Explore the directory

A command-line tool that converts documentation sites, GitHub repositories, PDFs, videos, notebooks and other sources into structured knowledge packages for AI skills, RAG pipelines and coding assistants.

• RAG
• CLI tools

A personal, community-sourced collection of study notes and real interview questions about large language models, covering fundamentals, architecture, training, fine-tuning, inference, RLHF, retrieval-augmented generation and evaluation.

• Tutorials
• Books

A TypeScript pattern-matching library that lets code express complex conditional logic as a single expression, with type inference and compile-time exhaustiveness checking.

• Libraries

A curated list of Claude Skills and related tools for customizing Claude's workflows, including official document, design and development skills plus guidance on installing and building them.

• Agent skills
• Curated lists

An open-source, self-hosted status page system for publishing service status to users, built on PHP and Laravel with a rebuild underway for its 3.x release.

• Monitoring

A local-first knowledge system for Claude Code and other Agent Skills hosts that turns source material into linked, source-cited Obsidian notes, with workflows for research, retrieval and vault maintenance.

• Agent skills
• Agent memory

A multiplayer AI agent harness for a company's Slack and web workspace, giving each employee and each room its own scoped memory, files, permissions and sandbox while sharing one underlying agent core across any supported model or harness.

• Agent frameworks
• Agent memory

A self-hosted platform that puts SSH terminals, remote desktop, file transfers, tunnels, Docker management and server metrics in one web, desktop and mobile app, positioned as a free alternative to Termius.

• Terminals
• Monitoring

An open-source Docker Compose template, curated by n8n, that quickly sets up a local, low-code AI development environment with a workflow platform, a local LLM runner, a vector store and a database.

• Containers
• Workflow automation

A web GUI for ChatGPT and many other large language models, adding chat history management, file-based question answering, agent tools, web search and GPT fine-tuning on top of a range of hosted and locally deployed models.

• Inference

An open platform that builds a unified metadata knowledge graph across an organization's data, connecting lineage, ownership, quality, glossaries and data contracts so both people and AI agents can discover, trust and use data correctly.

• Data engineering

A curated list of creative-coding resources for beginners and intermediates, covering generative art, data visualization and interaction design across books, frameworks, courses and communities.

• Curated lists

An open-source desktop application for running a local, multi-agent AI workforce, built on the CAMEL-AI framework, as a self-hosted alternative to closed cowork agent products.

• Agent frameworks

An Obsidian plugin that embeds AI coding agents such as Claude Code, Codex, Grok and OpenCode as a collaborator inside a user's vault, with file read and write access, search, a shell and multi-step workflows over the vault's notes.

• Coding agents

A JavaScript library that transpiles ordinary functions into shader code so they run accelerated on the GPU in the browser or Node, falling back to plain JavaScript when no GPU is available.

• Libraries

An open-source library and MCP server that turns PDFs, Word documents, HTML, images and other unstructured files into clean, structured data ready for language models, vector databases and other downstream processing.

• MCP servers
• RAG

A general-purpose, secure sandbox platform for AI applications, giving coding agents, GUI agents and code-execution workloads an isolated place to run with the same API from a laptop to a large cluster.

• Containers

An autonomous penetration-testing agent that drives Claude Code or Codex through staged reconnaissance, exploitation and reporting phases for security assessments and capture-the-flag challenges.

• Security

A lightweight, from-scratch reimplementation of vLLM in about 1,200 lines of Python, offering comparable offline inference throughput with prefix caching, tensor parallelism and CUDA graphs.

• Inference

A large model and multimodal model fine-tuning and deployment framework from the ModelScope community, supporting training, inference, evaluation, quantization and deployment for more than 600 text and 400 multimodal models.

• Models
• Inference

An open-source AI Development Environment that turns a code editor into a place to build, debug and deploy LLM and machine learning pipelines, running on a multithreaded C++ engine with any model, tool or framework.

• Models
• Data engineering

A Docker image that runs Android emulators for app development, testing and automation, with noVNC access, adb control from outside the container, and beta support for an MCP server and AI agents.

• Testing
• Containers

A Python library that guarantees structured output from a language model during generation itself, by specifying a desired output type such as a Python literal, an integer or a Pydantic model, rather than parsing or fixing the output afterward.

• Libraries

A curated collection of 132 example projects, tutorials and recipes for building LLM-powered applications, covering starter agents, voice agents, MCP-backed tools, memory agents, RAG applications and fine-tuning across many agent frameworks.

• Tutorials
• Curated lists