Agent Memory Mcp

It's designed for tracking architecture decisions, patterns, and context that would otherwise get lost between conversations. The setup involves cloning a repo, running an npm server with your project ID, and then Claude can query it like "find all authentication patterns" or save new decisions with tags. There's also a localhost dashboard to visualize what's been stored. Useful if you're working on a long-running project where the agent needs to remember design choices and accumulated knowledge rather than starting fresh every time.