Agent Magnet
Behavioral memory layer for AI tools that learns preferences and context across Claude, Cursor, and Codex.
Agent Magnet is a behavioral memory layer for AI coding tools that learns user preferences and context across sessions in Claude, Cursor, and Codex. It persists learned behaviors and personalizations so AI assistants remember how you work. The server requires a MAGNET_USER_ID and is distributed as a PyPI package.
Source
Repository: https://github.com/helinakdogan/agentmagnet
Maintain Agent Magnet?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[](https://getagentictools.com/mcp/helinakdogan-agentmagnet?ref=badge) Related mcp
XMemo User-owned persistent memory for AI agents, CLIs, and IDEs via Streamable HTTP MCP.
Memoir Persistent memory layer for AI coding tools that syncs context across sessions, tools, and machines.
Serial Port Serial port communication with line-oriented I/O, control lines, and device plugins.
Claude FAF Persistent project context for Claude Desktop and Claude Code, built on the IANA-registered .faf format.
Currents Test Results Provides a bridge to Currents test results platform, enabling AI to analyze failing tests, optimize test suites, and troubleshoot
Attestix AI agent identity, W3C credentials, and EU AI Act compliance tools.