REA
Verified · 34 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
Give Claude an honest self-model — behavioral tendencies built from evidence, not session memory. Mi
claude mcp add --transport http mirror https://mirror.mctx.ai/v0.4.0
Offers a remote-only self-model or behavioral-memory layer intended to give Claude a more evidence-based profile over time. It is for advanced AI users interested in longer-horizon personalization, reflection, or memory experiments. The concept is specialized and somewhat hard to evaluate from the listing alone, so it should be treated as experimental rather than established.
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.