A Swift client library for interacting with Ollama. Supports structured outputs, tool use, and vision models.

Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! 🦥

LLM.swift is a simple and readable library that allows you to interact with large language models locally with ease for macOS, iOS, watchOS, tvOS, and visionOS.

llama and other large language models on iOS and MacOS offline using GGML library.

Simple, unified interface to multiple Generative AI providers

NanoGPT (124M) in 3 minutes

Examples with SwiftUI that showcase various interactions, animations and more

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

🧡 Follow everything in one place

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

Window peeking for macOS

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。

open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.

Audio super resolution using neural networks

Unified framework for building enterprise RAG pipelines with small, specialized models

A collection of examples that show how to use CrewAI framework to automate workflows.

订阅人数最多的rss源，中文优质rss源

Speex audio processing library - THIS IS A MIRROR, DEVELOPMENT HAPPENS AT https://gitlab.xiph.org/xiph/speexdsp

Automatic tiling window manager for macOS à la xmonad.

Move and resize windows on macOS with keyboard shortcuts and snap areas

The Memory layer for AI Agents

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Aurora Editor is a IDE built by the community, for the community, and written in Swift for the best native performance and feel for macOS.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

🙌 OpenHands: Code Less, Make More

NVActivityIndicatorView implemented in SwiftUI

A self-hostable bookmark-everything app (links, notes and images) with AI-based automatic tagging and full text search