REA
Verified · 34 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
Behavioral memory layer for AI tools. Learns preferences and context across Claude, Cursor, Codex.
claude mcp add agent-magnet -- uvx agent-magnet
Implements a behavioral memory layer intended to preserve preferences and context across multiple AI tools such as Claude, Cursor, and Codex. It is aimed at users building persistent agent workflows who want continuity beyond a single session or product. The use case is timely, but the project appears young and trust-sensitive, so data handling, portability, and accuracy of remembered context deserve close scrutiny.
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.