Explore the directory

A virtual terminal for AI agents that mounts services such as S3, Google Drive, Slack and Gmail as one filesystem, provides virtualized command-line tools, and gates what an agent can run or see through a policy engine.

• Agent frameworks

The complete materials for the book Agentic Design Patterns by Antonio Gulli, covering 21 chapters and 7 appendices on building AI agent systems, with accompanying code notebooks for hands-on learning.

• Tutorials
• Books

A Rust implementation of the age file encryption format, providing a simple command-line tool and library with small explicit keys and no configuration options.

• CLI tools
• Security

An independent, educational deep dive into Claude Code's internal architecture, based on analysis of a leaked source snapshot, covering its agent loop, context compression, streaming and safety design.

• Coding agents
• Books

A self-directed learning drill of methods, processes and systems for AI and data engineering, covering a path from foundational tools through machine learning, large language models, retrieval-augmented generation, fine-tuning and autonomous agents.

• Tutorials

An open-source, AI-native backend-as-a-service combining a Postgres data plane, auth, storage, serverless functions, an AI/LLM gateway and a built-in MCP server so agents can operate the backend with tools instead of glue code.

• MCP servers
• Backend

A daily-updated Chinese-language collection of AI and machine learning engineering articles, drawn from major technology companies' engineering blogs, research labs and technical communities, plus a curated AI product directory.

• Curated lists

A small, SMP-aware embedded operating system kernel ported to many CPU architectures, used as the bootloader in numerous Android phones.

• Libraries

An open-source skill-based memory layer for AI agents that automatically captures what an agent learns from its runs and stores it as readable, editable agent skill files shared across agents and frameworks.

• Agent skills
• Agent memory

A collaborative multi-agent coding workspace that aggregates sessions from Claude Code, Codex, OpenCode, Pi, Grok Build and other agent CLIs into one searchable place and lets them delegate work to each other.

• Coding agents

A completion-discipline skill for AI coding agents that requires writing an acceptance checklist before substantial work, running and reverifying its checks, and reporting only what the evidence supports.

• Agent skills

A customizable web chat component that can be added to a site with one line of code, connecting to more than 20 AI APIs or a custom backend, with file, audio and speech support.

• UI kits

The official Java SDK for the Model Context Protocol, enabling Java applications to build MCP clients and servers with synchronous or asynchronous communication, and extended by Spring AI's MCP integration.

• MCP servers

A curated collection of practical, complete AI project examples spanning OCR, retrieval-augmented generation, multi-agent systems and other AI use cases, with full code and setup instructions for each.

• Tutorials

A command-line power tool and workflow manager for talking to ChatGPT and other LLMs from the terminal, with a plugin architecture, multiple provider support and Ansible-based workflow integration.

• CLI tools
• Workflow automation

A catalog and shared engineering foundation for Microsoft's official Model Context Protocol server implementations, currently covering Azure and Microsoft Fabric, giving AI applications standardized access to Microsoft's data and tools.

• MCP servers

FastDeploy is a PaddlePaddle-based inference and deployment toolkit for large language models and vision-language models, with an OpenAI-compatible API service and support for several accelerator families.

• Inference

A set of guidelines that helps AI coding agents write modern, idiomatic Go by detecting a project's Go version and preferring newer language features and standard-library additions over older patterns.

• Agent skills
• Languages

Browserbase's official collection of Agent Skills that let Claude Code drive real or cloud browser sessions, capture traces, generate WebMCP tools and test web applications.

• Agent skills
• Browser automation

A terminal window manager and multiplexer with tiling panes, persistent sessions and awareness of the coding agents running inside it, unifying their status into one inbox.

• Terminals

A proxy server that lets Anthropic clients such as Claude Code send requests to Gemini or OpenAI models, or to Anthropic itself, by translating between the Anthropic API and each provider through LiteLLM.

• LLM gateways

A C++ and Python library implementing fast rigid body dynamics algorithms and their analytical derivatives, used in robotics, biomechanics, and physics simulation.

• Libraries

A plugin that adds an editable code editor, an enhanced file tree, a Git panel, task management and a side chat to DSH's sidebar, and exposes a service API for other plugins to register their own tabs and file viewers.

• Coding agents
• Editors

An open-source, self-hostable platform that connects AI agents and assistants to a company's business systems, providing permission-aware search and cited answers over Slack, Google Drive, GitHub, Notion and more.

• RAG