Stars
Using system APIs directly with adb/root privileges from normal apps through a Java process started with app_process.
识别旋转验证码（如百度）的图片旋转度数，可用于辅助机器通过旋转验证码验证。
AI模型聚合管理中转分发系统，一个应用管理您的所有AI模型，支持将多种大模型转为统一格式调用，支持OpenAI、Claude、Gemini等格式，可供个人或者企业内部管理与分发渠道使用。🍥 The next-generation LLM gateway and AI asset management system supports multiple languages.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
✨🌟✨ my stars list, thx for https://github.com/maguowei/starred 😘
Python Socket.IO server and client
AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.
🚗 个人做过的技术分享... ( topic: 高性能架构, 中间件原理实践，云原生，Golang 等)
Enterprise-ready MCP Gateway & Registry — unify AI development tools with secure OAuth, dynamic tool discovery, and seamless access for both autonomous agents and coding assistants.
Self-hosted MCP Gateway and Registry for AI agents
A Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
AgentScope: Agent-Oriented Programming for Building LLM Applications
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
Implementation of Nougat Neural Optical Understanding for Academic Documents
MS-Agent: Lightweight Framework for Empowering Agents with Autonomous Exploration in Complex Task Scenarios
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, …
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & TIS & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
A simple screen parsing tool towards pure vision based GUI agent
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
A lightweight LMM-based Document Parsing Model
Multilingual Document Layout Parsing in a Single Vision-Language Model
100+ Fine-tuning Tutorial Notebooks on Google Colab, Kaggle and more.