Starred repositories
A simple and easy-to-use MCP Host CLI Tool
Aggregate MCP servers & apply middlewares; host & emit unified MCP servers out
Self-Hosted Plaform for Secure Execution of Untrusted User/AI Code
MemoRizz: A Python library serving as a memory layer for AI applications. Leverages popular databases and storage solutions to optimize memory usage. Provides utility classes and methods for effici…
🤯 Lobe Chat - an open-source, modern design AI chat framework. Supports multiple AI providers (OpenAI / Claude 4 / Gemini / DeepSeek / Ollama / Qwen), Knowledge Base (file upload / knowledge manage…
OCRFlux is a lightweight yet powerful multimodal toolkit that significantly advances PDF-to-Markdown conversion, excelling in complex layout handling, complicated table parsing and cross-page conte…
GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.
ManimML is a project focused on providing animations and visualizations of common machine learning concepts with the Manim Community Library.
Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
Copilot Chat extension for VS Code
LostRuins / koboldcpp
Forked from ggml-org/llama.cppRun GGUF models easily with a KoboldAI UI. One File. Zero Install.
The proxy server for AI-native apps. Arch handles the pesky low-level work in building agents like clariyfing vague user input, routing prompts to the right agents and unifying access to any LLM - …
A powerful coding agent toolkit providing semantic retrieval and editing capabilities ( B76D MCP server & Agno integration)
Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models (CVPR 2024 Highlight)
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.
The entrance repository of Markdown presentation ecosystem
A web app for creating flexible layouts with the power of CSS Flexbox.
A powerful AI coding agent. Built for the terminal.
拼好RAG：手搓并融合了GraphRAG、LightRAG、Neo4j-llm-graph-builder进行知识图谱构建以及搜索；整合DeepSearch技术实现私域RAG的推理；自制针对GraphRAG的评估框架| Integrate GraphRAG, LightRAG, and Neo4j-llm-graph-builder for knowledge graph construct…
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Easy-to-use, high-performance, multi-platform inference deployment framework
From Images to High-Fidelity 3D Assets with Production-Ready PBR Material