Explore the directory

A curated, community-submitted list of Model Context Protocol servers, including reference servers that demonstrate the TypeScript and Python SDKs and official servers maintained by companies for their own platforms.

• MCP servers
• Curated lists

A red-teaming and offensive-security knowledge base with cheat sheets, tools, and tips for reconnaissance, vulnerability research, exploitation, and both offensive and defensive operations.

• Security
• Curated lists

A private, local, markdown-first WYSIWYG editor with built-in AI editing, designed for knowledge bases, LLM wikis, specs and notes, integrated with harnesses such as Claude, Codex and OpenCode.

• Editors
• Documentation tools

An AI-powered game-development assistant for the Unity Editor and runtime, connecting agents such as Claude, Cursor and Windsurf to Unity through MCP tools and generated skills, including inside a compiled, running game.

• MCP servers

A collection of technical resources, including complete example applications, that help developers build AI applications, agents and systems using Oracle AI Database and Oracle Cloud Infrastructure services.

• Tutorials

A simple proxy that exposes any MCP server's tools as a standard, secure OpenAPI-compatible HTTP server, so they work with tools, SDKs and UIs that expect REST APIs instead of raw MCP transport.

• MCP servers
• APIs

A high-performance, in-memory graph database, compatible with Neo4j's Cypher, combining built-in vector and text indexes with graph traversal for GraphRAG, AI agent memory, and real-time graph analytics.

• Databases

A Chinese-language, hands-on tutorial that builds large language models from scratch, starting from a GPT-style model and extending into architecture walkthroughs of GLM4, Llama3 and RWKV6.

• Tutorials

A fast, lightweight x86 and x86-64 disassembler and code generation library with no dynamic memory allocation and no third-party dependencies, used by projects such as x64dbg and Firefox.

• Debugging
• Libraries

A Model Context Protocol server, built on the AntV visualization library, that exposes tools for generating more than 26 chart and diagram types for chart generation and data analysis.

• MCP servers

A free, open-source AI coding assistant for enterprises, with a strict mode for standardized, requirements-driven code generation, repository-wide AI code review, and private, self-hosted deployment.

• Coding agents
• Editors

A modular, extensible open-source agent framework for long-running tasks, combining models, tools, skills and sub-agents behind a customizable harness that manages planning, context, permissions and execution feedback.

• Agent frameworks

A minimalist, self-hosted, WakaTime-compatible backend that collects coding statistics by project, language, editor, host, and operating system, with badges and weekly email reports.

• Monitoring

An open-source evaluation toolkit for large vision-language models, supporting one-command evaluation across more than 220 models and 80 benchmarks with generation-based scoring.

• AI evals

A Ruby-native AI framework, for plain Ruby or Rails, offering chats, tools, agents, image and video generation, embeddings, reranking, transcription, speech and OCR through one consistent API across 19 model providers.

• Agent frameworks

A Chinese-language collection of 50 verified real-world use cases for OpenClaw, a self-hosted personal AI agent, spanning platform bots, content creation, research and monitoring, office work, and personal-assistant setups.

• Agent frameworks
• Curated lists

A free, open-source personal AI agent that runs in any terminal, including SSH sessions, tmux and CI pipelines, with built-in shell, Python, web and vision tools, and a choice of hosted or local models.

• Coding agents

A collection of optimized, pre-trained deep-learning models and demo applications for the OpenVINO Toolkit, intended to speed up development of high-performance inference applications instead of training models from scratch.

• Models
• Inference

A distributed SQL database, compatible with PostgreSQL and built on Lucene, for storing and analyzing large amounts of data in near real time, including time series and IoT data.

• Databases

A collection of small, composable skills that add capabilities to a coding agent, including PR review and shipping workflows, visual planning and editing tools, and utilities for managing usage limits and context.

• Agent skills

An open, still-evolving curriculum that bridges basic reinforcement-learning concepts to LLM alignment, RLVR and agentic RL, with reproducible experiment code and browser-runnable training notebooks.

• Tutorials

A LanceDB-backed long-term memory plugin for OpenClaw agents that auto-captures preferences, decisions, and project context, then recalls them with hybrid vector and keyword search.

• Agent memory
• RAG

A database with a strongly-typed, polymorphic data model and a declarative query language called TypeQL that unifies relational, document, and graph modeling in one schema.

• Databases

A Microsoft research initiative on fundamental technology for building AI products with large language and multimodal models, covering prompt optimization, long context, alignment, faster inference and domain adaptation.

• Models
• Papers