Explore the directory

A self-hosted web interface for configuring and managing Nginx, adding online server statistics, automatic configuration backups, multi-server cluster management, and an MCP endpoint.

• Networking

An AI agent skill, usable unchanged in Codex and Claude Code, that turns natural-language descriptions into geometry-checked SVG technical diagrams, PNG exports, SVG-to-GIF motion and interactive HTML.

• Agent skills
• Design tools

A memory operating system for LLMs and AI agents that unifies storing, retrieving and managing long-term memory as an inspectable graph, with multimodal support and plugins for several agent runtimes.

• Agent memory

An incremental data-indexing engine that keeps context such as codebases, meeting notes, inboxes, Slack, PDFs and video continuously fresh for AI agents and LLM apps, recomputing only what changed.

• Agent memory
• RAG

A multi-core-friendly C++ rigid-body physics and collision-detection library for games and VR, built for deterministic simulation and used in shipped titles such as Horizon Forbidden West.

• Libraries

An open-source AI observability and evaluation platform for tracing, evaluating and troubleshooting LLM applications, with an integrated debugging agent and a remote MCP server for querying traces.

• MCP servers
• AI evals

The official Vim and Neovim plugin for GitHub Copilot, turning comments and method names into inline code suggestions that can be accepted with a keypress.

• Coding agents
• Editors

A continuously updated, Chinese-language curated guide to ChatGPT and frontier AI, covering prompt engineering, application development, DeepSeek, Claude Skills, MCP, coding agents and browser automation.

• Curated lists

A Codex-native distribution of the Academic Research Skills suite, packaging deep-research, paper-writing and peer-review workflows as a single installable skill for OpenAI's Codex.

• Agent skills

A Python library of neural networks for image semantic segmentation built on PyTorch, with a two-line high-level API, 12 architectures and more than 800 pretrained encoders.

• Libraries

A collection of PyTorch Jupyter notebook demos showing how to use Hugging Face's Transformers library across many model architectures, from BERT and DETR to CLIPSeg, DPT and Donut.

• Tutorials

A declarative deep-learning framework, hosted by the Linux Foundation, for training, fine-tuning and deploying large language models and other AI models from a YAML configuration file instead of custom code.

• Models

A component-driven C++ framework from NASA's Jet Propulsion Laboratory for building flight software and other embedded applications, with modeling tools that generate code and a bootstrapping CLI.

• Libraries

An open-source PyTorch toolkit for conversational AI, covering speech recognition, speaker recognition, speech enhancement and separation, and language modeling, with more than 200 training recipes.

• Speech

A key-value cache management layer for scalable LLM inference that turns transient KV cache into reusable, shareable state across serving engines, cutting time-to-first-token and improving throughput.

• Inference

An open-source, enterprise-focused LLM application DevOps platform combining a visual generative-AI workflow builder, retrieval-augmented generation, agents, model management, evaluation and fine-tuning.

• Agent frameworks
• RAG

An early-stage, declarative orchestration runtime from Google for running billions of autonomous agent workloads across a cluster, sandboxing each task on top of a separate 'Agent Substrate' layer.

• Agent frameworks
• Containers

A Codex Skill that turns a Chinese-language article's core judgment, process or metaphor into a single white-background, hand-drawn 16:9 illustration featuring a recurring character called Xiaohei.

• Agent skills
• Generative media

An MCP server that lets AI agents such as Claude, GPT and Copilot autonomously run more than 150 cybersecurity tools for automated penetration testing, vulnerability discovery and bug-bounty work.

• MCP servers
• Security

A free, self-hosted PHP URL shortener that gives full control over your own domain, statistics and plugin-based extensions.

• Backend

A one-stop retrieval toolkit for search and retrieval-augmented generation, providing a family of open embedding, reranking and multimodal-search models known as BGE.

• RAG
• Models

A ranking of GitHub repositories by how often they have been starred and forked, refreshed automatically once a day, broken out overall and by programming language.

• Curated lists

An open-source, bilingual Chinese-English conversational language model with tool-calling support, developed by Fudan University, including model weights, dialogue training data, and deployment and fine-tuning code.

• Models

A command-line productivity tool that uses a large language model to generate shell commands, code snippets and documentation directly in the terminal, accepting piped input from other commands.

• CLI tools