by kraklabs · MCP Server · ★ 36
MIE - Memory Intelligence Engine Stop re-explaining yourself to every AI agent. MIE gives all your agents — Claude, ChatGPT, Cursor, Gemini — a shared, persistent knowledge graph they can read and write. Decisions, context, facts, and relationships survive across sessions, tools, and providers. The Problem You explained your entire architecture to Claude. Two hours of context, decisions, tradeoffs. Next day, new conversation — it knows nothing. So you explain it again. Then you switch to Cursor for implementation. Zero context. You open ChatGPT to brainstorm a different angle. Blank slate.
| Stars | 36 |
| Forks | 4 |
| Language | Go |
| Category | MCP Server |
| License | AGPL-3.0 |
| Quality Score | 70.1509319413273/100 |
| Open Issues | 1 |
| Last Updated | 2026-03-17 |
| Created | 2026-02-05 |
| Platforms | claude-code, cli, go, mcp |
| Est. Tokens | ~71k |
These tools work well together with mie for enhanced workflows:
Explore other popular mcp server tools:
mie is Persistent memory graph for AI agents. Facts, decisions, entities, and relationships that survive across sessions, tools, and providers. MCP server — works with Claude, Cursor, ChatGPT, and any MCP cl. It is categorized as a MCP Server with 36 GitHub stars.
mie is primarily written in Go. It covers topics such as ai-agents, ai-memory, ai-tools.
You can find installation instructions and usage details in the mie GitHub repository at github.com/kraklabs/mie. The project has 36 stars and 4 forks, indicating an active community.
mie is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.