REA
Verified · 34 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
AI safety middleware — detects self-harm and criminal intent in LLM prompts.
claude mcp add humane-proxy -- uvx humane-proxy
Acts as a safety middleware layer that screens prompts for self-harm and criminal-intent patterns before they reach downstream models or tools. It is for developers adding lightweight policy enforcement to LLM apps without building a full moderation stack from scratch. The purpose is clear, but safety filtering is high-stakes and hard to validate, so this should be treated as one control in a broader review process, not a complete solution.
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.
AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Draw and visually collaborate with your agents on tldraw's canvas.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Keyword research, site audits, rank tracking and AI visibility for your AI agent.