Explore the directory

A universal MCP security-audit server that runs a three-tier penetration-testing methodology, reconnaissance, source-to-sink analysis and live validation, so a finding is confirmed before it is ever reported.

• MCP servers
• Security

Templatical is a drag-and-drop email editor you embed in a web app with one function call; it stores templates as JSON, renders output as MJML for cross-client compatibility, and works with React, Vue, Svelte, Angular or vanilla JS.

• Agent skills
• Libraries

ECA Emacs is an Emacs client for Editor Code Assistant, an AI pair-programming server that provides interactive chat, code suggestions and context management inside the editor.

• Coding agents
• Editors

An MCP server that bridges LLMs such as Claude and Cursor with the x64dbg and x32dbg debuggers, giving an AI assistant direct access to more than 40 debugging tools through natural-language prompts.

• MCP servers
• Debugging

An MCP server that lets AI assistants query and analyze Prometheus metrics through standardized interfaces, running PromQL queries against a configured Prometheus server.

• MCP servers
• Monitoring

An open-source, local-first 3D parametric CAD application that runs in the browser, built on OpenCascade WebAssembly, for both human designers and permissioned AI agents editing the same document.

• Design tools

An MCP server that searches Airbnb listings and retrieves detailed property information for AI agents, with location, date, guest and price filtering.

• MCP servers

A bash-to-PowerShell translation layer for AI coding agents on Windows, letting an agent keep writing familiar bash commands that fauxnix deterministically translates, executes natively, and returns in GNU-style output, with no VM or WSL.

• CLI tools

A curated comparison of second-brain, AI-memory and personal-knowledge systems, organized around a five-stage lifecycle of collecting, organizing, evolving, using and governing personal and team context.

• Agent memory
• Curated lists

envrc.el is an Emacs package that uses direnv to set per-project environment variables on a per-buffer basis, so processes launched from different projects' buffers pick up each project's own environment.

• Editors

A Kubernetes operator for enterprise LLM serving that automates model management, GPU scheduling and deployment across runtimes such as SGLang, vLLM, TensorRT-LLM and Triton.

• Inference
• Containers

An open-source memory and reliability layer for multi-agent setups that keeps agents coordinated without a central orchestrator, combining local long-term memory, drift detection and cross-agent contracts.

• Agent memory

A single Zig binary for running local large-language-model inference on AMD GPUs and Apple Silicon, loading GGUF files behind a command line, a browser chat interface, a model manager and an OpenAI-compatible API.

• Inference

A curated list of tools, frameworks and resources for agent harness engineering: designing the environments, constraints and feedback loops that make AI coding agents reliable at scale.

• Agent frameworks
• Curated lists

REAP is a research codebase for pruning experts from large sparse Mixture-of-Experts language models, using a criterion that combines router gate values and expert activation norms to compress models with less accuracy loss than merging.

• Models

A curated list of tools, agent skills, plugins, IDE integrations and other resources for developers working with Anthropic's Claude Code, organized into categories such as agents, skills, plugins, clients and SDKs.

• Curated lists

An open-source Python package for data-driven evaluation of LLM-powered applications, with a modular metric library covering retrieval-augmented generation, code generation, agent tool use and classification.

• AI evals

A Chinese-language agent-engineering tutorial site for programmers, covering agent frameworks, coding-agent internals and production deployment, alongside a downloadable book of nearly 800 Agent interview questions for Chinese tech-company recruiting.

• Tutorials

A Claude Code and Codex plugin for spec-driven development that turns a feature request into a structured specification, then executes it one task at a time with fresh context and resumable progress.

• Coding agents
• Agent skills

A hybrid retrieval-augmented generation system combining vector search, a knowledge graph and cross-encoder reranking, with document parsing, image and table captioning, and inline citations.

• RAG

A local-first desktop app that converts PDFs, Office documents and other file formats into clean, AI-ready Markdown, with OCR for scanned pages and batch processing for a whole folder.

• RAG

A list of recent developments in retrieval-augmented generation for large language models, tracking accepted papers by conference and year along with common evaluation datasets.

• RAG
• Curated lists
• Papers

A curated, community-sourced collection of prompts for Google's Gemini 3 model, with a companion web gallery for browsing, searching and filtering them.

• Curated lists

ppx_deriving is an OCaml library and syntax-extension framework that generates boilerplate code from type declarations through plugins such as show, eq, ord, enum, iter, map, fold, make, yojson and protobuf.

• Libraries