A structured visual roadmap and resource collection that helps developers transition to AI application engineering by linking papers, code, and diagrams for deep learning models.

An LLMOps template for Prompt flow that streamlines the end-to-end lifecycle of LLM applications, from local experimentation and evaluation to production deployment.

An open-source observability library for JavaScript/TypeScript LLM applications that uses OpenTelemetry to trace calls to LLM providers and vector databases.

A multimodal retrieval engine that enables AI applications to search and understand visually rich documents, such as PDFs and charts, without losing spatial or visual context.

A tracking system and dashboard that compares the success rates of AI coding agents by analyzing their pull request merge rates on GitHub.

A Python framework for multi-objective optimization that provides a wide range of evolutionary algorithms, benchmark problems, and tools for statistical analysis.

A Python library for machine learning on graphs that uses sparse matrices for memory-efficient network analysis.

A Julia package for performing efficient nearest neighbor searches using KD-Trees, Ball-Trees, and support for periodic boundary conditions.

A machine learning library that rapidly benchmarks dozens of classification, regression, and time series forecasting models to identify the best performing algorithm without manual tuning.

A post-training compression tool that makes transformer networks smaller and faster by slicing off insignificant weight matrix components using orthogonal transformations.

A modular platform for powergrid operation simulation, providing a Gymnasium-compatible environment for training reinforcement learning agents to manage power networks.

An autonomous task execution system for Claude CLI that monitors usage windows and automatically runs predefined tasks from a Markdown file.

A comprehensive benchmark and toolkit for studying backdoor attacks and defenses in LLMs, featuring a standardized pipeline for poisoning and a suite of seven defense strategies.

Tnlearn is a Python library that builds neural networks from task-based neurons discovered via symbolic regression. It uses either vectorized symbolic regression or LLM-guided equation discovery (DrSR) to fit formulas to tabular data, then embeds these as learnable neurons into an MLP, achieving better accuracy than classical gradient boosting and tabular deep learning methods.

A platform for building RL environments for AI agents across coding, browser, computer-use, and robotics, enabling seamless transition from evaluation to training.

A native full-stack framework for Delphi that provides a unified ecosystem for web APIs, ORM, dependency injection, and AI agent integration via MCP.

A Julia library for architecture-agnostic, high-performance parallel stencil computations that allows domain scientists to write high-level code deployable on both CPUs and GPUs.

A collection of reference applications and tutorials for Vespa, demonstrating how to implement hybrid search, RAG, and multimodal vector retrieval at scale.

A dataset manipulation API for the tech.ml.dataset library in Clojure, providing a high-level, R-inspired interface for data frame operations.

A high-performance Julia library for solving systems of nonlinear equations using a unified API and advanced root-finding algorithms.

A living benchmark for symbolic regression that provides a unified, reproducible framework to compare modern SR methods using diverse datasets and scikit-learn compatible APIs.

A JAX and Flax NNX-based framework for the high-performance training, fine-tuning, and serving of LLMs and multimodal models on TPU/GPU clusters.

Sopify is a development process protocol for AI coding that prevents premature coding by enforcing a plan-first workflow and storing resumable project plans in git-tracked files.

An intelligent data search and enrichment library that automatically finds and integrates accuracy-improving external features into ML pipelines using LLMs and GNNs.

A self-hosted version of Weights & Biases for tracking machine learning experiments and metrics on private infrastructure.

A library that transforms ONNX models into PyTorch models, allowing users to utilize PyTorch's backend and neural network manipulation tools.

A RAG service built with FastAPI and LangChain that provides a REST API for managing document collections and performing semantic searches using PostgreSQL and pgvector.

A pure-Rust machine learning and deep learning library that provides tools for classical ML, neural networks, and evaluation metrics without C/C++ dependencies.

A collection of common utilities and functions used by converters to translate AI models from various frameworks into the ONNX format.

A distributed, high-throughput pipeline for processing web-scale multimodal datasets, featuring Rust-accelerated operators for filtering, scoring, and deduplication.

A deep learning framework for uncertainty quantification that provides tools to make neural networks more reliable through uncertainty-aware training, evaluation, and post-processing.

Unbody is an open-source backend infrastructure project designed to provide a comprehensive data management and indexing system for AI applications.

A toolkit for converting Excel data into Neo4j knowledge graphs, featuring both legacy educational examples and modern GraphRAG and vector-search implementations.

A Go-based vulnerability scanner and exploitation tool for the Spring framework that integrates with AI agents via MCP to automate penetration testing.

A Claude Code plugin that provides persistent memory across sessions by compressing conversations into curated logs and automatically restoring context.

A Python library implementing Natural Gradient Boosting for probabilistic prediction, allowing models to output probability distributions instead of single point estimates.

An orchestration framework that runs multiple Claude Code agents in parallel to systematically fix bugs and implement best practices across large codebases.

A CLI scaffolding tool that generates full-stack, domain-specific AI applications with integrated Neo4j knowledge graphs and agent frameworks.

A TUI application for managing and chatting with local Ollama models and major cloud LLM providers in a single terminal interface.

Rust bindings for Apple's MLX library, enabling high-performance machine learning and array operations optimized for Apple Silicon.

A framework for training and deploying low-bit quantized neural networks on low-end microcontrollers, enabling high-accuracy inference on devices with as little as 2KB RAM.

A collection of example codes and benchmarks for deploying common open-source deep learning algorithms on Axera AI SoC hardware.

An all-in-one web data collection API that handles proxy rotation, CAPTCHA solving, and JavaScript rendering to deliver structured data from public websites.

A professional-grade Burp Suite extension for API security testing that provides automated reconnaissance, intelligent fuzzing, and AI-ready data exports to detect OWASP API Top 10 vulnerabilities.

A framework for feature engineering and data preprocessing in R that uses pipeable sequences of steps to prepare data for machine learning models.

A toolkit for extracting chat history, code context, and diffs from AI coding assistants to create datasets for machine learning training.

An autonomous planning and execution framework for Claude Code and Codex CLI that transforms complex tasks into a single, self-healing autonomous run.

A Python library for predictive uncertainty calibration and conformalization, providing rigorous uncertainty estimations for any machine learning model across various tasks.