Open Source Windows Research Software
Sort By:
Research Software for Windows
View 42 business solutionsBrowse free open source Research software and projects for Windows below. Use the toggles on the left to filter open source Research software by OS, license, language, programming language, and project status.
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
AI-powered service management for IT and enterprise teamsGive your IT, operations, and business teams the ability to deliver exceptional services—without the complexity. Maximize operational efficiency with refreshingly simple, AI-powered Freshservice.
-
1
Stellarium
GPL software which renders realistic skies in real time
Stellarium is a free GPL software which renders realistic skies in real time with OpenGL. It is available for Linux/Unix, Windows and macOS. With Stellarium, you really see what you can see with your eyes, binoculars or a small telescope. Stellarium is a free open source planetarium for your computer. It shows a realistic sky in 3D, just like what you see with the naked eye, binoculars or a telescope. Plugin system adding artifical satellites, ocular simulation, telescope control and more. Ability to add new solar system objects from online resources. Add your own deep sky objects, landscapes, constellation images, scripts, etc. Supernovae and novae simulation. Exoplanet locations. 3D sceneries. Skinnable landscapes with spheric panorama projection. -
2
Virastyar
Virastyar is an spell checker for low-resource languages
Virastyar is a free and open-source (FOSS) spell checker. It stands upon the shoulders of many free/libre/open-source (FLOSS) libraries developed for processing low-resource languages, especially Persian and RTL languages Publications: Kashefi, O., Nasri, M., & Kanani, K. (2010). Towards Automatic Persian Spell Checking. SCICT. Kashefi, O., Sharifi, M., & Minaie, B. (2013). A novel string distance metric for ranking Persian respelling suggestions. Natural Language Engineering, 19(2), 259-284. Rasooli, M. S., Kahefi, O., & Minaei-Bidgoli, B. (2011). Effect of adaptive spell checking in Persian. In NLP-KE Contributors: Omid Kashefi Azadeh Zamanifar Masoumeh Mashaiekhi Meisam Pourafzal Reza Refaei Mohammad Hedayati Kamiar Kanani Mehrdad Senobari Sina Iravanin Mohammad Sadegh Rasooli Mohsen Hoseinalizadeh Mitra Nasri Alireza Dehlaghi Fatemeh Ahmadi Neda PourMorteza -
3
Device Activity Tracker
A phone number can reveal whether a device is active
Device Activity Tracker is a platform created to monitor and log the activity of digital devices across networks, giving users visibility into usage patterns, connection events, app launches, and interaction timelines that can be applied for security monitoring, parental oversight, productivity tracking, or device lifecycle analytics. It integrates with devices via sensors or APIs, continually capturing activity metrics and reporting them to a centralized dashboard that visualizes patterns over time, highlights anomalies, and correlates events across systems or users. Because it is designed with privacy and transparency in mind, the tracker offers configurable retention policies and granular consent controls, ensuring administrators can tailor what gets logged and how long data is stored. -
4
DSpace
Open Source "turn-key" institutional repository application
Open Source Digital Asset Management system that enables services for access, provision, stewardship and re-use of digital assets with a focus on educational and research materials For Support, please see: https://wiki.lyrasis.org/display/DSPACE/Support RELEASES: The most recent releases are now distributed via GitHub: https://github.com/DSpace/DSpace/releases MAILING LISTS: Mailing lists have all been moved to Google Groups: https://wiki.lyrasis.org/display/DSPACE/Mailing+Lists -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
5
Hacker Laws
Laws, theories, principles and patterns useful to developers
Laws, Theories, Principles and Patterns that developers will find useful. There are lots of laws which people discuss when talking about development. This repository is a reference and overview of some of the most common ones. Principles and laws to follow such as: If a program is made up of two parts, part A, which must be executed by a single processor, and part B, which can be parallelised, then we see that adding multiple processors to the system executing the program can only have a limited benefit. It can potentially greatly improve the speed of part B - but the speed of part A will remain unchanged. Also, theories like The Broken Windows Theory, which suggests that visible signs of crime (or lack of care of an environment) lead to further and more serious crimes (or further deterioration of the environment). Conway's Law suggests that the technical boundaries of a system will reflect the structure of the organisation. These among others, are featured in this project. -
6
Zotero
Tool to help you collect, organize, annotate, cite, and share research
Zotero is a powerful, free, open-source research management application designed to help students, academics, and professionals collect, organize, annotate, cite, and share research sources and materials for papers, projects, or books. It can save web pages, PDFs, books, articles, and more with metadata, automatically extract bibliographic information, and organize items into collections and tag systems, while supporting notes and annotations directly alongside references. Zotero’s interface integrates with word processors like Microsoft Word and LibreOffice to generate formatted citations and bibliographies in many styles, and it can sync libraries across devices or share them with collaborators. The software has a plugin architecture and a connector for web browsers to enable one-click capturing of sources from library catalogs, academic databases, and other sites. -
7
Linux command
Linux command encyclopedia search tool
Linux command encyclopedia search tool, the content includes Linux command manual, detailed explanation, study, and collection. The current warehouse has collected more than 570 Linux commands. It is a non-profit warehouse. It has generated a web site for easy use. Currently, the site does not have any advertisements. The content includes Linux command manuals, detailed explanations, and learning. Very worthy collection of Linux command quick reference manual. The copyright belongs to the original author, and does not assume any responsibility for any legal issues and risks. There is no commercial purpose. If you think that your copyright is infringed, please write to us. I cannot guarantee the correctness of the content. The risks caused by using the content of this site have nothing to do with me. When using this site, it means that you have accepted the terms of use and privacy terms of this site. -
8
eLabFTW
Open source electronic lab notebook for research labs
eLabFTW is a modern, open-source electronic laboratory notebook (ELN) that helps research teams store, organize, and manage experimental records and laboratory data from a central web interface. Designed for scientific environments, the software provides a secure, browser-accessible platform where users can log protocols, results, and observations in structured records that replace traditional paper notebooks. Beyond simple experiment journaling, eLabFTW includes an inventory database for tracking lab materials, reagents, and equipment, making it a versatile tool for laboratory management. It also supports collaboration across teams, enabling multiple users to access shared records and streamline project workflows. The software features advanced search, tagging, timestamping, and export tools, which are essential for reproducibility and long-term project tracking. -
9
AutoResearchClaw
Autonomous research from idea to paper. Chat an Idea. Get a Paper 🦞
AutoResearchClaw is an open-source framework designed to automatically generate full academic research papers from a single idea or topic. Built in Python, it orchestrates a multi-stage research pipeline that gathers literature, formulates hypotheses, runs experiments, analyzes results, and writes the final paper. The system retrieves real academic references from sources such as arXiv and Semantic Scholar to ensure credible citations. It can automatically generate code for experiments, run them in a sandbox environment, and analyze the results with statistical methods. The platform also uses multi-agent debate and automated peer review processes to refine research findings and improve paper quality. By combining literature discovery, experimentation, and writing automation, AutoResearchClaw aims to turn research ideas into conference-ready papers with minimal human intervention. -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
10
WIKINDX
Virtual Research Environment / On-line Bibliography Manager
Reference management, bibliography management, citations and a whole lot more. Designed by academics for academics, under continuous development since 2003, and used by both individuals and major research institutions worldwide, WIKINDX is a Virtual Research Environment (an enhanced on-line bibliography manager) storing searchable references, notes, files, citations, ideas, and more. An integrated WYSIWYG word processor exports formatted articles to RTF, DOCX, and HTML. Plugins include a citation style editor and import/export of bibliographies (BibTeX, Endnote, RIS etc.). WIKINDX supports multiple attachments with each reference, multiple language localizations, and uses a template system to allow users to visually integrate WIKINDX into their sites. WIKINDX runs on a web server giving you and your research group ownership and global access from any web-enabled device. You manage your database, you own your data. WIKINDX can be test-driven at: https://testdrive.wikindx.com -
11
Hypernomicon
Hypertext-infused philosophy personal database software
Hypernomicon is a personal productivity/database application for researchers that combines structured note-taking, mind-mapping, management of files (e.g., PDFs) and folders, and reference management into an integrated environment that organizes all of the above into semantic networks or hierarchies in terms of debates, positions, arguments, labels, terminology/concepts, and user-defined keywords by means of database relations and automatically generated hyperlinks (hence ‘Hyper’ in the name). Hypernomicon keeps track of all these things in a highly structured, thoroughly indexed and user friendly relational database, automatically generates semantic hyperlinks between all of them, and presents this information in many different forms so that you are constantly informed of ways all of your information is related that you had not realized. -
12
-
13
Catalyst
Accelerated deep learning R&D
Catalyst is a PyTorch framework for accelerated Deep Learning research and development. It allows you to write compact but full-featured Deep Learning pipelines with just a few lines of code. With Catalyst you get a full set of features including a training loop with metrics, model checkpointing and more, all without the boilerplate. Catalyst is focused on reproducibility, rapid experimentation, and codebase reuse so you can break the cycle of writing another regular train loop and make something totally new. Catalyst is compatible with Python 3.6+. PyTorch 1.1+, and has been tested on Ubuntu 16.04/18.04/20.04, macOS 10.15, Windows 10 and Windows Subsystem for Linux. It's part of the PyTorch Ecosystem, as well as the Catalyst Ecosystem which includes Alchemy (experiments logging & visualization) and Reaction (convenient deep learning models serving). -
14
Local Deep Research
95% on SimpleQA (e.g. Qwen3.6-27B on a 3090)
Local Deep Research is an open-source AI-powered research assistant designed to perform deep, iterative investigations by combining large language models with multi-source search capabilities. It runs locally, giving users full control over their data, privacy, and infrastructure while supporting both local and cloud-based LLMs. The system breaks down complex queries into smaller steps, performs parallel searches across web and academic sources, and generates structured, citation-backed reports. It also supports personal document ingestion through vector search, enabling users to build a private, searchable knowledge base. The platform includes a web interface, Docker-based deployment, and flexible configuration options, making it accessible to both developers and researchers. Its architecture emphasizes transparency, customization, and reproducibility in AI-assisted research workflows. -
15
PageLM
PageLM is a community driven version of NotebookLM
PageLM is an open-source AI-powered education platform that transforms study materials into interactive learning experiences inspired in part by the NotebookLM style of knowledge interaction. It is built to help students, educators, and researchers turn documents and topics into more engaging forms of study rather than leaving content in static notes or isolated files. The platform includes a broad set of learning tools such as contextual chat, Cornell-style note generation, flashcards, quizzes, AI podcasts, voice transcription, homework planning, exam simulation, debate practice, and a personalized study companion. It supports uploaded documents including PDF, DOCX, Markdown, and TXT, allowing users to ground questions and generated materials in source content. On the technical side, it supports multiple model providers, multiple embedding back ends, WebSocket streaming for real-time generation, persistent content storage, and structured markdown outputs. -
16
ThingPulse ESP8266 Weather Station
ESP8266 Weather Station library supporting OpenWeatherMap
This code works best with the NodeMCU V2 ESP8266 module and an 0.96" OLED display. To get you up and running in no time we created a kit that contains all the necessary parts. By buying this and other kits from us you are funding the maintenance and development of this library. Make sure you use a version of the Arduino IDE which is supported by the ESP8266 platform. If you are using the PlatformIO environment for building, choose one of the available IDE integration or the Atom-based IDE, install libraries 561, 562, and 563 with "platformio lib install", adapt the WeatherStationDemo.ino file to your needs. The simple class uses the header date and time to set the clock. NTP-based time class written by Fabrice Weinberg. We fixed many bugs and improved performance and changed the API a little bit. Either compare your code to the updated WeatherStationDemo or read through the upgrade guide. -
17
VulnX
Intelligent Bot, Shell can achieve automatic injection
vulnx, an intelligent Bot, Shell can achieve automatic injection, and help researchers detect security vulnerabilities in CMS systems. It can perform a quick CMS security detection, information collection (including sub-domain name, IP address, country information, organizational information and time zone, etc.), and vulnerability scanning. Vulnx is An Intelligent Bot Auto Shell Injector that detects vulnerabilities in multiple types of Cms, fast cms detection, information gathering, and vulnerability scanning of the target like subdomains, IP addresses, country, org, timezone, region, and more. Instead of injecting each and every shell manually as all the other tools do, VulnX analyses the target website checking the presence of a vulnerability if so the shell will be Injected by searching URLs with the dorks Tool. Detects CMS (wordpress, joomla, prestashop, drupal, opencart, magento, lokomedia). -
18
Biblatex is a LaTeX package which provides full-featured bibliographic facilities
-
19
Brain Tokyo Workshop
Experiments and code from Google Brain’s Tokyo research workshop
The Brain Tokyo Workshop repository hosts a collection of research materials and experimental code developed by the Google Brain team based in Tokyo. It showcases a variety of cutting-edge projects in artificial intelligence, particularly in the areas of neuroevolution, reinforcement learning, and model interpretability. Each project explores innovative approaches to learning, prediction, and creativity in neural networks, often through unconventional or biologically inspired methods. The repository includes implementations, experimental data, and supporting research papers that accompany published studies. Notable works such as Weight Agnostic Neural Networks and Neuroevolution of Self-Interpretable Agents highlight the team’s exploration of how AI can learn more efficiently and transparently. Overall, this repository serves as an open research hub for sharing ideas and advancing the understanding of intelligent systems. -
20
Lucid
A collection of infrastructure and tools for research
Lucid is a collection of infrastructure and tools for research in neural network interpretability. Lucid is research code, not production code. We provide no guarantee it will work for your use case. Lucid is maintained by volunteers who are unable to provide significant technical support. Start visualizing neural networks with no setup. The following notebooks run right from your browser, thanks to Collaboratory. It's a Jupyter notebook environment that requires no setup to use and runs entirely in the cloud. You can run the notebooks on your local machine, too. Clone the repository and find them in the notebooks subfolder. You will need to run a local instance of the Jupyter notebook environment to execute them. Feature visualization answers questions about what a network, or parts of a network, are looking for by generating examples. -
21
nanoGPT
The simplest, fastest repository for training/finetuning models
NanoGPT is a minimalistic yet powerful reimplementation of GPT-style transformers created by Andrej Karpathy for educational and research use. It distills the GPT architecture into a few hundred lines of Python code, making it far easier to understand than large, production-scale implementations. The repo is organized with a training pipeline (dataset preprocessing, model definition, optimizer, training loop) and inference script so you can train a small GPT on text datasets like Shakespeare or custom corpora. It emphasizes readability and clarity: the training loop is cleanly written, and the code avoids heavy abstractions, letting students follow the architecture step by step. While simple, it can still train non-trivial models on modern GPUs and generate coherent text. The project has become widely used in tutorials, courses, and experiments for people learning how transformers work under the hood. -
22
KingJamesPureBibleSearch
GUI Application to Search and Count the Pure King James Bible
Study and analyze the Fingerprint of God in the mathematical structure, known as the King James Code, of the King James text of the Holy Bible. Allows instant real-time searches, with an autocompleter droplist to assist with words which come next. Jump to specific words, verses, or chapters by number, and see all possible count statistics of phrases within the text. Graphically visualize search results, cross-reference sources and word lexicons, and search foreign translations derived from the same Divine Masoretic/Textus Receptus Vine of Scripture. For more info and downloads, see http://www.purebiblesearch.com/ For details on the King James Code, see http://visitbethelchurch.com/ -
23
moebinv
C++ libraries for manipulations in non-Euclidean geometry
These are two C++ libraries for symbolic, numeric and graphical manipulations in non-Euclidean geometry. There is GUI which allows to interact with these libraries by mouse clicks. On a dipper level the first library Cycle implements basic operations on cycles (quadrics) through FSCc construction. The second library Figure operates on ensembles of cycles connected by Moebius-invariant relations, e.g. orthogonality. Both libraries are based on the Clifford algebra capacities of the GiNaC computer algebra system (http://ginac.de). Besides C++ libraries there is a Python wrapper, which can be used in interactive mode (https://codeocean.com/capsule/7952650/). Both libraries work in arbitrary dimensions and signatures of metric. Additionally, there are some 2D/3D-specific routines including a visualisation to PostScript files through Asymptote (http://asymptote.sourcefourge.net) software. The source is written in literate programming NoWeb. -
24
Dopamine
Framework for prototyping of reinforcement learning algorithms
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms. It aims to fill the need for a small, easily grokked codebase in which users can freely experiment with wild ideas (speculative research). This first version focuses on supporting the state-of-the-art, single-GPU Rainbow agent (Hessel et al., 2018) applied to Atari 2600 game-playing (Bellemare et al., 2013). Specifically, our Rainbow agent implements the three components identified as most important by Hessel et al., n-step Bellman updates, prioritized experience replay, and distributional reinforcement learning. For completeness, we also provide an implementation of DQN (Mnih et al., 2015). For additional details, please see our documentation. We provide a set of Colaboratory notebooks which demonstrate how to use Dopamine. We provide a website which displays the learning curves for all the provided agents, on all the games. -
25
Megatron-LM
Ongoing research training transformer models at scale
Megatron-LM is a GPU-optimized deep learning framework from NVIDIA designed to train extremely large transformer-based language models efficiently at scale. The repository provides both a reference training implementation and Megatron Core, a composable library of high-performance building blocks for custom large-model pipelines. It supports advanced parallelism strategies including tensor, pipeline, data, expert, and context parallelism, enabling training across massive multi-GPU and multi-node clusters. The framework includes mixed-precision training options such as FP16, BF16, FP8, and FP4 to maximize performance and memory efficiency on modern hardware. Megatron-LM is widely used in research and industry for pretraining GPT-, BERT-, T5-, and multimodal-style models, with tooling for checkpoint conversion and interoperability with Hugging Face. Overall, it is a production-grade system for organizations pushing the limits of large-scale language model training.
