Quepid is a tool that turns search relevance tuning into a repeatable engineering process, helping teams collaborate and test search results to improve app search quality.

KH Coder is a software tool for quantitative content analysis and text mining used for computational linguistics across multiple languages.

CaptchaSolver is a JDownloader 2 plug‑in that uses a YOLO/Darknet neural‑network model (run via Node.js) to automatically solve 6‑digit and geometric captchas for a handful of file‑hosting sites. It provides pre‑compiled binaries for Windows/Linux (amd64) and build instructions for other platforms, letting users run JDownloader fully unattended on servers or NAS devices.

A secure computation device that uses Secure Multi-Party Computation (MPC) to perform tensor operations on private data while keeping it protected.

GUDHI is a C++ and Python library for Topological Data Analysis (TDA) and Higher Dimensional Geometry Understanding, focusing on simplicial complexes and persistent homology.

A Blender add-on for visually creating OpenDRIVE and OpenSCENARIO driving scenarios for autonomous driving and ADAS testing.

A linear dimensionality reduction tool that decomposes complex population activities into components tied to specific task parameters, such as stimuli or rewards.

A benchmarking suite for machine learning and optimization workflows designed to ensure reproducibility and comparability across solvers written in multiple programming languages.

A collection of sample implementations and templates for creating custom Web API enrichment skills to extend the indexing pipelines of Azure AI Search.

Raix is a Ruby library that adds LLM chat, tool (function) dispatch, and prompt‑chain capabilities to any Ruby class. It wraps multiple providers via RubyLLM/OpenRouter, manages a transcript, offers global/class/instance hooks, supports JSON mode, caching, and prompt caching, and provides a DSL for declaring functions and multi‑step prompts.

A lightweight Python library for parsing CoNLL-U formatted NLP data into nested dictionaries or dependency trees.

An iOS integration example demonstrating the use of Faceunity's Nama SDK for real-time face AR, beautification, and motion tracking.

Flytekit Python is the official SDK for Flyte, letting you write, test, and deploy AI/ML workflows in pure Python using `@task` and `@workflow` decorators. Install with `pip install flytekit`, follow the quick‑start guide, and extend via plugins or contribute through the provided docs.

An AI-powered tool for generating traditional Chinese Spring Festival couplets, supporting both custom OpenAI-compatible API keys and a managed account system.

A rendering and component library focused on the annotation experience, designed to help developers quickly build data labeling applications.

A machine learning extension for Beancount importers that predicts transaction accounts and payees based on historical ledger data.

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

A library of probabilistic data structures for fast similarity estimation and cardinality counting on massive datasets.

A Python library for evaluating multiple object tracking results using standard metrics like MOTA, MOTP, IDF1, and HOTA.

A Java toolkit for computing similarity scores between words, phrases, sentences, and paragraphs, featuring sentiment analysis and Word2vec-based synonym discovery.

Anserini is a toolkit built on Apache Lucene designed to make information retrieval research reproducible and bridge the gap between academic baselines and real-world search applications.

A traffic scenario definition and execution engine for the CARLA simulator used to test and prepare autonomous driving agents.

A JupyterLab extension that provides real-time GPU usage dashboards and one-click GPU acceleration for pandas and scikit-learn.

A real-time Python-based anomaly detection and performance monitoring system that automatically identifies anomalies in high-resolution time series data without requiring manual threshold configuration.

A VS Code extension that enhances the dbt development experience with autocomplete, visual lineage, and automated documentation generation.

An open-source AI SaaS boilerplate that provides the monetization, billing, and infrastructure needed to turn AI prototypes into paid products.

CodaLab is an open-source web platform for organizing and operate scientific challenges and competitions in machine learning and advanced computation research.

A Python library for system identification and time series forecasting using NARMAX models, offering tools for model structure selection and parameter estimation.

Mapviz is a ROS-based visualization tool with a plug-in system specifically designed for visualizing 2D robotic data.

A GPU-accelerated portfolio optimization framework that uses NVIDIA cuOpt and RAPIDS cuML to speed up scenario generation and Mean-CVaR risk modeling.

An open-source AI agent orchestrator that allows developers to run multiple AI coding agents in parallel across isolated git worktrees.

An AI-powered Python tool that generates professional resumes and automatically tailors them to specific job descriptions using a job URL and OpenAI's GPT.

A comprehensive framework for creating and analyzing large-scale hyper-relational knowledge graphs using a scalable, disk-based TSV format.

An enterprise deployment framework for Claude Code and Claude Cowork on Amazon Bedrock, providing secure SSO, per-user usage monitoring, and token quota enforcement.

An MCP server and CLI tool that automatically generates baseline AWS IAM policies by analyzing application source code or Terraform plans to reduce permission-related debugging.

A CLI tool that helps AI agents translate localization files efficiently by syncing only missing strings and preserving manual corrections.

An automated pipeline for creating short-form videos that handles AI script generation, stock footage sourcing, TTS voiceovers, and social media scheduling.

A .NET port of Gradio that allows developers to build web interfaces for machine learning models and APIs using only C# code, eliminating the need for JavaScript or CSS.

A Nav2-integrated complete coverage path planning system that uses Fields2Cover to generate efficient paths for robots to cover entire fields or rows.

A lightweight JavaScript library that brings computer vision algorithms like color tracking and face detection directly into the browser.

A library and set of tools that use data analytics (like Google Analytics) to predict which pages a user will visit next and prefetch them to improve web performance.

A fast, on-device NoSQL and vector database for Java and Kotlin that enables efficient object storage and local vector search for AI applications.

An AI-native data notebook platform that replaces Jupyter's JSON format with a human-readable YAML structure for better collaboration and version control.

An AI-powered low-code framework that uses a metadata-driven architecture to enable developers and AI to build maintainable, enterprise-grade intelligent applications.

A Python wrapper for the Tesseract OCR API that enables efficient text extraction from images with support for concurrent execution and Pillow integration.

Gollama is a Go‑based terminal UI for listing, inspecting, editing, running, copying, deleting and pushing Ollama LLM models, with hot‑key navigation, vRAM estimation, configurable JSON settings, and theme support.

A modular Python library for t-SNE dimensionality reduction that scales to millions of data points for high-dimensional data visualization.

A collection of Python sample codes and simulations covering localization, mapping, path planning, and path tracking for autonomous vehicle control.