Explore the directory

A five-step prompt and command-line workflow that takes an idea through research, a product requirements document, a technical design and a build plan, then helps verify and recover a project.

• Coding agents

A code-generation tool for Laravel that turns a single human-readable YAML draft into models, migrations, controllers, requests, and tests all at once.

• Backend

A resumable, long-running task workflow and skill platform for coding agents, covering requirements through implementation and archiving, with tools to create, evaluate and release agent skills.

• Coding agents
• Agent skills

An AI agent framework for black-box penetration testing, supporting bug bounty, red-team and pentesting workflows from a terminal interface, with tools such as nmap, Metasploit and sqlmap.

• Security

A must-read paper list on large language model agents, organized by topic such as personality, memory, planning, tool use, reinforcement-learning training, and multi-agent communication.

• Papers

The companion repository for a systematic academic survey of vision-language models for visual recognition tasks, curating papers by pre-training method, transfer learning and application.

• Papers

A C++ template library that provides STL-like fixed-size containers and utilities for embedded systems, with no dynamic memory allocation.

• Libraries

A Claude Code and Codex plugin that delegates planning, implementation and review to the agent through a disciplined plan, work, review, sync and release loop, with the developer approving each stage.

• Coding agents

An open-source, enterprise-grade MCP and agent-to-agent gateway that gives AI copilots and autonomous agents secure, governed access to internal tools, with identity management and observability.

• MCP servers
• Security

Two books on harness engineering that examine the design philosophies behind Claude Code and Codex, covering constraints, query loops, context governance and multi-agent verification.

• Coding agents
• Books

An agent skill that lets a coding agent write and run real Playwright browser-automation code on the fly, from simple page checks to complex multi-step flows.

• Testing
• Browser automation

A public catalog of reusable AI-agent workflow loops, repeatable playbooks that check their own results and decide what to do next, plus an optional installable skill for finding and publishing them.

• Agent skills
• Curated lists

A benchmark, presented at NeurIPS 2024, for evaluating multimodal AI agents on open-ended tasks inside real virtualized computer environments rather than sandboxed simulations.

• AI evals

A local demo application for running the Bonsai 2 27B language model, a heavily compressed reasoning model with vision and tool-calling support, on a laptop or single GPU.

• Models
• Inference

A hat-based orchestration framework that keeps AI coding agents looping through planning and implementation until a task is done, with a web dashboard and per-repository MCP server.

• Coding agents
• Agent frameworks

A tiny, open, model-agnostic coding agent CLI written in Zig, with an interface closer to a Unix shell than an IDE, embeddable as a harness in larger systems.

• Coding agents

An MCP server that lets AI assistants control DaVinci Resolve Studio through its official scripting API, covering editing, media pool organization, rendering, color grading, Fusion and Fairlight.

• MCP servers
• Generative media

A permission-hardened AI agent with token budgets and persistent memory that runs continuously from the command line, Telegram or the web, asking before it acts.

• Agent frameworks
• Agent memory

A cross-platform on-device AI app for phone and Mac that runs GGUF language models, vision, Whisper speech-to-text and Stable Diffusion image generation entirely offline, with tool calling.

• Inference
• Speech
• Generative media

A native desktop app for managing a complete local development stack, runtimes, databases, web servers, and local HTTPS sites, across Windows, macOS, and Linux, positioned as an alternative to XAMPP, MAMP, Laragon, and Laravel Herd.

• Backend

A local MCP server for AI agents doing literature research on arXiv, reading original LaTeX sections one at a time, exporting BibTeX citations, and keeping topic watches.

• MCP servers
• Papers

A management GUI for Milvus vector databases, available as a web or desktop app, for browsing collections, running vector searches, and monitoring cluster health.

• Databases

A Next.js web application for chatting with any LangGraph server, in Python or TypeScript, that exposes a messages key, through a configurable chat interface.

• Agent frameworks

A Python library, command-line tool and MCP server for searching Google Flights directly through its own API, without web scraping or browser automation.

• CLI tools
• APIs