10 agents available in the Cursor directory
Universal Laws of Artificial Entities — a modern governance framework for AI agents, evolved from Asimov's Three Laws. Drop-in CLAUDE.md for Claude Code & Cursor AI.
Merge gates and safety checks for AI coding agents. Works with Claude Code, Cursor, Windsurf, Codex via MCP. Detect scope violations, missing tests, and risks before merge.
Intercept risky rm commands on your VPS with email approval. Perfect for AI coding agents (Claude Code, Cursor, etc.) that execute commands on production servers.
Give AI coding agents (Claude Code, Cursor, Aider, Codex) a structured autonomous loop with guardrails — boundaries, 5 verification gates, 3-layer self-reflection, and autonomous remediation. pip install ouro-loop. Zero dependencies.
AI Agent Security Middleware — 8-layer defense, DLP data flow, prompt injection detection, zero dependencies. SDK + MCP server for Claude Code, Cursor, LangChain, Hermes Agent & more.
Cryptographic audit receipts for AI coding agents. Ed25519 + Merkle + RFC 3161 TSA. Supports Claude Code & Cursor.
Agent governance that stops costly AI mistakes before they run: pre-action gates, shared lessons, and team safeguards for AI coding workflows.
Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTTP API. Works with Cursor, Claude Code, Codex, and any MCP-compatible agent.
Cross-platform epistemic access control for AI coding assistants - Claude Code, Cursor, GitHub Copilot
Work safely with AI agents like Claude Code, Cursor, Kiro