Explore the directory

A free, hands-on cohort course teaching developers to build, test, deploy and audit software with AI coding tools while keeping engineering discipline.

• Tutorials

A curated list of tools, papers, articles and communities for understanding how large language models work internally.

• Curated lists

A curated academic collection of jailbreak attack and defense research on large and vision-language models, with papers, code, datasets and evaluations.

• Security
• Curated lists

A short, freely available introduction to reinforcement learning, from the basics through applied algorithms, with a PyTorch implementation of each algorithm covered and supplementary proofs for the dynamic-programming material.

• Books

A local-first, cross-device desktop AI agent that remembers context across sessions, pursues long-running goals in the background, and can generate designs, documents and code changes.

• Coding agents

An AI-powered OSINT agent for authorized security research, with twenty investigation tools behind a natural-language interface and an MCP server so any compatible AI client can drive them.

• Security

A Python runtime framework for building GenAI application backends with structured outputs, observable actions, reusable skills and Model Context Protocol support.

• Agent frameworks

A bootstrapping script that turns a fresh Ubuntu or Arch server into a fully configured, multi-agent AI coding environment in about thirty minutes.

• Coding agents
• CLI tools

A curated marketplace plugin of skills, sub-agents and configuration templates for Claude Code, adding deep research, image generation and GitHub automation with multi-model switching.

• Agent skills

A collection of React Native skills for AI coding assistants, covering building, testing and migrating React Native apps, drawn from Callstack's production app work.

• Agent skills

A biweekly-updated, curated collection of research papers on AI agent applications and architecture, organized by capability, architecture, operations and application.

• Curated lists
• Papers

A Python library from Stanford and Berkeley that adds LLM-based map, reduce and filter operators to bulk-process large datasets with agents, optimizing for accuracy and cost.

• Data engineering

A real-time visualizer that turns Claude Code and Codex agent activity into an interactive node graph, so a developer can watch how an agent breaks down and executes a task.

• AI evals
• Debugging

An Agent Skill that gives any compatible AI coding tool expert guidance on Swift concurrency, distilled from a paid course, for migrating to Swift 6 and fixing data races.

• Agent skills

An unofficial, community desktop client for chatting with Claude and other LLM providers, built with Tauri, Rust and React, with local chat history, MCP tools and multi-agent orchestration.

• Agent frameworks
• Inference

A large-model compression toolkit supporting quantization, speculative decoding and distillation for LLMs, VLMs and diffusion models, aimed at making compressed models more usable and efficient to deploy.

• Models

A lightweight, modern server control panel for deploying, managing and monitoring web applications, databases, Docker containers and security on a VPS or dedicated server, without Kubernetes or a managed-platform subscription.

• Hosting

A local MCP server that lets a compatible AI client read, search and edit notes in an Obsidian vault, restricted to the configured vault folder.

• MCP servers

An agent harness for interpreting financial markets that gives an agent a persistent research workspace per goal, so analysis and theses compound across sessions instead of resetting each time.

• Agent frameworks

A curated list of official Anthropic resources, Claude Code and MCP tooling, community-built extensions and applications, and educational material about Claude.

• Curated lists

A terminal coding agent that inspects a repository, edits files and runs commands under a configurable permission and sandbox policy, working with a choice of model provider.

• Coding agents
• Terminals

A 34-chapter, file-by-file and line-by-line technical analysis of Claude Code's source code, covering its prompt engineering, multi-agent orchestration, tool system and security model.

• Books

An OpenCode plugin that gives coding agents persistent, searchable memory across sessions, backed by a local vector database with no separate server to run.

• Agent memory

The official list of Notepad++ plugins consumed by the editor's built-in Plugin Admin, for installing, updating and removing plugins from inside Notepad++.

• Editors