on cloud APIs.