Explore the directory

A native MCP plugin for the x64dbg debugger that exposes its full functionality over HTTP, letting an AI assistant set breakpoints, step through code, read memory and control debugging sessions programmatically.

• MCP servers
• Debugging

A Claude Code and Codex skill that turns a topic or document into a narrated, code-animated explainer video, with TTS voiceover, word-aligned subtitles and a chapter progress bar, using Remotion rather than stock footage or a video model.

• Agent skills
• Generative media

A lightweight C++ inference library for ONNX models built to minimize memory use rather than latency, able to run Stable Diffusion XL on a Raspberry Pi Zero 2 or Mistral 7B on a desktop, with ARM, x86, WebAssembly and RISC-V support.

• Inference

A pair of agent skills that study the real screens of top-grossing mobile apps through an MCP research tool, then build native-quality Expo and React Native screens held to a simulator-verified motion and design bar.

• Agent skills
• Mobile

A self-hosted, Sentry-SDK-compatible error tracking server for collecting and reviewing application exceptions from your own infrastructure.

• Monitoring

A local coding agent that adds planning, candidate generation, sandboxed verification and repair around compact open models, so smaller models running on a developer's own hardware can handle real software tasks without a hosted API.

• Coding agents

An open-source, model-agnostic RAG platform with end-to-end tooling for ingestion, chunking, embeddings and retrieval, a chat playground with citations, multi-tenant hosting and a typed API, available hosted or self-hosted.

• RAG

A recursive self-improving agent operating system for embodied and robotic tasks, where an agent plans tool calls, a Gateway executes them, an observation collector captures before and after evidence, and a verifier checks the goal was actually achieved.

• Agent frameworks

A PHP framework for building and orchestrating agentic AI applications, connecting LLMs, tools, vector databases and memory into agents with event-driven workflows, human-in-the-loop steps, streaming and MCP support.

• Agent frameworks

A curated, categorized list of AI-powered coding tools for developers, covering editors, code completion, coding agents, CLI tools, app builders, code review, testing, security and database or API tooling.

• Curated lists

A self-hosted, open-source API management platform that turns databases, microservices, and custom business logic into REST APIs and AI agent tools, with a developer portal and SDK generation.

• APIs
• Backend

A Gymnasium-compatible PyBullet simulation environment for single- and multi-agent reinforcement learning of quadcopter control, with Betaflight software-in-the-loop and classical PID control examples.

• Libraries

A headless iOS Simulator controller and self-hosted web UI that boots devices, streams their screen, and injects taps, gestures and system input without opening Xcode or Simulator.app.

• Testing
• Mobile

Trail of Bits' opinionated collection of Claude Code defaults, documentation and workflows for security audits, development and research, covering sandboxing, permissions, hooks, skills and MCP server configuration.

• Agent skills
• Security

The official TypeScript SDK for the Claude API, providing typed access to Anthropic's language models for server-side JavaScript and TypeScript applications across Node.js, Deno, Bun, Cloudflare Workers and Vercel Edge.

• Libraries
• APIs

A native Go MCP server that lets AI assistants operate Kubernetes and OpenShift clusters directly through the API server: generic resource CRUD, pod operations, Helm releases, and Tekton pipeline management.

• MCP servers
• Containers

A web and mobile dashboard for monitoring and controlling AI agent CLI sessions running in tmux on your own machine, reachable from any browser while terminal traffic stays local by default.

• Coding agents

A source-level architectural analysis of Claude Code's roughly 512,000 lines of TypeScript, arguing that only a small fraction is AI decision logic while the rest is deterministic infrastructure, packaged with a design guide for agent builders.

• Coding agents
• Tutorials

An open-source, local-first desktop app where a commander model plans a goal and coordinates a team of specialist agents, including a repo-aware coding agent, running your own installed coding CLIs as local sessions with your own model keys.

• Coding agents
• Agent frameworks

A Claude Code workspace of skills, commands and templates that write a video script, generate voiceover, music and visuals with open-source models, and render the finished MP4, running on the user's own cloud GPU account at near-cost prices.

• Agent skills
• Generative media

A weekly updated, curated collection of over a thousand OpenClaw agent skills spanning research, browser and computer automation, prompt engineering, text-to-speech and image generation.

• Agent skills
• Curated lists

A Chinese-language, monthly-updated textbook on medical large language models, covering foundational LLM technique through vertical training for healthcare, clinical applications, and the field's ethical and safety challenges.

• Books

A Rust crate that generates compile-time-checked builders for structs and functions, plus named and optional function parameters, using the typestate pattern to prevent missing or repeated arguments.

• Libraries

An MCP server that gives Claude and other LLMs access to MySQL databases: inspecting schemas and running read-only queries by default, with per-flag opt-in write access, SSH tunneling, multi-database mode and automatic PII redaction.

• MCP servers
• Databases