Built for AI agents that need to remember context across conversations without losing track of what changed when. Gives you persistent storage with version control semantics: write and read memory entries, roll back to previous states, and search through history semantically. The audit trail means you can trace how an agent's knowledge evolved over time, which is useful for debugging unexpected behavior or understanding decision chains. Reach for this when you're building agents that accumulate knowledge over multiple sessions and you need more than just appending to a context window. The rollback feature alone makes it worth considering for any production agent deployment.
claude mcp add --transport stdio io.github.novyxlabs-novyx-mcp uvx novyx-mcp