Stars
Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
Open-source, community-driven agent harness
Huashu Design · HTML-native design skill for Claude Code · Claude Code 里 HTML 原生的设计 skill · 高保真原型 / 幻灯片 / 动画 + 20 设计哲学 + 5 维评审 + MP4 导出 · Agent-agnostic
An agentic skills framework & software development methodology that works.
An open-source AI agent that brings the power of Gemini directly into your terminal.
这是一个简单的技术科普教程项目，主要聚焦于解释一些有趣的，前沿的技术概念和原理。每篇文章都力求在 5 分钟内阅读完成。
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without …
Collection of notebook guides created by the Brev.dev team!
SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.
Low-code framework for building custom LLMs, neural networks, and other AI models
A collection of GPT system prompts and various prompt injection/leaking knowledge.
Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment
Official repository for LongChat and LongEval
A large-scale 7B pretraining language model developed by BaiChuan-Inc.
Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive arch…
A GPT-4 AI Tutor Prompt for customizable personalized learning experiences.
Home of StarCoder: fine-tuning & inference!
LlamaIndex is the leading document agent and OCR platform
The official gpt4free repository | various collection of powerful language models | opus 4.6 gpt 5.3 kimi 2.5 deepseek v3.2 gemini 3
A llama.cpp drop-in replacement for OpenAI's GPT endpoints, allowing GPT-powered apps to run off local llama.cpp models instead of OpenAI.
We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts…
JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.