Explore the directory

A hands-on notebook series that teaches Retrieval-Augmented Generation from an introductory setup through advanced techniques such as multi-querying, logical and semantic routing, and custom RAG pipeline construction.

• RAG
• Tutorials

A Visual Studio 2022 extension, built on a Language Server Protocol backend, that adds assembly-language syntax highlighting, code completion, and signature help for x86, x64, and AVX-512 code.

• Editors

A curated list of articles, playbooks, benchmarks, specifications, and open-source projects for harness engineering: shaping the environment around AI agents so they work reliably.

• AI evals
• Curated lists

A tiny, fast, fully open-source HTML5 game engine with 2D and 3D rendering, physics, particles, sound, and input handling in a small footprint.

• Libraries

The official repository for Alibaba's Qwen3.8 large language model, which brings a top-tier Qwen-Max-class model to open release, with stronger coding, professional-work, research and long-horizon agentic performance.

• Models

A collection of reference workflows, tutorials and sample applications for building generative-AI systems, such as retrieval-augmented generation pipelines and agentic workflows, optimized for NVIDIA's accelerated software stack.

• Tutorials

A Model Context Protocol server that lets an AI agent create, read and modify Excel workbooks, including formulas, formatting, charts, pivot tables and data validation, without Microsoft Excel installed.

• MCP servers

An Agent Skill that runs Claude Design locally inside Cursor, Claude Code, or another file-capable coding agent, producing UI mockups, prototypes, wireframes, and decks as self-contained HTML.

• Agent skills
• Design tools

A structured multi-perspective deliberation tool for hard decisions, assigning a question to independent analytical personas that must disagree directly before returning a verdict with dissent, kill criteria and a next action.

• Agent skills

A modular Agentic RAG tutorial and project template built with LangGraph, demonstrating hierarchical retrieval, conversation memory, query clarification and multi-agent orchestration for retrieval-augmented generation.

• RAG
• Tutorials

A Codex agent skill that turns a natural-language description into game-ready 2D sprite sheets, layered tile maps and engine-ready prototypes for Godot or Unity, combining generated art with deterministic cleanup scripts.

• Agent skills
• Generative media

A Python library, built on Hugging Face Transformers, that trains and evaluates a range of NLP models in as little as three lines of code, covering classification, question answering, retrieval and generation tasks.

• Models
• Libraries

An open-source research decision layer for agent-to-agent networks that decides, mid-task, whether an in-flight piece of work should continue with the current agent, recruit collaborators, or hand off to a specialist.

• Agent frameworks

MongoDB's collection of example notebooks, sample applications and workshops covering retrieval-augmented generation, AI agents and industry-specific generative-AI use cases, with MongoDB acting as vector store, operational database and memory provider.

• Tutorials

A Python static-site generator for interactive data apps that bundles compute, data access, and UI into a single offline-capable HTML file using Pyodide, DuckDB, Pandas, and Plotly.

• Web frameworks
• Data engineering

A 15-chapter Chinese-language technical book that reverse-engineers Claude Code's architecture, covering its conversation loop, tool system, permission pipeline, memory, context management, sub-agents and MCP integration.

• Coding agents
• Books

A free, open-source macOS menu bar app that tracks usage, credits, and spend across AI coding subscriptions such as Claude, Codex, Cursor, Copilot, and OpenRouter.

• Desktop utilities

A Claude and Codex Agent SDK skill that runs many isolated, differently framed reasoning branches in parallel, then scores, prunes and deepens them, aimed at open-ended design and brainstorming prompts.

• Agent skills

A visualization intermediate language that lets AI agents turn a compact, human-editable chart specification into a polished chart, compiling one input to Vega-Lite, ECharts, Chart.js, Plotly or native Excel output.

• Libraries

A lightweight, Python-based inference and serving framework for large language models, built to be easy to scale and extend by drawing on techniques from FasterTransformer, TGI, vLLM and FlashAttention.

• Inference

An OpenAI API-compatible inference proxy that applies more than 20 published inference-time techniques, such as mixture-of-agents and Monte Carlo tree search, to improve LLM accuracy on reasoning tasks without retraining.

• Inference

An open-source, enterprise AI platform that combines a chat interface for non-technical users, an LLM and MCP gateway for developers, and guardrails, observability and identity management, built on SSO, RBAC and sandboxed execution.

• MCP servers
• LLM gateways

A compact, single-header similarity search and clustering engine for vectors and arbitrary objects, with bindings in eleven languages and support for user-defined distance metrics.

• RAG
• Databases

A set of Model Context Protocol servers that let an MCP client, such as Cursor or Claude, read Cloudflare account configuration, make suggestions, and apply changes across Cloudflare's application, security and performance services using natural language.

• MCP servers