Open Source Artificial Intelligence Software
Sort By:
Artificial Intelligence Software
Browse free open source Artificial Intelligence software and projects for Windows and ChromeOS below. Use the toggles on the left to filter open source Artificial Intelligence software by OS, license, language, programming language, and project status.
-
Try Google Cloud Risk-Free With $300 in CreditUse your credit across every product. Compute, storage, AI, analytics. When it runs out, 20+ products stay free. You only pay when you choose to.
-
Gemini 3 and 200+ AI Models on One PlatformBuild generative AI apps with Vertex AI. Switch between models without switching platforms.
-
1
AutoGen
An Open-Source Programming Framework for Agentic AI
AutoGen is an open-source programming framework for building AI agents and facilitating cooperation among multiple agents to solve tasks. AutoGen aims to provide an easy-to-use and flexible framework for accelerating development and research on agentic AI, like PyTorch for Deep Learning. It offers features such as agents that can converse with other agents, LLM and tool use support, autonomous and human-in-the-loop workflows, and multi-agent conversation patterns. AutoGen provides multi-agent conversation framework as a high-level abstraction. With this framework, one can conveniently build LLM workflows. AutoGen offers a collection of working systems spanning a wide range of applications from various domains and complexities. AutoGen supports enhanced LLM inference APIs, which can be used to improve inference performance and reduce cost. -
2
NLP
Open source NLP guide with models, methods, and real use cases
NLP is an open source introductory resource for natural language processing, presented as a continuously updated book hosted on GitHub. It explains how machines process and understand human language, combining theory with practical examples. Its covers core NLP concepts such as text representation, feature extraction, and model evaluation, alongside hands-on implementations using tools like Word2Vec, TF-IDF, and FastText. It also introduces topic modeling with LDA, keyword extraction techniques, and document similarity methods. NLP extends into real-world applications, including sentiment analysis and text classification, helping readers connect concepts to use cases. Designed for accessibility, the project evolves over time, allowing updates and improvements as NLP techniques advance. It reflects a practical approach to learning, where readers can explore code, experiment with models, and build foundational skills in machine learning-driven language processing. -
3
prompts.chat
Share, discover, and collect prompts
prompts.chat, also known as Awesome ChatGPT Prompts, is an open-source community project that curates high-quality prompt examples for modern AI chat models. The repository functions as a centralized library where users can browse, share, and collect prompt templates designed to improve the usefulness and creativity of AI interactions. Originally built around ChatGPT use cases, the prompts are broadly compatible with many contemporary large language models, making the resource flexible across platforms. The project emphasizes discoverability and collaboration by allowing community submissions that automatically synchronize with the repository. It can also be self-hosted, enabling organizations to maintain a private prompt knowledge base if needed. -
4
Exposure Correction
Learning multi-scale deep model correcting over- and under- exposed
Exposure_Correction is a research project that provides the implementation for the paper Learning Multi-Scale Photo Exposure Correction (CVPR 2021). The repository focuses on correcting poorly exposed photographs, handling both underexposure and overexposure using a deep learning approach. The method employs a multi-scale framework that learns to enhance images by adjusting exposure levels across different spatial resolutions. This allows the model to preserve fine details while correcting global lighting inconsistencies. The repository includes pre-trained models, datasets, and training/testing code to enable reproducibility and experimentation. By leveraging this framework, researchers and developers can apply exposure correction to a wide range of natural images, improving visual quality without manual editing. The project serves both as a research reference and a practical tool for computational photography and image enhancement. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
5
Microsoft Learn MCP Server
Official Microsoft Learn MCP Server, powering LLMs and AI agents
Microsoft Learn MCP Server is the official GitHub repository for the Microsoft Learn MCP (Model Context Protocol) Server, a service that implements the Model Context Protocol to provide AI assistants and tools with reliable, real-time access to Microsoft’s official documentation. Rather than relying on training data that may be outdated or incomplete, MCP servers let agents like GitHub Copilot, Claude, or other LLM-based tools search and pull context directly from up-to-date Microsoft Learn content, including Azure, .NET, and other tech docs. By connecting to the MCP endpoint, coding agents can answer questions, retrieve code examples, and offer best practices grounded in authoritative sources without requiring API keys or manual browser searches. This capability helps eliminate hallucinations, improve accuracy, and streamline developer workflows by keeping relevant tech guidance close at hand. -
6
LLM Applications
A comprehensive guide to building RAG-based LLM applications
LLM Applications is a practical reference repository that demonstrates how to build production-grade applications powered by large language models. The project focuses particularly on Retrieval-Augmented Generation architectures, which combine language models with external knowledge sources to improve accuracy and reliability. It provides step-by-step guidance for constructing systems that ingest documents, split them into chunks, generate embeddings, index them in vector databases, and retrieve relevant context during inference. The repository also shows how these components can be scaled and deployed using distributed computing frameworks such as Ray. In addition to development workflows, the project includes notebooks, datasets, and evaluation tools that help developers experiment with different retrieval strategies and model configurations. -
7
This is a database of the Arabic roots and their derivatives in voweled and unvoweled forms along with stems. The database is extracted from the well known Arabic legacy dictionary "تاج العروس من جواهر القاموس".
-
8
CoTracker
CoTracker is a model for tracking any point (pixel) on a video
CoTracker is a learning-based point tracking system that jointly follows many user-specified points across a video, rather than tracking each point independently. By reasoning about all tracks together, it can maintain temporal consistency, handle mutual occlusions, and reduce identity swaps when trajectories cross. The model takes sparse point queries on one frame and predicts their sub-pixel locations and a visibility score for every subsequent frame, producing long, coherent trajectories. Its transformer-style architecture aggregates information both along time and across points, allowing it to recover tracks even after brief disappearances. The repository ships with inference scripts, pretrained weights, and simple interfaces to seed points, run tracking, and export trajectories for downstream tasks. Typical uses include correspondence building, motion analysis, dynamic SLAM priors, video editing masks, and evaluation of geometric consistency in real scenes. -
9
Cpt Kirk
Obtain why and why-not justifications for answer set programs.
Since the method proposed in https://www.researchgate.net/publication/262599199_Unifying_Provenance_and_Debugging_for_Answer-Set_Programs?ev=prf_pub is based on meta-programming, it is possible to use existing state-of-the-art software systems that support well-founded and answer-set semantics, which allowed us to start developing this new tool by extending the one that exists related to a debugging approach: Spock, hence the name Cpt. Kirk. Furthermore and more importantly, one direction to explore is to use the technique of reification as described in "metaASP" to obtain the implicants via a saturation technique, and obtaining the prime implicants of provenance formulae by optimization and thus proper minimal justifications. -
Forever Free Full-Stack Observability | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
10
DE-HEoC
DE-based Weight Optimisation for Heterogeneous Ensemble
We propose the use of Differential Evolution algorithm for the weight adjustment of base classifiers used in weighted voting heterogeneous ensemble of classifier. Average Matthews Correlation Coefficient (MCC) score, calculated over 10-fold cross-validation, has been used as the measure of quality of an ensemble. DE/rand/1/bin algorithm has been utilised to maximize the average MCC score calculated using 10-fold cross-validation on training dataset. The voting weights of base classifiers are optimized for the heterogeneous ensemble of classifiers aiming to attain better generalization performances on testing datasets. -
11
DreamBooth Dataset
Text-to-Image Diffusion Models for Subject-Driven Generation
DreamBooth is a research project and dataset repository representing the official assets for the DreamBooth technique, a method for fine-tuning text-to-image generative diffusion models so they can generate specific, personalized subjects from just a handful of example images. Originally developed by researchers at Google Research and Boston University, DreamBooth works by associating a unique identifier token with a small set of photos of a person, object, or style, enabling the model to produce diverse and accurate images of that subject in new contexts once fine-tuned. This method addresses a common limitation of general-purpose diffusion models, which often struggle to faithfully reproduce lesser-known or custom subjects without extensive retraining. -
12
Extract Objects from Image
Connected Component Labeling Algorithm - Extracting Objects From image
fast Connected Component Labeling Algorithm - java application - Extracting Objects From image -
13
FALCON - Text Search Java Project
JSON based text search Java Project
----------------- - What is it? - ----------------- The "Falcon Search" is a JAVA API and tool to search inside the documents. It was originally started to search the content in pdf files under the project "HAWK Search". Searching with this tool is query-based not word-based as in most of the document search tools OR document readers. It also takes care of jumbling of words within query and spelling mistakes. Commonly used techniques in this project are Natural Language Processing, Information Extraction and Question-Answering Architecture. ---------------------- - Latest Version - ---------------------- Details of latest version can be found on project website - http://geekdadaji.com --------------------------- - CONTACT DETAILS - --------------------------- CREATOR : SWAPNIL A JADHAV (saj1919) EMAIL ID : dadajibudhau@gmail.com WEBSITE : http://geekdadaji.com LICENSE : CC BY-NC 4.0 -
14
FaceAccess Facial Recognition System
FaceAccess is an Access Control System based on Facial Recognition
With the growing need to exchange information and share resources, information security has become more important than ever in both the public and private sectors. Although many technologies have been developed to control access to files or resources, to enforce security policies, and to audit network usages, there does not exist a technology that can verify that the user who is using the system is the same person who logged in. FaceAccess provides a prototype implementation as a "login module" of an information system. The goal is to enhance the level of system security by periodically checking the user’s identity without disrupting the user’s activities. Installation instructions can be found in the package. If you need anymore guidance, please use the Wiki to post any kind of inquiry. NB: Please Donate to support the development of this project. PM me for other means. Any kind of support will be very much appreciated. Thanks a bunch. -
15
GA-EoC
GeneticAlgorithm-based search for Heterogeneous Ensemble Combinations
In data classification, there are no particular classifiers that perform consistently in every case. This is even worst in case of both the high dimensional and class-imbalanced datasets. To overcome the limitations of class-imbalanced data, we split the dataset using a random sub-sampling to balance them. Then, we apply the (alpha,beta)-k feature set method to select a better subset of features and combine their outputs to get a consolidated feature set for classifier training. To enhance classification performances, we propose an ensemble of classifiers that combine the classification outputs of base classifiers using the simplest and largely used majority voting approach. Instead of creating the ensemble using all base classifiers, we have implemented a genetic algorithm (GA) to search for the best combination from heterogeneous base classifiers. The classification performances achieved by the proposed method method on the chosen datasets are promising. -
16
Hermes Natural Language Processing
A repository of software, documentation and data for NLP
Hermes is a repository of software, documentation and data for NLP. I am currently adding corpora extracted from Wikipedia (mostrly in Romance languages). -
17
-
18
ML YouTube Courses
Discover the latest machine learning / AI courses on YouTube
ML YouTube Courses is a curated index of high-quality machine learning and AI courses available on YouTube, designed to make open education easier to discover and navigate. The repository organizes lectures from top universities and educators into a structured list so learners can quickly find reputable material. It covers a wide range of topics including deep learning, NLP, probabilistic modeling, reinforcement learning, and computer vision. The project reflects DAIR.AI’s broader mission to democratize access to AI education for the global community. Rather than hosting course content itself, it acts as a discovery hub pointing learners to the most valuable freely available video curricula. The list is periodically updated to include new courses and maintain relevance. Overall, ML-YouTube-Courses functions as a centralized directory for self-paced AI education through video learning. -
19
Machine Learning & Deep Learning
machine learning and deep learning tutorials, articles
Machine Learning & Deep Learning Tutorials is an open-source repository that provides practical tutorials demonstrating how to implement machine learning and deep learning models using popular frameworks such as TensorFlow and PyTorch. The project focuses on helping learners understand machine learning through hands-on coding examples rather than purely theoretical explanations. Each tutorial walks through the process of building and training models for tasks such as image classification, neural network training, and computer vision applications. The repository also includes explanations of how different algorithms function internally, helping readers connect theoretical knowledge with implementation details. Because the tutorials are organized into separate projects, users can easily explore specific topics or technologies within the machine learning ecosystem. -
20
Machine Learning for Software Engineers
A complete daily plan for studying to become a machine learning engine
Machine Learning for Software Engineers is an open-source learning roadmap designed to help software engineers transition into machine learning roles through a structured, practical study plan. The repository presents a top-down learning path that emphasizes hands-on experience rather than heavy theoretical prerequisites, making it particularly approachable for developers who already have programming experience but limited formal training in machine learning. The project organizes a multi-month study schedule that covers topics such as machine learning fundamentals, algorithm understanding, data preparation, and practical experimentation. It aggregates a wide range of resources including books, online courses, Kaggle competitions, podcasts, conferences, and community learning opportunities. The repository is structured to help learners gradually build the skills required for machine learning engineering positions while maintaining a focus on real-world application development. -
21
MetaCLIP
ICLR2024 Spotlight: curation/training code, metadata, distribution
MetaCLIP is a research codebase that extends the CLIP framework into a meta-learning / continual learning regime, aiming to adapt CLIP-style models to new tasks or domains efficiently. The goal is to preserve CLIP’s strong zero-shot transfer capability while enabling fast adaptation to domain shifts or novel class sets with minimal data and without catastrophic forgetting. The repository provides training logic, adaptation strategies (e.g. prompt tuning, adapter modules), and evaluation across base and target domains to measure how well the model retains its general knowledge while specializing as needed. It includes utilities to fine-tune vision-language embeddings, compute prompt or adapter updates, and benchmark across transfer and retention metrics. MetaCLIP is especially suited for real-world settings where a model must continuously incorporate new visual categories or domains over time. -
22
Movement Detection
Uses a webcam as a photo trap / movement detector
Inspired by Head First C. Small program written in C. It takes a photo with your webcam every time something moves before your webcam. Requires OpenCV library. -
23
Open Infra Index
Production-tested AI infrastructure tools
open-infra-index is a central “infrastructure index” repository maintained by DeepSeek AI that acts as a catalog and hub for a collection of production-tested AI infrastructure tools and internal building blocks they have open-sourced. Instead of a single monolithic codebase, it functions more like an index or launching point: linking and documenting a set of library repos (e.g. FlashMLA, DeepEP, DeepGEMM, 3FS, etc.) that together form DeepSeek’s infrastructure stack. The repo's README describes the project as sharing “humble building blocks” of their online service—code that is documented, deployed, and battle-tested in production. The timing of its opening matches DeepSeek’s “Open-Source Week” campaign (starting around February 2025) when they gradually released internal infrastructure components publicly. It is licensed under CC0-1.0 (Creative Commons Zero) to maximize openness. -
24
SIGGI
Simulation of Ideation Games and Games concerning Ideation
This is the SIGGI program used for a diploma thesis in 2012. It can be used as a solid basis for research concerning Ideation Games (Idea Creation). If you have module requests or want to contribute please contact the author. -
25
SimpleAiBot
A simple chat bot project for educational purposes! (OS X Only)
SimpleAiBot is created for educational purposes but it can grow out to something much bigger, however still educational. This project exists so other people can actually look at the code of a working chat bot and learn from it or even improve SimpleAiBot! If you're looking for this: this is it! Also don't hesitate to join and improve SimpleAiBot, better make your changes public and usable to everyone then experimenting on your own. PS: More experienced AI developers are also welcome to learn others how AI works!
