REA
Verified · 33 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
claude mcp add delego -- uvx delego
Intent-bound action authorization for agents: policy rules, human approval gates, and a signed, tamper-evident audit ledger — aimed squarely at the prompt-injection-can't-re-point-an-approval problem, which is a real one. The engineering story is more serious than most agent-security listings. It's also brand new: the org and repo appeared the same day in June 2026, community is near zero, and you're trusting a young project with your approval pipeline. State lives locally under ~/.delego.
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.