Open Source Linux Artificial Intelligence Software - Page 81
Sort By:
Artificial Intelligence Software for Linux
View 1204 business solutions-
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.
-
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.
-
1
Xorbits Inference
Replace OpenAI GPT with another LLM in your app
Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any open-source language models, speech recognition models, and multimodal models, whether in the cloud, on-premises, or even on your laptop. Xorbits Inference(Xinference) is a powerful and versatile library designed to serve language, speech recognition, and multimodal models. With Xorbits Inference, you can effortlessly deploy and serve your or state-of-the-art built-in models using just a single command. Whether you are a researcher, developer, or data scientist, Xorbits Inference empowers you to unleash the full potential of cutting-edge AI models. -
2
Z80-μLM
Z80-μLM is a 2-bit quantized language model
Z80-μLM is a retro-computing AI project that demonstrates a tiny language model (Z80-μLM) engineered to run on an 8-bit Z80 CPU by aggressively quantizing weights down to 2-bit precision. The repository provides a complete workflow where you train or fine-tune conversational models in Python, then export them into a format that can be executed on classic Z80 systems. A key deliverable is producing CP/M-compatible .COM binaries, enabling a genuinely vintage “chat with your computer” experience on real hardware or accurate emulators. The project sits at the intersection of machine learning and systems constraints, showing how model architecture, quantization, and inference code generation can be adapted to extreme memory and compute limits. It also functions as an educational reference for how to reduce inference to operations that fit an old-school instruction set and runtime environment. -
3
ZenML
Build portable, production-ready MLOps pipelines
A simple yet powerful open-source framework that scales your MLOps stack with your needs. Set up ZenML in a matter of minutes, and start with all the tools you already use. Gradually scale up your MLOps stack by switching out components whenever your training or deployment requirements change. Keep up with the latest changes in the MLOps world and easily integrate any new developments. Define simple and clear ML workflows without wasting time on boilerplate tooling or infrastructure code. Write portable ML code and switch from experimentation to production in seconds. Manage all your favorite MLOps tools in one place with ZenML's plug-and-play integrations. Prevent vendor lock-in by writing extensible, tooling-agnostic, and infrastructure-agnostic code. Run your ML workflows anywhere: local, on-premises, or in the cloud environment of your choice. Keep yourself open to new tools - ZenML is easily extensible and forever open-source! -
4
Zep
Zep: A long-term memory store for LLM / Chatbot applications
Easily add relevant documents, chat history memory & rich user data to your LLM app's prompts. Understands chat messages, roles, and user metadata, not just texts and embeddings. Zep Memory and VectorStore implementations are shipped with your favorite frameworks: LangChain, LangChain.js, LlamaIndex, and more. Automatically embed texts and messages using state-of-the-art opeb source models, OpenAI, or bring your own vectors. Zep’s local embedding models and async enrichment ensure a snappy user experience. -
Earn up to 16% annual interest with Nexo.Put idle assets to work with competitive interest rates, borrow without selling, and trade with precision. All in one platform. Geographic restrictions, eligibility, and terms apply.
-
5
Zero to Mastery Machine Learning
All course materials for the Zero to Mastery Machine Learning
Zero to Mastery Machine Learning is an open-source repository that contains the complete course materials for the Zero to Mastery Machine Learning and Data Science bootcamp. The project provides a structured curriculum designed to teach machine learning and data science using Python through hands-on projects and interactive notebooks. The repository includes datasets, Jupyter notebooks, documentation, and example code that walk learners through the entire machine learning workflow from problem definition to model deployment. The course introduces essential tools such as NumPy, pandas, Matplotlib, and scikit-learn before moving on to deep learning with frameworks like TensorFlow and Keras. It also includes milestone projects that demonstrate how to build end-to-end machine learning systems using real datasets, including classification and regression tasks. -
6
Zvec
A lightweight, lightning-fast, in-process vector database
Zvec is an open-source, lightweight, in-process vector database designed to embed directly into applications and serve fast similarity search workloads without the overhead of a separate server process. Developed by Alibaba’s Tongyi Lab, it positions itself as the “SQLite of vector databases” by being easy to integrate, minimal in dependencies, and capable of handling high throughput with low latency on edge devices or small systems. Zvec excels at approximate nearest neighbor search and retrieval tasks that power features like semantic search, recommendation systems, and retrieval-augmented generation (RAG) setups. Its performance benchmarks show it achieving high queries-per-second and fast index build times compared to similar tools. Because it runs in-process, developers can embed it in native apps, microservices, or edge computing scenarios where traditional server-based vector databases might be overkill. -
7
agency-agents-zh
193 plug-and-play AI expert roles
agency-agents-zh is a framework focused on building and coordinating multiple AI agents, likely with a particular emphasis on Chinese-language environments or documentation. The project appears to explore the concept of agent collaboration, where different agents handle specialized tasks and communicate to achieve broader objectives. It is designed to simulate organizational workflows, enabling complex problem-solving through distributed intelligence rather than a single monolithic model. The system likely includes tools for defining agent roles, managing communication protocols, and orchestrating task execution across agents. Its multilingual or localized orientation suggests it is tailored for specific linguistic or regional use cases, particularly in Chinese-speaking contexts. Overall, it serves as an experimental platform for studying and deploying cooperative AI agent systems. -
8
agentgateway
Next Generation Agentic Proxy for AI Agents and MCP servers
Agentgateway is an open-source “data plane” built specifically for agentic AI connectivity, focusing on how agents talk to other agents and to tools across different frameworks and environments. It presents itself as a complete connectivity solution that adds drop-in security, observability, and governance to agent-to-agent and agent-to-tool communication without requiring you to rebuild your agent stack. The project supports interoperable protocols designed for this ecosystem, including Agent2Agent (A2A) and Model Context Protocol (MCP), which helps standardize how tools and agents interoperate. It is designed for performance and scale, implemented in Rust and engineered to handle large throughput and multi-tenant deployments. Operationally, it emphasizes safety and control with an RBAC system tuned for MCP/A2A use cases, plus the ability to update configuration dynamically via xDS without downtime. -
9
amazon-connect-wisdomjs
Gives you the power to build your own Wisdom widget
Amazon Connect Wisdom, a feature of Amazon Connect, delivers agents the information they need, reducing the time spent searching for answers. Today, knowledge articles, wikis, and FAQs are spread across separate repositories. Agents lose a lot of time trying to navigate all those different sources of information, and in the meantime, the customer waits for an answer. Amazon Connect Wisdom connects relevant knowledge repositories with built-in connectors for third-party applications like Salesforce and ServiceNow, as well as internal wikis, FAQ stores, and file shares. With Wisdom, agents can search across connected repositories to find answers and quickly resolve customer issues. In addition, Wisdom uses real-time speech analytics and natural language processing (NLP) from Contact Lens for Amazon Connect to detect customer issues during calls, and then provide agents with recommendations and answers. Wisdom provides faster issue resolution and improved customer satisfaction. -
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
baoyu-design
Run Claude Design locally as an Agent Skill
baoyu-design is an Agent Skill that lets local coding agents produce polished visual design artifacts. It packages Claude Design-style methodology for environments such as Cursor, Claude Code, Codex, Claude Desktop, and other file-capable agents. The skill can generate UI mockups, prototypes, wireframes, landing pages, dashboards, mobile app screens, and slide decks as self-contained HTML. It keeps outputs inside the local project, so artifacts can be versioned, edited, previewed, and refined without uploading work to a separate design website. The repository includes core design instructions, harness-specific references, built-in skills, starter components, and local preview guidance. It is useful for developers and designers who want agent-assisted product design inside their own editor workflow. -
11
canvas-constructor
An ES6 utility for canvas with built-in functions and chained methods
An ES6 utility for canvas with built-in functions and chained methods. Alternatively, you can import canvas-constructor/browser. That will create a canvas with size of 300 pixels width, 300 pixels height. Set the color to #AEFD54. Draw a rectangle with the previous color, covering all the pixels from (5, 5) to (290 + 5, 290 + 5) Set the color to #FFAE23. Set the font size to 28 pixels with font Impact. Write the text 'Hello World!' in the position (130, 150) Return a buffer. -
12
chat
chat web app for teams, sass with user management and ratelimit
chat is a team-oriented chat web application delivered as a SaaS-style system with built-in user management, rate limiting, and support for several major model providers. It is positioned as a collaborative chat platform rather than a single-user demo, which is reflected in its administrative structure, multi-user handling, and deployment-oriented documentation. The project supports OpenAI, Azure OpenAI, Claude, Gemini, and Ollama-hosted models, giving teams flexibility in how they connect model backends. Its feature set includes shareable static pages generated from conversations, searchable conversation snapshots, text file uploads, multimedia file support when the model allows it, and prompt management with shortcut-based access. The repository structure also points to both web and Flutter-based mobile components, suggesting a broader product surface than a simple browser-only interface. -
13
claurst
Your favorite Terminal Coding Agent, now in Rust
claurst is an experimental AI agent framework that appears to focus on structured reasoning and task execution within coding or automation environments. The project likely explores how agents can be designed to handle complex workflows through modular components and clearly defined execution steps. It may include abstractions for managing context, decision-making, and interaction with external tools, enabling agents to perform multi-step tasks efficiently. The architecture suggests a focus on flexibility, allowing developers to adapt the system to different use cases or domains. It is likely intended as a lightweight but extensible platform for experimenting with agent behavior and orchestration. The project may also emphasize simplicity, making it accessible for developers who want to prototype agent systems quickly. -
14
compromise
Modest natural-language processing
Language is complicated and there's a gazillion words. Compromise is a javascript library that interprets and pre-parses text and makes some reasonable decisions so things are way easier. Compromise tries its best to parse text. it is small, quick, and often good-enough. It is not as smart as you'd think. Conjugate and negate verbs in any tense. Play between plural, singular and possessive forms. Interpret plain-text numbers. Handle implicit terms. Use it on the client-side or as an es-module. compromise is 180kb (minified). It's pretty fast. It can run on keypress. It works mainly by conjugating all forms of a basic word list. Decide how words get interpreted or make heavier changes with a compromise-plugin. Parse text without running POS-tagging. Pre-parse any match statements for faster lookups. It is not the most accurate, or clever nlp library, but found its niche as an easy, small library that can run everywhere. -
15
designlang
Extract any website's complete design system with one command
designlang is a powerful tool that extracts complete design systems from existing websites using automated analysis and converts them into reusable assets and tokens. It generates structured outputs such as design tokens, semantic components, and styling systems that can be used across multiple platforms. The tool supports exporting to frameworks like Tailwind, SwiftUI, Flutter, and WordPress, making it highly versatile for cross-platform development. It also integrates with tools like Figma and shadcn, enabling seamless design-to-code workflows. The system includes accessibility analysis features, such as WCAG compliance checks and CSS health audits, helping developers improve usability and standards compliance. It can be used via CLI or browser extension, making it flexible for different workflows. Overall, design-extract automates the process of reverse-engineering design systems, significantly accelerating frontend development. -
16
elevenlabs-api
elevenlabs-api is an open source Java wrapper around the ElevenLabs
Elevenlabs-api is an open-source Java wrapper around the ElevenLabs Voice Synthesis and Cloning Web API. Compiled JARs are available via the Releases tab. To access your ElevenLabs API key, head to the official website, you can view your xi-API-key using the 'Profile' tab on the website. To set up your ElevenLabs API key, you must register it with the ElevenLabsAPI Java API. For any public repository security, you should store your API key in an environment variable, or external from your source code. The most realistic and versatile AI speech software, ever. Eleven brings the most compelling, rich and lifelike voices to creators and publishers seeking the ultimate tools for storytelling. Generate top-quality spoken audio in any voice and style with the most advanced and multipurpose AI speech tool out there. Our deep learning model renders human intonation and inflections with unprecedented fidelity and adjusts delivery based on context. -
17
embedchain
Framework to easily create LLM powered bots over any dataset
Embedchain is a framework to easily create LLM-powered bots over any dataset. If you want a javascript version, check out embedchain-js. Embedchain empowers you to create chatbot models similar to ChatGPT, using your own evolving dataset. Start building LLM powered bots under 30 seconds. -
18
esp32-ai
Running a 28.9M parameter LLM on an $8 microcontroller
esp32-ai is an experimental language-model project that runs a 28.9-million-parameter model entirely on an ESP32-S3 microcontroller. The quantized model occupies about 14.9 MB and generates text without sending data to a server. Most parameters remain in flash through a Per-Layer Embeddings design, while active computation uses SRAM and PSRAM. This memory layout allows the device to retrieve only the embedding rows required for each token. The implementation reaches roughly 9.5 tokens per second and can display generated words on a connected screen. Trained on TinyStories, the model produces short, simple stories rather than answering questions, following instructions, or providing factual knowledge. The repository includes firmware, wiring and flashing instructions, training code, quantization experiments, ablations, and measured results. -
19
finetuner
Task-oriented finetuning for better embeddings on neural search
Fine-tuning is an effective way to improve performance on neural search tasks. However, setting up and performing fine-tuning can be very time-consuming and resource-intensive. Jina AI’s Finetuner makes fine-tuning easier and faster by streamlining the workflow and handling all the complexity and infrastructure in the cloud. With Finetuner, you can easily enhance the performance of pre-trained models, making them production-ready without extensive labeling or expensive hardware. Create high-quality embeddings for semantic search, visual similarity search, cross-modal text image search, recommendation systems, clustering, duplication detection, anomaly detection, or other uses. Bring considerable improvements to model performance, making the most out of as little as a few hundred training samples, and finish fine-tuning in as little as an hour. -
20
hfapigo
Unofficial (Golang) Go bindings for the Hugging Face Inference API
(Golang) Go bindings for the Hugging Face Inference API. Directly call any model available in the Model Hub. An API key is required for authorized access. To get one, create a Hugging Face profile. -
21
hloc
Visual localization made easy with hloc
This is hloc, a modular toolbox for state-of-the-art 6-DoF visual localization. It implements Hierarchical Localization, leveraging image retrieval and feature matching, and is fast, accurate, and scalable. This codebase won the indoor/outdoor localization challenges at CVPR 2020 and ECCV 2020, in combination with SuperGlue, our graph neural network for feature matching. We provide step-by-step guides to localize with Aachen, InLoc, and to generate reference poses for your own data using SfM. Just download the datasets and you're reading to go! The notebook pipeline_InLoc.ipynb shows the steps for localizing with InLoc. It's much simpler since a 3D SfM model is not needed. We show in pipeline_SfM.ipynb how to run 3D reconstruction for an unordered set of images. This generates reference poses, and a nice sparse 3D model suitable for localization with the same pipeline as Aachen. -
22
html-ppt
AgentSkill with 24 themes, 31 layouts, 20+ animations
html-ppt-skill is an AI-oriented skill designed to generate presentation slides using HTML as the underlying structure instead of traditional PowerPoint formats. It enables users to create visually structured, web-based slide decks that can be rendered in browsers or converted into presentation formats. The system focuses on translating structured ideas into clean layouts, combining content organization with lightweight styling. It integrates well with AI workflows, allowing automated generation of presentations from prompts or documents. The approach emphasizes flexibility, enabling customization through standard web technologies like HTML and CSS. It is particularly useful for developers and creators who prefer programmable presentation pipelines. Overall, it bridges the gap between web development and presentation design. -
23
img2dataset
Easily turn large sets of image urls to an image dataset
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine. Also supports saving captions for url+caption datasets. Opt-out directives: Websites can pass the http headers X-Robots-Tag: noai, X-Robots-Tag: noindex , X-Robots-Tag: noimageai and X-Robots-Tag: noimageindex By default img2dataset will ignore images with such headers. -
24
imodelsX
Interpretable prompting and models for NLP
Interpretable prompting and models for NLP (using large language models). Generates a prompt that explains patterns in data (Official) Explain the difference between two distributions. Find a natural-language prompt using input-gradients. Fit a better linear model using an LLM to extract embeddings. Fit better decision trees using an LLM to expand features. Finetune a single linear layer on top of LLM embeddings. Use these just a like a sci-kit-learn model. During training, they fit better features via LLMs, but at test-time, they are extremely fast and completely transparent. -
25
kMCP
Kubernetes Controller for building, testing and deploying MCP servers
KMCP is a companion toolchain for building, testing, and deploying MCP servers with a workflow that spans local development through Kubernetes production deployments. It includes a CLI for day-to-day development tasks like scaffolding new MCP projects, managing tools, building container images, and running an MCP server locally for validation. For cluster operations, it includes a Kubernetes controller that manages MCP server lifecycles using a dedicated Custom Resource Definition (CRD), allowing MCP servers to be represented as native Kubernetes objects you can operate with familiar kubectl-driven patterns. A key component is the transport adapter, which fronts MCP servers to provide routing and multi-transport support without requiring code changes in your server implementation. The project is geared toward consistency, aiming to reduce the “glue work” of writing Dockerfiles, hand-rolling manifests, and manually wiring networking and deployment details for each MCP server.
