Open Source Windows Research Software
Sort By:
Research Software for Windows
View 43 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.
-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
1
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 -
2
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. -
3
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. -
4
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. -
Veeam Data Platform v13.1Try Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
5
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. -
6
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 -
7
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. -
8
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 -
9
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. -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
10
OpenScience
The open-source AI workbench for scientific research
OpenScience is an open-source AI workbench for scientific research. It lets users give an agent a research goal, then have it read literature, form hypotheses, write and run code, run experiments, analyze results, and write up findings. The workspace runs in the browser and includes a file tree, editor, terminal, session history, and scientific rendering for molecules, structures, genomes, and plots. It supports frontier, open-weight, and local models through bring-your-own-key provider configuration. The project includes research agents, domain specialists, critique agents, literature-review agents, and more than 290 scientific skills. OpenScience is especially useful for machine learning, biology, physics, chemistry, and research automation workflows that need tool use and provenance. -
11
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. -
12
Biblatex is a LaTeX package which provides full-featured bibliographic facilities
-
13
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. -
14
Open Science
Open Science is an open-source, local-first, model-agnostic research
Open Science is an open-source, local-first AI research workbench built for scientific discovery on macOS, Windows, and Linux. Researchers can describe a task in plain language and let an agent inspect files, execute Python or R, search the web, and call scientific data connectors. The system is model-agnostic, allowing users to connect supported providers, compatible gateways, or subscription-based backends. It produces reproducible reports, tables, figures, and other artifacts inside a unified project workspace. Users can inspect tool activity, approve sensitive actions, branch earlier conversations, and compare alternative research paths without losing prior work. Immutable artifact versions and detailed provenance connect results to code, inputs, execution history, environment evidence, conversation context, and review findings. -
15
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. -
16
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. -
17
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. -
18
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/ -
19
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). -
20
JSONLab
JSONLab: compact, portable, robust JSON/binary-JSON encoder
JSONLab is a free and open-source JSON/UBJSON/MessagePack encoder and decoder written in the native MATLAB language. It can be used to convert a MATLAB data structure (array, struct, cell, struct array, cell array, and objects) into JSON/UBJSON/MessagePack formatted strings and files, or to parse a JSON/UBJSON/MessagePack file into MATLAB data structure. JSONLab supports nearly all versions of MATLAB and GNU Octave (a free MATLAB clone). The development of JSONLab is currently funded by the US National Institute of Health (NIH) as part of the NeuroJSON project (data portal https://neurojson.io) under grant U24-NS124027. The goal of the NeuroJSON project is to develop scalable, searchable, and reusable neuroimaging data formats and data-sharing platforms. All data produced from the NeuroJSON project will be using JSON/Binary JData formats as the underlying serialization standards and the lightweight JData specification as a language-independent data annotation standard. -
21
PRIMA
PRIMA is a package for solving general nonlinear optimization problems
PRIMA is a package for solving general nonlinear optimization problems without using derivatives. It provides the reference implementation for Powell's derivative-free optimization methods, i.e., COBYLA, UOBYQA, NEWUOA, BOBYQA, and LINCOA. PRIMA means Reference Implementation for Powell's methods with Modernization and Amelioration, P for Powell. PRIMA is a package for solving general nonlinear optimization problems without using derivatives. It provides the reference implementation for Powell's renowned derivative-free optimization methods, i.e., COBYLA, UOBYQA, NEWUOA, BOBYQA, and LINCOA. The "P" in the name stands for Powell, and "RIMA" is an acronym for "Reference Implementation with Modernization and Amelioration". -
22
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. -
23
Ceka
Crowd Environment and its Knowledge Analysis
A knowledge analysis tool for crowdsourcing based on Weka. We also have a Python version of Crowdsourcing Learning: CrowdwiseKit on GitHub (https://github.com/tssai-lab/CrowdwiseKit). -
24
Choco is not hosted on sourceforge anymore. Please now visit http://choco-solver.org/ !
-
25
Docear
An Academic Literature Suite
Docear (pronounced dog-ear) is what we call an “academic literature suite”. It integrates everything you need to search, organize and create academic literature in a single application: a digital library, reference manager, PDF and file manager, note taking and mind mapping. And the best: Docear works seemlessly with many existing tools like Mendeley, Microsoft Word, and Foxit Reader. Docear is free and open source, based on Freeplane, funded by the German Federal Ministry of Technology and developed by scientists from around the world, among others from OvGU, and the University of California, Berkeley.
