Open Source Linux Artificial Intelligence Software - Page 19
Sort By:
Artificial Intelligence Software for Linux
View 1204 business solutions-
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
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.
-
1
MIT Deep Learning Book
MIT Deep Learning Book in PDF format by Ian Goodfellow
The Deep Learning textbook is a resource intended to help students and practitioners enter the field of machine learning in general and deep learning in particular. The online version of the book is now complete and will remain available online for free. MIT Deep Learning Book in PDF format (complete and parts) by Ian Goodfellow, Yoshua Bengio and Aaron Courville. An MIT Press book Ian Goodfellow and Yoshua Bengio and Aaron Courville. Written by three experts in the field, Deep Learning is the only comprehensive book on the subject. This is not available as PDF download. So, I have taken the prints of the HTML content and bound them into a flawless PDF version of the book, as suggested by the website itself. Printing seems to work best printing directly from the browser, using Chrome. Other browsers do not work as well. -
2
Munder Difflin
local multi-agent harness
Munder Difflin is a desktop multi-agent harness that turns terminal coding CLIs into a coordinated team of autonomous workers. Each supported CLI runs as a real terminal process with its own identity, workspace, and visual avatar. A central orchestrator called Michael routes tasks, resolves routine coordination, and escalates sensitive actions for human approval. Agents communicate through local mailboxes, share a blackboard, and retain long-term memory across sessions. The app provides live terminals, task management, Git tools, cost telemetry, and optional per-agent worktrees. It supports major coding agents, bring-your-own keys, local LLMs, and desktop builds for macOS, Windows, and Linux. -
3
Octelium
A next-gen FOSS self-hosted unified zero trust secure access platform
Octelium is an open source, self-hosted unified secure-access platform built for modern infrastructure and hybrid environments. It positions itself as more than a typical VPN; it supports zero-trust network access (ZTNA), “BeyondCorp”-style access, API/AI gateway functionality, and even serves as a PaaS-like deployment surface. One of its key strengths is identity-based, application-layer (L7) aware control, meaning access decisions are made per request, with context and policy rather than simple network-level allow/block rules. It supports both client-based (e.g., WireGuard/QUIC tunnels) and client-less access models, which makes it flexible for both human users and automated workloads. The project also highlights self-hosted, no hidden “server-side” locked components, giving organizations greater ownership and control over access, rather than relying on proprietary SaaS. -
4
Qwen-Image
Qwen-Image is a powerful image generation foundation model
Qwen-Image is a powerful 20-billion parameter foundation model designed for advanced image generation and precise editing, with a particular strength in complex text rendering across diverse languages, especially Chinese. Built on the MMDiT architecture, it achieves remarkable fidelity in integrating text seamlessly into images while preserving typographic details and layout coherence. The model excels not only in text rendering but also in a wide range of artistic styles, including photorealistic, impressionist, anime, and minimalist aesthetics. Qwen-Image supports sophisticated editing tasks such as style transfer, object insertion and removal, detail enhancement, and even human pose manipulation, making it suitable for both professional and casual users. It also includes advanced image understanding capabilities like object detection, semantic segmentation, depth and edge estimation, and novel view synthesis. -
Earn up to 16% annual interest with Nexo.Generate interest, borrow against your crypto, and trade a range of cryptocurrencies — all in one platform. Geographic restrictions, eligibility, and terms apply.
-
5
TTS Voice Wizard
Speech to Text to Speech, sends text as OSC messages
Speech to Text to Speech. Song now playing. Sends text as OSC messages to VRChat to display on avatar. (STTTS) (Speech to TTS) (VRC STT System) Use TTS Voice Wizard's accessibility features to improve your VRChat experience (it works outside of VRChat too!) You can convert your Speech-to-Text and back to Speech through various Speech Recognition and Text-to-Speech methods. You can send what you say as OSC messages to VRChat to be displayed on your avatar using KillFrenzyAvatarText or VRChats Chatbox. The app can translate your speech from one language to over 20 other support languages. There are 100+ different voices with various customization options so you can pick a voice that best suits you. Display the current song you are listening to on Spotify or via your browser. Display tracker and controller battery life in conjunction with XSOverlay. Use in conjunction with HRtoVRChat_OSC to enable you to display your heartrate in VRChat's Chatbox. -
6
Thinc
A refreshing functional take on deep learning
Thinc is a lightweight deep learning library that offers an elegant, type-checked, functional-programming API for composing models, with support for layers defined in other frameworks such as PyTorch, TensorFlow and MXNet. You can use Thinc as an interface layer, a standalone toolkit or a flexible way to develop new models. Previous versions of Thinc have been running quietly in production in thousands of companies, via both spaCy and Prodigy. We wrote the new version to let users compose, configure and deploy custom models built with their favorite framework. Switch between PyTorch, TensorFlow and MXNet models without changing your application, or even create mutant hybrids using zero-copy array interchange. Develop faster and catch bugs sooner with sophisticated type checking. Trying to pass a 1-dimensional array into a model that expects two dimensions? That’s a type error. Your editor can pick it up as the code leaves your fingers. -
7
Unity MCP
AI-powered bridge connecting LLMs and advanced AI agents
Unity-MCP is an open-source integration that connects artificial intelligence assistants with the Unity game development environment through the Model Context Protocol. The project enables AI tools such as coding assistants and autonomous agents to interact directly with Unity projects, allowing them to analyze scenes, modify assets, and generate code within the development environment. By exposing Unity editor functionality through MCP tools, the plugin allows external AI systems to understand the structure of a game project and manipulate it programmatically. Developers can use natural language prompts to instruct AI assistants to create objects, modify scenes, or generate gameplay scripts automatically. The system supports both editor-level automation and runtime integration, meaning AI models can also be used inside compiled games for dynamic behavior such as interactive characters or debugging tools. -
8
Unla
Gateway service that instantly transforms existing MCP Servers
Unla is a lightweight, highly available MCP gateway written in Go that turns existing MCP servers or ordinary HTTP APIs into MCP-compliant services through configuration, not code changes. Its goal is to let teams “wire up” tools they already run—internal REST endpoints, third-party APIs, or local MCP servers—and present a single, reliable MCP interface to clients like Claude Desktop, Cursor, and IDEs. The gateway focuses on operational concerns you’d expect in production: multi-instance availability, health checking, and declarative routing that maps upstreams to MCP tools and resources. A quick-start and CLI make it easy to stand up an API server, while the package structure exposes helpers for people who want to embed or extend the gateway. Because it is itself MCP-speaking, Unla can sit in front of mixed fleets and normalize transports and schemas for clients. Documentation and pkg.go.dev pages reinforce the positioning as a stable, Go-native building block for MCP deployments. -
9
Unsloth Studio
Unified web UI for training and running open models locally
Unsloth Studio is a web-based interface for running and training AI models locally with a unified and user-friendly experience. It allows users to work with a wide range of models for text, audio, vision, embeddings, and more without relying heavily on cloud infrastructure. Built on top of the Unsloth framework, it focuses on high-performance training with reduced VRAM usage and faster speeds compared to traditional methods. The platform supports fine-tuning, pretraining, and reinforcement learning workflows, making it suitable for both experimentation and production use. Users can interact with models through chat, upload files like PDFs or images, and execute code within the environment to improve outputs. By combining powerful optimization techniques with an intuitive UI, Unsloth Studio simplifies the process of building and customizing AI models locally. -
AI-generated apps that pass security reviewRetool lets you generate dashboards, admin panels, and workflows directly on your data. Type something like “Build me a revenue dashboard on my Stripe data” and get a working app with security, permissions, and compliance built in from day one. Whether on our cloud or self-hosted, create the internal software your team needs without compromising enterprise standards or control.
-
10
VoxCPM
TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning
VoxCPM is a tokenizer-free text-to-speech system that models speech in a continuous space, aiming for extremely realistic, context-aware synthesis and true-to-life zero-shot voice cloning. Instead of converting speech into discrete tokens, it uses an end-to-end diffusion-autoregressive architecture built on the MiniCPM-4 backbone, combining hierarchical language modeling, finite scalar quantization (FSQ), and local Diffusion Transformers. This design helps decouple semantic and acoustic information while preserving fine-grained prosody, leading to more stable and expressive generation than many discrete-token systems. Trained on a large 1.8-million-hour bilingual corpus, VoxCPM can infer appropriate speaking style from context, dynamically adjusting intonation, rhythm, and emotional tone. It supports zero-shot voice cloning from a short reference audio clip, capturing timbre, accent, and pacing to closely mimic a target speaker without per-speaker fine-tuning. -
11
birdclaw
Stores all your tweets nicely claw-able for agents
birdclaw is a local-first Twitter workspace designed for archiving, organizing, searching, and interacting with Twitter or X content in a structured environment. The project combines a web application and command-line interface to help users import personal archives, cache live content locally, and manage replies or engagement workflows from a centralized system. Its architecture prioritizes data ownership and offline accessibility, allowing users to retain searchable records of posts, likes, bookmarks, and conversations without depending entirely on external platforms. birdclaw also supports synchronization and filtering features that make large archives easier to navigate and analyze. The tool is intended for researchers, creators, developers, and heavy social media users who want more control over their Twitter history and workflows. By emphasizing local storage and flexible retrieval, the project transforms social media archives into a searchable personal knowledge system. -
12
face-api.js
JavaScript API for face detection and face recognition in the browser
face-api.js is a JavaScript and TypeScript library for face analysis in web browsers and Node.js. It runs neural networks through TensorFlow.js and accepts images, videos, canvases, or tensors as input. The API can locate one or many faces using several detector models with configurable accuracy and performance settings. It can identify facial landmarks, compute recognition descriptors, classify expressions, and estimate age and gender. High-level chained methods let developers combine detection and analysis tasks in a compact workflow. Browser applications can draw boxes, labels, landmarks, and results on overlay canvases. Node.js support is available through image and canvas polyfills, with native TensorFlow bindings recommended for faster processing. -
13
free-code
The free build of Claude Code
Free-code is an open-source platform aimed at providing accessible coding resources, tools, or templates that help developers learn, build, and share projects without barriers. It typically focuses on simplifying the development process by offering prebuilt components, example projects, or utilities that can be reused across different applications. The project is designed to encourage collaboration and knowledge sharing within the developer community, making it easier for beginners and experienced developers alike to access useful code snippets and frameworks. It may include a collection of curated resources that span multiple programming languages and use cases. Free-code emphasizes openness and accessibility, ensuring that users can freely explore, modify, and distribute the code. Its structure often supports modular usage, allowing developers to pick and choose what they need for their projects. -
14
openalpr
Automatic license plate recognition library
Deploy license plate and vehicle recognition with Rekor’s OpenALPR suite of solutions designed to provide invaluable vehicle intelligence which enhances business capabilities, automates tasks, and increases overall community safety! Rekor’s OpenALPR suite of solutions utilizes artificial intelligence and machine learning to greatly surpass legacy OCR solutions. Now, in real-time, users can receive a vehicle's plate number, make, model, color, and direction of travel. Rekor’s OpenALPR suite of solutions allows law enforcement and homeowners to protect their communities, while businesses can boost customer loyalty by receiving alerts the moment a plate of interest is detected. Rekor’s OpenALPR suite of solutions is a force multiplier. Rekor Scout™ upgrades nearly any IP, traffic, or security camera to give you an immediate edge, while Rekor CarCheck analyzes vehicle images and returns valuable data for countless business use-cases. -
15
stable-diffusion-webui-colab
Stable diffusion webui colab
Stable Diffusion webui colab. lite has a stable WebUI and stable installed extensions. stable has ControlNet, a stable WebUI, and stable installed extensions. Nightly has ControlNet, the latest WebUI, and daily installed extension updates. If you want to use more models, you can download your model into Colab, which has an empty 50GB space. You can also free up more space by deleting the default model in your drive. If you don't plan to use ControlNet models, you can also free up space by deleting them. -
16
supabase-py
Python Client for Supabase. Query Postgres from Flask, Django
Python Client for Supabase. Query Postgres from Flask, Django, FastAPI. Python user authentication, security policies, edge functions, file storage, and realtime data streaming. Good first issue. -
17
tgbot-cpp
C++ library for Telegram bot API
C++ library for Telegram bot API. -
18
xTuring
Easily build, customize and control your own LLMs
xTuring is an open-source AI personalization software. xTuring makes it easy to build and control LLMs by providing a simple interface to personalize LLMs to your own data and application. xTuring provides fast, efficient and simple fine-tuning of LLMs, such as LLaMA, GPT-J, Galactica, and more. By providing an easy-to-use interface for fine-tuning LLMs to your own data and application, xTuring makes it simple to build, customize and control LLMs. The entire process can be done inside your computer or in your private cloud, ensuring data privacy and security. -
19
AI Runner
Offline inference engine for art, real-time voice conversations
AI Runner is an offline inference engine designed to run a collection of AI workloads on your own machine, including image generation for art, real-time voice conversations, LLM-powered chatbots and automated workflows. It is implemented as a desktop-oriented Python application and emphasizes privacy and self-hosting, allowing users to work with text-to-speech, speech-to-text, text-to-image and multimodal models without sending data to external services. At the core of its LLM stack is a mode-based architecture with specialized “modes” such as Author, Code, Research, QA and General, and a workflow manager that automatically routes user requests to the right agent based on the task. The project has a strong focus on developer ergonomics, with thorough development guidelines, environment configuration using .env variables, and a clear structure for tests, tools and agents. -
20
AlphaFold 3
AlphaFold 3 inference pipeline
AlphaFold 3, developed by Google DeepMind, is an advanced deep learning system for predicting biomolecular structures and interactions with exceptional accuracy. This repository provides the complete inference pipeline for running AlphaFold 3, though access to the model parameters is restricted and must be obtained directly from Google under specific terms of use. The system is designed for scientific research applications in structural biology, biochemistry, and bioinformatics, enabling accurate modeling of proteins, ligands, and covalent modifications. Users can perform local predictions via Docker containers, integrating AlphaFold 3’s inference process with provided JSON input configurations. The software includes flexible options for running both data preprocessing and GPU-accelerated inference, allowing users to adapt to available computational resources. -
21
AlphaZero.jl
A generic, simple and fast implementation of Deepmind's AlphaZero
Beyond its much publicized success in attaining superhuman level at games such as Chess and Go, DeepMind's AlphaZero algorithm illustrates a more general methodology of combining learning and search to explore large combinatorial spaces effectively. We believe that this methodology can have exciting applications in many different research areas. Because AlphaZero is resource-hungry, successful open-source implementations (such as Leela Zero) are written in low-level languages (such as C++) and optimized for highly distributed computing environments. This makes them hardly accessible for students, researchers and hackers. Many simple Python implementations can be found on Github, but none of them is able to beat a reasonable baseline on games such as Othello or Connect Four. As an illustration, the benchmark in the README of the most popular of them only features a random baseline, along with a greedy baseline that does not appear to be significantly stronger. -
22
BotKube
An app that helps you monitor your Kubernetes cluster
BotKube is a messaging bot for monitoring and debugging Kubernetes clusters. It's built and maintained by InfraCloud. BotKube can be integrated with multiple messaging platforms like - Slack, Mattermost, Microsoft Teams to help you monitor your Kubernetes cluster(s), debug critical deployments and gives recommendations for standard practices by running checks on the Kubernetes resources. BotKube watches Kubernetes resources and sends a notification to the channel if any event occurs for example a ImagePullBackOff error. You can customize the objects and level of events you want to get from the Kubernetes cluster. You can turn on/off notifications simply by sending a message to @BotKube. BotKube can execute kubectl commands on Kubernetes cluster without giving access to Kubeconfig or underlying infrastructure. With BotKube you can debug your deployment, services or anything about your cluster right from your messaging window. -
23
CTranslate2
Fast inference engine for Transformer models
CTranslate2 is a C++ and Python library for efficient inference with Transformer models. The project implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU. The execution is significantly faster and requires less resources than general-purpose deep learning frameworks on supported models and tasks thanks to many advanced optimizations: layer fusion, padding removal, batch reordering, in-place operations, caching mechanism, etc. The model serialization and computation support weights with reduced precision: 16-bit floating points (FP16), 16-bit integers (INT16), and 8-bit integers (INT8). The project supports x86-64 and AArch64/ARM64 processors and integrates multiple backends that are optimized for these platforms: Intel MKL, oneDNN, OpenBLAS, Ruy, and Apple Accelerate. -
24
DINOv3
Reference PyTorch implementation and models for DINOv3
DINOv3 is the third-generation iteration of Meta’s self-supervised visual representation learning framework, building upon the ideas from DINO and DINOv2. It continues the paradigm of learning strong image representations without labels using teacher–student distillation, but introduces a simplified and more scalable training recipe that performs well across datasets and architectures. DINOv3 removes the need for complex augmentations or momentum encoders, streamlining the pipeline while maintaining or improving feature quality. The model supports multiple backbone architectures, including Vision Transformers (ViT), and can handle larger image resolutions with improved stability during training. The learned embeddings generalize robustly across tasks like classification, retrieval, and segmentation without fine-tuning, showing state-of-the-art transfer performance among self-supervised models. -
25
Denoiser
Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)
Denoiser is a real-time speech enhancement model operating directly on raw waveforms, designed to clean noisy audio while running efficiently on CPU. It uses a causal encoder-decoder architecture with skip connections, optimized with losses defined both in the time domain and frequency domain to better suppress noise while preserving speech. Unlike models that operate on spectrograms alone, this design enables lower latency and coherent waveform output. The implementation includes data augmentation techniques applied to the raw waveforms (e.g. noise mixing, reverberation) to improve model robustness and generalization to diverse noise types. The project supports both offline denoising (batch inference) and live audio processing (e.g. via loopback audio interfaces), making it practical for real-time use in calls or recording. The codebase includes training and evaluation scripts, configuration management via Hydra, and pretrained models on standard noise datasets.
