
Mnemoverse
Memory for AI agents that learns from outcomes
npx -y @mnemoverse/mcp-memory-server@latesthttps://mcp.mnemoverse.com/mcpDetails
- Follow on
- Categories
- Target Audience
- Pricing
- Freemium from $29
- Alternatives
Discovery signals
How AI and people discover Mnemoverse on PeerPush
About Mnemoverse
Mnemoverse gives an AI agent long-term memory that persists across sessions and across tools. Key features: - Stores preferences, decisions and lessons, and recalls them by natural-language search - Learns from outcomes: tell it a recalled memory helped or misled, and what comes back next changes - Shared rooms: several agents or teammates read and write one memory pool - Works in Claude, Cursor, VS Code, ChatGPT and any MCP client, with OAuth sign-in or a free API key What makes it different: recall is not ranked by similarity alone. Feedback on what actually helped changes the order of future results, and the same memory follows you from tool to tool instead of living inside one app. What you can expect: a decision made in Claude Code is there when you open Cursor an hour later, and a preference stated in VS Code holds in a ChatGPT session that evening. With shared rooms, a team's agents build on the same lessons about a codebase instead of relearning them in every seat. The MCP server is open source (MIT); the memory engine is a hosted service with a free plan.
Screenshots
Reviews (0)
No reviews yet. Be the first to rate this product!

Comments (1)
I build Mnemoverse: long-term memory for AI agents that follows your account across sessions and tools, and learns which memories helped. Free plan, open-source MCP server. Feedback welcome.