Open-source alternatives to Sumo

This research framework provides a deep learning driving simulator and a multimodal data pipeline for autonomous vehicle research. It centers on the creation of synchronized autonomous vehicle datasets, which combine high-frequency vehicle telemetry with camera frames to train neural networks. The project implements a convolutional neural network trainer specifically designed to predict steering angles and vehicle transition states from visual data. It features generative capabilities, using autoencoders and transition models to synthesize driving environments and simulate future vehicle move

This project is an autonomous vehicle simulator designed to validate self-driving logic and train deep learning algorithms within a virtual environment. It functions as a training platform for developing neural networks that control vehicle movement and steering based on visual sensor data. The simulator uses the Unity game engine to provide a physics-based world where autonomous driving algorithms can be tested on virtual road courses without the use of physical hardware. The system integrates a C# scripting backend with a physics engine for collision detection and vehicle dynamics. It util

OpenTTD is an open-source game engine and transport simulation game. It provides an isometric sandbox environment for building and managing complex logistics and transport networks. The project functions as a multiplayer simulation sandbox where users can build infrastructure cooperatively or competitively in a shared virtual world. The platform is designed as a moddable simulation system that supports external assets, graphics, and gameplay modifications. It includes mechanisms for downloading and integrating add-on content and utilizes a plugin-based system to extend game mechanics beyond t

This project is a geospatial data rendering engine and OpenStreetMap road network visualizer. It functions as a vector map visualization tool that imports geocoded area data and converts road layouts into visual layers for digital or physical output. The system enables the creation of generative map art and stylized images intended for physical production via pen-plotters or laser cutters. It allows for the manipulation of line widths and colors of city streets to produce custom visual representations of urban environments. The engine provides capabilities for urban road visualization, geogr

cmux is a GPU-accelerated terminal emulator and workspace manager designed for coordinating multiple concurrent AI coding agents. It functions as an orchestration terminal that uses scriptable workspaces and split panes to manage parallel AI agent workflows, while also serving as a headless browser automation tool and a remote development relay. The project differentiates itself through a programmatic control plane using a Unix domain socket and CLI, allowing for the automated management of terminal layouts and input delivery. It features an integrated web engine for programmatic DOM manipula

This is a collection of machine learning projects, data visualization portfolios, and predictive analytics tools. The repository provides implementation examples for training predictive models, executing data analysis pipelines, and estimating metadata values through historical statistical tables. The project emphasizes evolutionary computing, utilizing genetic algorithms and programming to solve optimization problems. This includes calculating the shortest distance between geographic coordinates and automating the selection of models and hyperparameters within machine learning pipelines. Ad

DifferentialEquations.jl is a comprehensive numerical library designed for solving ordinary, stochastic, delay, and algebraic differential equations. It functions as a high-performance solver suite that integrates scientific machine learning, probabilistic programming, and automated differentiation into a unified framework. By leveraging multiple dispatch and symbolic-numeric integration, the library provides a flexible environment for complex mathematical modeling and simulation. The project distinguishes itself through its ability to bridge traditional numerical analysis with modern machine

This project is a neural network route optimizer and unsupervised learning tool designed to solve the traveling salesman problem. It functions as a self-organizing map solver that calculates near-optimal paths through a set of coordinates to determine the shortest possible tour. The system utilizes a Kohonen map implementation to organize high-dimensional data into a lower-dimensional representation. It employs competitive learning and topology preservation to approximate solutions for combinatorial optimization problems. The solver covers route optimization analysis and heuristic pathfindin

This project is a cross-platform mapping SDK and hardware-accelerated rendering engine implemented in C++. It provides a shared geospatial core that allows for the embedding of interactive maps into Android, iOS, macOS, Node.js, and Qt applications. The system focuses on high-performance vector tile rendering using OpenGL and GPU primitives to display interactive 3D landscapes and complex geospatial datasets. It transforms compressed protocol buffers into customizable visuals through a style-driven layer pipeline. The capability surface extends to comprehensive location services, including g

GraphHopper is a Java routing library and OpenStreetMap routing engine used to calculate optimal paths and driving directions. It provides a map matching engine for aligning GPS coordinate traces to road networks, a GTFS transit router for multi-modal travel, and a spatial analysis utility for isochrone generation. The project supports the creation of custom vehicle profiles and weighting logic to influence path calculations. It implements contraction hierarchies to accelerate pathfinding by reducing the search space between coordinates. The engine covers a broad range of geospatial capabili

Makie.jl is a high-performance Julia data visualization library and hardware-accelerated plotting engine used to create interactive 2D and 3D visualizations. It functions as a reactive visualization framework where plots update automatically via observables and compute graphs, and as a vector graphics generator for high-resolution academic output. The system is distinguished by its backend-agnostic rendering pipeline, which supports OpenGL, WebGL, and ray-traced scenes. It employs a grammar-of-graphics approach to map variables to aesthetic attributes and utilizes a hierarchical scene graph t

Tippecanoe is a command-line tool used to generate optimized vector tiles for web maps. It converts large-scale geospatial datasets, including GeoJSON, CSV, and Geobuf files, into binary vector tiles or MBTiles SQLite databases. The project is designed to maintain map performance and visual quality across different zoom levels. It achieves this through geospatial data downsampling, which includes simplifying geometries and thinning point density to prevent tile overcrowding and keep tile sizes within specific limits. The tool provides extensive data transformation capabilities, such as attri

Plotnine is a data visualization library for Python based on the Grammar of Graphics. It serves as a declarative statistical plotting framework and multi-panel plotting engine, allowing users to create complex charts by mapping data variables to visual properties such as position, color, and size. The project is distinguished by its use of a layered composition model and a statistical transformation engine that performs aggregations and computations before rendering visuals. It features a comprehensive system for multi-panel faceting, which enables the splitting of a single visualization into

This project is a scientific visualization guide and data visualization framework designed for creating high-quality 2D and 3D figures for academic journals and scientific publishing. It provides a structured approach to designing precise layouts, coordinate systems, and typography for complex scientific data. The project features a specialized print-ready PDF workflow and a CMYK print production workflow. These systems translate digital RGB colors into printer-specific CMYK profiles to ensure visual accuracy for physical hardcover and softcover printing. It also serves as a guide for SVG dat

Cobe is a WebGL globe library designed for interactive 3D geographic data visualization. It functions as a canvas-based map component that renders a world map, allowing for the plotting of latitude and longitude coordinates via markers and connecting arcs. The library distinguishes itself by linking standard HTML elements to 3D coordinates using CSS anchor positioning. This integration enables the attachment of DOM elements, such as labels and tooltips, directly to markers and arcs on the sphere. The system covers geographic data plotting and network connection mapping, utilizing automated r

deck.gl is a GPU-accelerated geospatial engine and WebGL2 data visualization framework. It functions as a high-performance spatial visualizer and map overlay library designed to render large-scale spatial and temporal datasets. The system specializes in mapping data arrays into visual layers for complex geographic representations. It provides the capability to create interactive visual overlays and cartographic projections that align with various third-party map providers. The framework supports large-scale data visualization, interactive spatial analysis, and the development of custom high-

EasyEffects is a real-time audio processor and system-wide effects manager designed for PipeWire audio streams. It functions as a comprehensive suite for applying filters, equalizers, and limiters to both input and output audio across the entire system. The project distinguishes itself through its use of deep learning for neural network noise suppression and voice isolation, as well as its ability to simulate physical acoustic environments using impulse-response convolution. It includes a sophisticated preset management system that allows users to associate specific audio configurations with

This is a grammar of graphics visualization library used to build charts by mapping tabular data to visual marks. It functions as an SVG data visualization tool and an exploratory data analysis API, allowing users to render complex visualizations and geographic maps. The library features a GeoJSON map renderer that projects spherical coordinates into two-dimensional pixel space and an Apache Arrow visualization interface for high-efficiency data processing. Its capability surface covers data transformation through binning and grouping, visual encoding via automatic scale inference and color

vx is a declarative charting framework and SVG data visualization library. It serves as an integration layer that combines D3 mathematical scales and shapes with a component-based UI for rendering visualizations. The project provides a set of building blocks for constructing custom charts and diagrams using React components. It bridges mathematical data and visual representation by utilizing low-level primitives to manage scalable vector graphics without manual document object model manipulations. The library covers a broad capability surface including custom chart development, declarative S

OSMnx is a Python library for downloading, modeling, and analyzing street networks and other geospatial features from OpenStreetMap. It enables users to retrieve and work with real-world infrastructure data anywhere in the world, providing tools for network analysis, spatial queries, and visualization. The library offers capabilities for working with urban features such as building footprints, transit stops, and elevation data, along with network statistics like intersection density and circuity. It supports multiple travel modes including driving, walking, and biking, and can calculate short

ggplot2 is a data visualization library for R based on a formal grammar of graphics. It provides a declarative plotting framework that allows users to create complex graphics by combining geometric objects, statistical summaries, and coordinate systems. The system is distinguished by a layered approach to composition, where visualizations are built incrementally by stacking independent geometric, statistical, and coordinate layers. It utilizes a hierarchical styling engine to manage non-data elements such as backgrounds, fonts, and margins, and includes a multi-panel faceting tool for splitti

Shapely is a geometric analysis library for the manipulation and analysis of planar geometric objects. It functions as a computational geometry toolkit, a spatial predicate engine for evaluating topological relationships, and a vectorized geometry processor. The library distinguishes itself through a vectorized geometry processor capable of executing operations across coordinate arrays with multi-threaded parallel processing. It utilizes prepared geometry optimization to accelerate repeated containment and intersection tests and implements R-tree spatial indexing for efficient nearest-neighbo

Kepler.gl is a web-based geospatial visualization framework designed for rendering large-scale location datasets. It functions as a modular React mapping component that enables developers to embed interactive, high-performance geographic visualizations into web applications, serving as a comprehensive engine for building browser-based GIS dashboards. The library distinguishes itself through a highly extensible architecture that centers on centralized state management. By utilizing a predictable state-driven model, it allows for the programmatic control of map layers, filters, and viewport set

jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti