Open Source Swift Artificial Intelligence Software
Sort By:
Swift Artificial Intelligence Software
View 16348 business solutionsBrowse free open source Swift Artificial Intelligence Software and projects below. Use the toggles on the left to filter open source Swift Artificial Intelligence Software by OS, license, language, programming language, and project status.
-
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.
-
$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.
-
1
Palmier Pro
macOS video editor built for AI
Palmier Pro is an open-source video editor for Mac built around AI-assisted video creation. It lets users and coding agents work together directly inside a timeline, blending traditional editing with generative workflows. The app is written from scratch in Swift and takes inspiration from professional editors like Premiere Pro while rethinking the workflow around AI. Users can generate videos and images inside the editor with models such as Seedance, Kling, and Nano Banana Pro. It also exposes an MCP server, so tools like Claude, Codex, and Cursor can interact with the project. The core editor, MCP server, and agent chat are open source, while generative AI processing remains closed source. It is designed specifically for macOS 26 on Apple Silicon. -
2
Enchanted
Enchanted is iOS and macOS app for chatting with language models
Enchanted is an open-source, cross-platform application built to let users chat with privately hosted large language models from Apple devices, including macOS, iOS, and visionOS. Designed to work seamlessly with servers like Ollama, it provides a privacy-focused alternative to traditional cloud AI UIs by connecting directly to your own LLM endpoints such as Llama, Mistral, Vicuna, and more. The interface resembles familiar commercial chat apps but emphasizes local control, offline capabilities, and multimodal support, making it ideal for users who want rich AI interaction without exposing sensitive prompts or conversations to third-party services. Enchanted enables features like voice prompts, image attachments, and markdown formatting within chats, giving flexibility for both casual and professional use. Built with attention to design and native Apple UI conventions, it aims to deliver consistent performance across devices while preserving powerful AI access. -
3
OpenAI
Swift community driven package for OpenAI public API
MacPaw OpenAI is a community-driven Swift SDK that provides developers with a structured and type-safe way to interact with the OpenAI API and compatible providers within Apple ecosystem applications. It simplifies the integration of AI capabilities into iOS, macOS, and other Swift-based applications by offering a clean abstraction over the underlying REST API, enabling developers to focus on functionality rather than low-level implementation details. The SDK supports a wide range of features including chat completions, embeddings, image generation, audio processing, and structured outputs, making it a comprehensive toolkit for building AI-powered applications. It also includes support for advanced features such as function calling, assistants, and tool integration through protocols like Model Context Protocol, enabling more complex and interactive AI workflows. -
4
Mochi Diffusion
Run Stable Diffusion on Mac natively
Run Stable Diffusion on Mac natively. This app uses Apple's Core ML Stable Diffusion implementation to achieve maximum performance and speed on Apple Silicon based Macs while reducing memory requirements. Extremely fast and memory efficient (~150MB with Neural Engine) Runs well on all Apple Silicon Macs by fully utilizing Neural Engine. Generate images locally and completely offline. Generate images based on an existing image (commonly known as Image2Image) Generated images are saved with prompt info inside EXIF metadata (view in Finder's Get Info window) Convert generated images to high resolution (using RealESRGAN) Autosave & restore images. Use custom Stable Diffusion Core ML models. No worries about pickled models. macOS native app using SwiftUI. -
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.
-
5
Generative AI Swift
This SDK is now deprecated, use the unified Firebase SDK
deprecated-generative-ai-swift is a Swift client and example scaffold for building generative AI apps using the Gemini models. Although marked “deprecated”, the repo demonstrates how to integrate Gemini inference into iOS and macOS apps via Swift APIs, providing boilerplate for prompt dispatching, streaming responses, UI integration, and error handling. It includes a sample app that showcases a chat interface, where users send messages and receive responses streamed in real time, with UI updates as tokens arrive. The code also handles request queuing, cancellation, and retry logic, giving developers a realistic foundation rather than a minimalist “hello world.” Despite its deprecated label, the repo remains valuable for developers who want to see how a native Swift integration might be structured before migrating to newer SDKs. Maintainability is emphasized: modular layers separate networking, prompt handling, and UI logic, making adaptation easier when switching to updated APIs. -
6
ClaudeBar
A macOS menu bar application that monitors AI coding assistant usage
ClaudeBar is a macOS menu bar utility that helps developers and power users monitor their AI coding assistant usage quotas from a lightweight system tray interface. Rather than constantly running CLI commands or navigating web dashboards, users can glance at their quota statistics for services like Claude, Codex, Gemini, GitHub Copilot, and Antigravity directly from the menu bar. The application provides real-time tracking of session, weekly, and model-specific usage percentages, using visual indicators such as color-coded progress bars to communicate when quotas are healthy, nearing limits, or depleted. It includes options to enable or disable monitoring for individual providers, supports multiple visual themes (including dark mode and a festive theme), and refreshes data at configurable intervals so users always have up-to-date information. -
7
VoiceInk
The best open-source alternative to Superwhisper & Wispr Flow
VoiceInk is a native macOS dictation application that converts speech into text almost instantly. It can process audio entirely on the device with local Whisper or Parakeet models, giving users a private offline workflow. Optional AI enhancement can clean up, rewrite, format, or adapt dictated text for different tasks. Modes apply different models, prompts, context settings, and shortcuts according to the active app or website. A personal dictionary improves recognition of names, technical terms, and recurring phrases, while configurable global shortcuts support toggle and push-to-talk recording. Context-aware tools can use selected text, clipboard content, or visible screen text to improve the final output. The app is written in Swift, supports macOS 14.4 or later, can be installed through Homebrew, and is available under the GPLv3 license. -
8
FluidVoice
Fastest macOS Offline Dictation app
FluidVoice is an open-source macOS dictation app that converts speech to text locally with optional AI enhancement. It is designed for fast, low-latency voice input across apps, with support for global hotkeys and direct text insertion. The app includes write mode for dictating or rewriting text in any text field and command mode for controlling Mac actions by voice. Its local enhancement layer can improve formatting, capitalization, and post-processing without sending data away from the Mac. FluidVoice supports multiple speech models so users can choose between speed, language coverage, and compatibility. It also includes live preview, history, usage stats, theming, menu bar access, and per-app configuration. -
9
apfel
Apple Intelligence from the command line
apfel is a lightweight and likely experimental development project focused on building efficient and minimal tools or frameworks, typically emphasizing simplicity, performance, and clean abstractions. The project appears to follow a philosophy of reducing unnecessary complexity while still enabling practical functionality for developers who prefer lean systems over heavy frameworks. It is designed to be adaptable, allowing developers to extend or modify its behavior depending on their specific use case. Apfel may include utilities or structural patterns that streamline development workflows, particularly in environments where speed and clarity are more important than feature richness. Its architecture likely avoids over-engineering, making it suitable for small projects, prototypes, or educational purposes. The project encourages direct interaction with code rather than relying on extensive abstraction layers, giving developers more control over implementation details. -
Demo Series - Small Business Backup By VeeamWatch this on-demand demo series and learn how to protect your Microsoft 365 data with clear, simple, actionable steps that are easy to implement for businesses of all sizes.
-
10
Clicky
AI teacher that lives as a buddy next to your cursor
Clicky is an experimental AI-powered desktop companion designed to act as an interactive, real-time teaching assistant that lives directly alongside the user’s cursor on macOS. It functions as a menu bar application that can observe the user’s screen, interpret context, and provide guidance through both voice and visual cues, effectively simulating the experience of having a human tutor sitting next to you. The system captures screenshots and combines them with voice input to send contextual queries to AI models, which then respond with both spoken explanations and on-screen visual pointers. One of its defining features is the ability to physically “point” at UI elements across multiple monitors using a cursor overlay, helping users navigate complex software step by step. The architecture includes integrations for speech-to-text, text-to-speech, and AI reasoning models, all routed securely through a proxy to protect API keys. -
11
MochiDiffusion
Run Stable Diffusion on Mac natively
MochiDiffusion is a native macOS application that allows users to run Stable Diffusion models locally, leveraging Apple Silicon GPU acceleration via Core ML. It offers users GUI controls for prompts and model configuration without needing Python or Docker, enabling offline image generation. -
12
Ollamac
Mac app for Ollama
Ollamac is an open-source native macOS application that provides a graphical interface for interacting with local large language models running through the Ollama inference framework. The project was created to simplify the process of using local AI models, which typically require command-line interaction, by offering a clean and intuitive desktop interface. Through this interface, users can run and chat with a variety of LLM models installed through Ollama directly on their own machines. The application focuses on delivering a lightweight and responsive experience that integrates seamlessly with the macOS ecosystem. Because the models run locally, the system enables private AI workflows without sending data to external APIs or cloud services. Ollamac supports different Ollama models and provides features designed to improve usability such as syntax highlighting and configurable settings. -
13
WhisperKit
On-device Speech Recognition for Apple Silicon
WhisperKit is a Swift package that integrates OpenAI's popular Whisper speech recognition model with Apple's CoreML framework for efficient, local inference on Apple devices. Whisper has pulled the future forward when fast, free and virtually error-free translation and transcription will be ubiquitous. It inspired numerous developers to improve and deploy it with minimal friction and maximum performance. We founded Argmax in November 2023 to empower developers and enterprises everywhere to deploy commercial-scale inference workloads on user devices. The fast-growing need for Whisper inference in production convinced us to take it on as our first project. -
14
fullmoon
Chat with private and local large language models
Fullmoon is a free, open-source application that enables users to interact with large language models directly on their devices, ensuring privacy and offline accessibility. Optimized for Apple silicon, it operates seamlessly across iOS, iPadOS, macOS, and visionOS platforms. Users can personalize the app by adjusting themes, fonts, and system prompts, and it integrates with Apple's Shortcuts for enhanced functionality. Fullmoon supports models like Llama-3.2-1B-Instruct-4bit and Llama-3.2-3B-Instruct-4bit, facilitating efficient on-device AI interactions without the need for an internet connection. -
15
Cheetah
AI macOS app for real-time coding interview coaching assistance
Cheetah is an AI-powered macOS application designed to assist users during software engineering interview practice through real-time coaching capabilities. It integrates audio transcription and AI-generated responses to help users navigate technical interview questions as they happen. Cheetah uses a local speech-to-text engine based on Whisper to capture and transcribe conversations in real time, enabling it to understand interviewer prompts. It then leverages language models to generate suggested answers, refinements, or explanations tailored to the ongoing discussion. Cheetah also connects with live coding environments through a browser extension, allowing it to analyze code and logs directly from supported platforms. Cheetah provides simple controls for generating answers, refining responses, and analyzing technical output, making it interactive during mock interviews. -
16
LLM.swift
LLM.swift is a simple and readable library
LLM.swift is a Swift package that enables developers to run Large Language Models (LLMs) directly on Apple devices, including iOS, macOS, and watchOS. By leveraging Apple's hardware and software optimizations, LLM.swift facilitates on-device natural language processing tasks, ensuring user privacy and reducing latency associated with cloud-based solutions. -
17
Quotio
Stop juggling AI accounts. Quotio is a beautiful native macOS menu bar
Quotio is a native macOS menu bar application designed to unify and manage multiple AI service accounts and quota usage in one consolidated interface. It works alongside a local proxy server (CLIProxyAPI) and helps developers who use various AI coding assistants such as Claude, Gemini, OpenAI Codex, Qwen, and others — avoiding the hassle of juggling tokens, keys, and rate limits across different providers. Through real-time dashboard views, users can monitor request traffic, token consumption, and success rates, and set smart auto-failover strategies so that services switch automatically when one provider’s quota is exhausted. Quotio simplifies setup with one-click agent configuration, menu bar access to server status, and notifications for low quotas or connection issues. While targeted at developers with CLI-based AI tools, its visually clear UI and quota tracking make it a useful utility for anyone working with multiple AI APIs on macOS. -
18
ImagePicker
Reinventing the way ImagePicker works
ImagePicker is an all-in-one camera solution for your iOS app. It lets your users select images from the library and take pictures at the same time. As a developer you get notified of all the user interactions and get the beautiful UI for free, out of the box, it's just that simple. ImagePicker has been optimized to give a great user experience, it passes around referenced images instead of the image itself which makes it less memory-consuming. This is what makes it smooth as butter. ImagePicker works with referenced images, that is really powerful because it lets you download the asset and choose the size you want. If you want to change the default implementation, just add a variable in your controller. -
19
Nativ
Chat, serve, monitor, and connect MLX models from one macOS app
Nativ is a native macOS workspace for running AI models locally on Apple silicon. It combines private chat, model management, image generation, voice tools, monitoring, and local inference serving in one SwiftUI application. The app discovers compatible MLX models in the Hugging Face cache and can download additional models with memory-fit warnings. Conversations support streaming responses, images, reasoning output, persistent history, and performance metrics. Nativ exposes OpenAI- and Anthropic-compatible APIs so local models can power editors, coding agents, and other software. It also provides system monitoring, scheduled routines, MCP tools, advanced inference controls, and an extension platform for additional local capabilities. -
20
iMCP
A macOS app that provides an MCP server to your Messages
iMCP is a native macOS application that exposes personal Apple services to AI clients through the Model Context Protocol. It can provide controlled access to Calendar, Contacts, Location, Maps, Messages, Reminders, and Weather. The menu bar interface lets users enable individual services and approve the required macOS permissions. A bundled command-line server communicates over standard input and output with clients such as Claude Desktop, Claude Code, Cursor, and Amp. Calendar and reminder tools can create items, while other tools support searches, directions, travel estimates, message history, and current conditions. The app itself does not collect or store user data, although connected AI clients may send tool results off device. It requires macOS 15.3 or later and can be installed directly or through Homebrew. -
21
GitHub Copilot for Xcode
AI coding assistant for Xcode
Copilot for Xcode brings GitHub Copilot’s AI-driven code suggestions directly into Apple’s Xcode IDE, giving iOS and macOS developers predictive completions, context-aware recommendations, and natural language assistance while they write Swift, Objective-C, and related code. It embeds seamlessly into the Xcode editor UI, offering completions as you type, including full lines or blocks of code derived from surrounding context and doc comments. Because the integration understands the structure of Xcode-based projects and Apple’s frameworks, suggestions are often tailored to platform idioms, APIs, and patterns used in Cocoa, UIKit, SwiftUI, and more. It also supports natural language prompts, letting developers ask for example code or explanations inline without leaving the IDE. The extension is designed to respect privacy and project scope, giving users control over when Copilot suggestions are enabled and how telemetry is shared. -
22
TurboFieldfare
Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook
TurboFieldfare is a custom Swift and Metal runtime for running the instruction-tuned Gemma 4 26B-A4B model on Apple Silicon Macs with limited memory. Instead of loading the entire model, it keeps the shared core and KV cache in RAM while streaming only the routed experts required for each token from SSD. This approach reduces active memory use to roughly 2 GB while the installed model occupies about 14.3 GB of storage. The project includes a native Mac application, command-line tools, a streaming installer, a Swift library, and an experimental OpenAI-compatible local server. Quantized weights, custom Metal kernels, chunked prefill, and a bounded expert cache improve efficiency. The installer downloads and repacks model ranges without staging a second full checkpoint. Its current scope is text-only Gemma inference on macOS 26 and Apple Silicon hardware. -
23
CodexBar
Show usage stats for OpenAI Codex and Claude Code
CodexBar is a lightweight macOS utility that displays real-time usage statistics for AI coding tools such as OpenAI Codex and Claude Code directly from the system menu bar. The application is designed to give developers quick visibility into token consumption and activity without requiring them to open web dashboards or log into provider portals. Built in Swift with a native macOS interface, it integrates seamlessly into the desktop environment and emphasizes minimal overhead. The tool is particularly useful for monitoring usage limits, managing costs, and keeping track of AI-assisted development sessions. CodexBar focuses on simplicity and fast feedback, presenting key metrics in an always-accessible format. Overall, it functions as a convenient observability companion for developers who rely heavily on AI coding assistants. -
24
NSFWDetector
A NSFW detector with CoreML
NSFWDetector is a small (17 kB) CoreML Model to scan images for nudity. It was trained using CreateML to distinguish between porn/nudity and appropriate pictures. With the main focus on distinguishing between Instagram model-like pictures and porn. -
25
OpenAI DALL·E AsyncImage SwiftUI
OpenAI swift async text to image for SwiftUI app using OpenAI
SwiftUI views that asynchronously loads and displays an OpenAI image from open API. You just type in your idea and AI will give you an art solution. DALL-E and DALL-E 2 are deep learning models developed by OpenAI to generate digital images from natural language descriptions, called "prompts". You need to have Xcode 13 installed in order to have access to Documentation Compiler (DocC) OpenAI's text-to-image model DALL-E 2 is a recent example of diffusion models. It uses diffusion models for both the model's prior (which produces an image embedding given a text caption) and the decoder that generates the final image. In machine learning, diffusion models, also known as diffusion probabilistic models, are a class of latent variable models. They are Markov chains trained using variational inference. The goal of diffusion models is to learn the latent structure of a dataset by modeling the way in which data points diffuse through the latent space.
