Search Results for "ai" - Page 9
Sort By:
Showing 520 open source projects for "ai"
View related business solutions-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
1
TensorRT
C++ library for high performance inference on NVIDIA GPUs
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference. It includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for deep learning inference applications. TensorRT-based applications perform up to 40X faster than CPU-only platforms during inference. With TensorRT, you can optimize neural network models trained in all major frameworks, calibrate for lower precision with high accuracy, and deploy to hyperscale data centers,... -
2
Kubectl OpenAI plugin
Kubectl plugin for OpenAI GPT
This project is a kubectl plugin to generate and apply Kubernetes manifests using OpenAI GPT. -
3
Positron
Positron, a next-generation data science IDE
...Built on the open-source Code-OSS foundation, Positron provides a familiar coding experience along with specialized panes and tooling for variable inspection, data-frame viewing, plotting previews, and interactive consoles designed for analytical work. The IDE supports notebook and script workflows, integration of data-app frameworks (such as Shiny, Streamlit, Dash), database and cloud connections, and built-in AI-assisted capabilities to help write code, explore data, and build models. -
4
FlashMLA
FlashMLA: Efficient Multi-head Latent Attention Kernels
FlashMLA is a high-performance decoding kernel library designed especially for Multi-Head Latent Attention (MLA) workloads, targeting NVIDIA Hopper GPU architectures. It provides optimized kernels for MLA decoding, including support for variable-length sequences, helping reduce latency and increase throughput in model inference systems using that attention style. The library supports both BF16 and FP16 data types, and includes a paged KV cache implementation with a block size of 64 to... -
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
Antigravity Awesome Skills
The Ultimate Collection of 700+ Agentic Skills for Claude Code
Antigravity Awesome Skills is a playful yet practical repository that curates a set of clever, expressive, and sometimes whimsical AI agent skill templates designed to help users bootstrap agent behavior quickly. Rather than focusing on production-grade systems, it provides creative and high-impact skills that demonstrate how agents can be used to automate tasks, generate content, assist with daily operations, or integrate into larger workflows with minimal configuration. -
6
Bot Framework SDK for JavaScript
Welcome to the Bot Framework SDK for JavaScript repository
This repository contains code for the JavaScript version of the Microsoft Bot Framework SDK, which is part of the Microsoft Bot Framework - a comprehensive framework for building enterprise-grade conversational AI experiences. This SDK enables developers to model conversation and build sophisticated bot applications using JavaScript. SDKs for .NET, Python and Java (preview) are also available. To get started building bots using the SDK, see the Azure Bot Service Documentation. If you are an existing user, then you can also find out what's new with Bot Framework. -
7
X-Crawl
Flexible Node.js AI-assisted crawler library
A high-performance web crawling and scraping framework for Node.js, designed for large-scale data extraction. -
8
GoShip
Opinionated Go/HTMX boilerplate with payments, emails, auth, etc.
An opinionated Go and HTMX boilerplate featuring payments, emails, authentication, and notifications. A Go + HTMX boilerplate with all the essentials for your SaaS, AI tools, or web apps. Start earning online quickly without the hassle. -
9
Plugins
Curated collection of Codex plugin examples
...The repository is useful for developers who want practical references instead of abstract plugin documentation alone. It demonstrates how different plugin components can work together to add specialized behavior to an AI coding environment. Its main value is helping builders understand how to create reusable Codex extensions with clear organization and predictable project conventions. -
Error to trace to log to deploy. One click. No SSH.AppSignal links every error to the trace, the trace to the log, the log to the deploy that shipped it.
-
10
Xata Agent
AI agent expert in PostgreSQL
Xata Agent is a local development tool that provides a seamless integration experience for developers working with Xata, a serverless database platform. It runs a local proxy that mimics production behavior, allowing developers to test and develop with local credentials, preview branches, and schema changes. The agent is built for productivity, enabling tight CLI and Git integration for data workflows. -
11
Trigger.dev
Trigger.dev is the open source background jobs platform
Write normal async code and we'll handle the rest, from deployment to elastic scaling. No timeouts, real-time monitoring, and zero infrastructure to manage. Reliably call AI APIs with no timeouts, automatic retrying, and tracing. Use existing Node.js SDKs and code from your repo. -
12
Karpathy-Inspired Claude Code Guidelines
A single CLAUDE.md file to improve Claude Code behavior
Karpathy-Inspired Claude Code Guidelines is a curated learning and experimentation repository inspired by the work and teaching philosophy of Andrej Karpathy, designed to help learners build practical competence in deep learning, neural networks, and AI infrastructure. The project organizes a progressive path through exercises, notebooks, code examples, and practical mini-projects that echo Karpathy’s approach to “learning by doing,” where students build core concepts from first principles rather than consuming superficial abstractions. It covers topics like implementing backpropagation from scratch, understanding convolutional and recurrent networks, building simple training loops, and exploring real datasets with hands-on code. ... -
13
Claude Island
Claude Code notifications without the context switch
Claude Island is a macOS menu-bar utility that elevates your command-line AI sessions by turning them into dynamic, always-visible notifications that live in your laptop’s notch area or menu bar. Rather than constantly switching back to a terminal window to check the status of Claude Code sessions, Claude Island monitors session state hooks and displays ongoing activity, permission requests, and chat history right from a lightweight overlay. -
14
txtai
Build AI-powered semantic search applications
txtai executes machine-learning workflows to transform data and build AI-powered semantic search applications. Traditional search systems use keywords to find data. Semantic search applications have an understanding of natural language and identify results that have the same meaning, not necessarily the same keywords. Backed by state-of-the-art machine learning models, data is transformed into vector representations for search (also known as embeddings). -
15
Librelancer
A re-implementation of Freelancer
Librelancer is an open-source reimplementation of the engine behind Freelancer, the iconic 2003 space trading and combat simulation game by Microsoft. Written in C# and powered by OpenGL and modern game development practices, Librelancer faithfully replicates the original gameplay while providing a flexible codebase for modding, analysis, and future enhancements. It supports original assets and is designed to be both a preservation project and a foundation for new space simulation games... -
16
Destructive Command Guard
The Destructive Command Guard (dcg) is for blocking dangerous git
Destructive Command Guard is a high-performance safety hook for AI coding agents and command-line workflows. It intercepts shell commands before execution and blocks operations that could erase files, rewrite Git history, destroy infrastructure, or remove data. The Rust implementation uses fast filtering and context-aware rules to distinguish dangerous execution from harmless text matches. Its modular security packs cover Git, filesystems, databases, containers, cloud platforms, Kubernetes, Terraform, and other tools. ... -
17
ollama-hpp
Modern, Header-only C++ bindings for the Ollama API
...The project also evolves alongside the Ollama API, adding support for newer features such as blob handling and improved model interaction capabilities. Its design prioritizes simplicity, allowing developers to quickly integrate AI features without introducing large dependencies. -
18
any-llm
Communicate with an LLM provider using a single interface
any-llm is a unified SDK and platform developed by Mozilla AI that allows developers to interact with multiple large language model providers through a single, consistent interface. Instead of rewriting code for each provider, developers can switch between services like OpenAI, Anthropic, Mistral, and Ollama simply by changing configuration parameters. The project is designed to be framework-agnostic, making it easy to integrate into scripts, applications, or production systems without being tied to a specific stack. ... -
19
CUDA Python
Performance meets Productivity
...It integrates tightly with the broader Python GPU ecosystem, including Numba for kernel compilation and CCCL for parallel primitives, allowing developers to write performant code without leaving Python. The toolkit also includes utilities for profiling, memory management, distributed computing, and numerical operations, making it suitable for scientific computing, AI, and data processing workloads. -
20
Codex Skill Manager
macOS app to manage your Codex skills
CodexSkillManager is a native macOS application built with SwiftUI that provides a visual and user-friendly interface for managing local skills used by AI coding assistants like Codex and Claude Code. It allows users to browse, install, delete, and inspect both locally stored and remote skills (such as those from Clawdhub) without requiring manual file manipulation on disk, making it simpler to keep skills organized and up to date. The app renders skill descriptions from SKILL.md files directly within the UI, including inline previews for references, which helps developers quickly understand a skill’s purpose and usage before installation. ... -
21
zeroshot CLI
Your autonomous engineering team in a CLI. Point Zeroshot at an issue
...It orchestrates a multi-agent workflow where separate roles such as planner, implementer, and independent validators collaborate in isolated environments, looping until the code meets acceptance criteria or produces reproducible failures. The tool supports multiple underlying AI providers like Claude Code, Codex, OpenCode, and Gemini, as well as integration with issue backends like GitHub, GitLab, Jira, and Azure DevOps, enabling flexible input sources and automation in diverse environments. Zeroshot manages isolation via git worktrees or Docker containers, which helps ensure that each agent’s work is reproducible and shielded from unwanted interference, and it persists crash-safe state so tasks can resume if interrupted. -
22
Three.js Skills for Claude Code
Collection of Three.js skill files
Three.js Skills for Claude Code repository is a curated collection of modular skills and educational code aimed at helping developers learn and apply Three.js, the popular JavaScript library for 3D graphics on the web. It groups foundational lessons, examples, and utilities that make it easier to set up 3D scenes, work with cameras, lighting, materials, shaders, and animation loops, and handle user interactions in a browser context. The project functions as a toolbox of practical snippets... -
23
FastMCP Framework
A TypeScript framework for building MCP servers
...Developers can use it to build server back-ends that expose data or capabilities to LLM applications in a standardized way, reducing the custom boilerplate required for integrating with AI systems. It includes tooling for development (examples, CLI) and is open-source, inviting contributions and extensions. -
24
SDGym
Benchmarking synthetic data generation methods
The Synthetic Data Gym (SDGym) is a benchmarking framework for modeling and generating synthetic data. Measure performance and memory usage across different synthetic data modeling techniques – classical statistics, deep learning and more! The SDGym library integrates with the Synthetic Data Vault ecosystem. You can use any of its synthesizers, datasets or metrics for benchmarking. You also customize the process to include your own work. Select any of the publicly available datasets from the... -
25
Privacy Respecting
Curated List of Privacy Respecting Services and Software
...The repository covers categories such as search engines, social networks, messengers, cloud storage, VPNs, hosting, email, operating systems, browsers, video sharing, AI assistants, and maps. It also links to related security checklists and privacy education projects. The list is useful for people comparing privacy-conscious tools before changing their everyday digital habits. Its main value is centralizing practical options for reducing tracking, improving data control, and finding more respectful software ecosystems.
