Designing, evaluating, and shipping autonomous AI agents.
7658 posts
Local simulation QA and regression framework for Abaqus FEA
Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, ref...
Git-like undo and rollback checkpoints for OpenAI Codex CLI. Snapshot, diff, and restore files before and after Codex edits. MCP server + Co...
Design superpowers for AI coding agents. 35 skills, 5 layers, 7 framework targets. Ideation, batch generation, design systems, iteration loo...
Open-source visual AI workflow platform powered by Skills, MCP, agents and extensible components.
A Model Context Protocol (MCP) server that exposes iTerm2 to agents for observation and non-destructive annotation. Agents can inspect sessi...
# 🐢🚀 Node.js Sandbox MCP ServerThis repository hosts a Node.js server that implements the Model Context Protocol (MCP) for running JavaScr...
Delegate coding tasks from Claude Code, Codex, or Copilot to Cursor's CLI agent over MCP. Your assistant plans and reviews; Composer 2.5 im...
Agent-native knowledge OS: turn messy PDFs, scans & DOCX into a verifiable, Markdown knowledge base that LLMs & AI agents read, search and c...
One local memory layer for Codex, Claude Code, opencode, Gemini CLI, Cursor, and MCP-capable coding agents.
Concord — multi-agent collaboration rooms for AI agents. Claude Code plugin + MCP server (also Gemini/Codex/Cursor). End-to-end encryption +...
