#
Starred repositories
An open protocol enabling communication and interoperability between opaque agentic applications.
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
Agent S: an open agentic framework that uses computers like a human
This open-source curriculum is designed to teach the concepts and fundamentals of the Model Context Protocol (MCP), with practical examples in .NET, Java, TypeScript, JavaScript and Python.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Integrate cutting-edge LLM technology quickly and easily into your apps
Memory for AI Agents; Announcing OpenMemory MCP - local and secure memory management.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.
real time face swap and one-click video deepfake with only a single image
21 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/
PlayStation 4 emulator for Windows, Linux and macOS written in C++
Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.
Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.
11 Lessons to Get Started Building AI Agents
Production-ready platform for agentic workflow development.
Fully local web research and report writing assistant
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.
mrmans0n / compose-rules
Forked from twitter/compose-rulesLint rules for ktlint/detekt aimed to contribute to a healthier usage of Compose. Actively maintained and evolved fork of the Twitter Compose rules.
Static checks to aid with a healthy adoption of Compose
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
A simple screen parsing tool towards pure vision based GUI agent
Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。
MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/READ…
A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!