Magnemo

Governed memory for AI agents. Memory with receipts. Local, plain files, zero network calls.

LLM Mart 3 views 145 listing impressions

Magnemo is a memory system for AI agents that persists across sessions. It runs entirely locally with no account, no telemetry, plain files, and zero network calls. Nothing is added to memory without user approval, and each entry has a receipt.

It works through the Model Context Protocol (MCP), allowing integration with any AI tool that supports MCP. It is tested with Claude Code and provides config snippets for Claude Desktop, Cursor, Windsurf, VS Code, Cline, Gemini CLI, and Codex CLI. The software is open source.

It requires Python 3.11 or newer.

Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.

Related servers

Universal MCP Server with advanced AI memory capabilities and semantic search.

30 views

MCP server for MikroTik routers: firewall, NAT, routing, DHCP, DNS, WireGuard and more via SSH.

28 views

Let Codex orchestrate external coding agents through their native harnesses.

28 views

Control plane MCP for scoped recon, triage, and bounded proofs.

27 views