carloluisito/mindkeg-mcp

A persistent memory MCP server for AI coding agents — stores, searches, and retrieves atomic learnings so agents retain knowledge across sessions.

42
/ 100
Emerging

This project helps software developers ensure their AI coding agents (like Claude Code or Cursor) retain crucial knowledge across different work sessions. It acts as a centralized, persistent 'brain' where agents can store and retrieve specific insights — such as debugging solutions, architectural choices, or code conventions. The result is that AI agents start each session with an understanding of past work, reducing repetitive explanations and common mistakes.

Available on npm.

Use this if you are a software developer frequently using AI coding agents and find that they 'forget' important context and decisions between sessions, leading to inefficiencies.

Not ideal if you do not use AI coding agents, or if your primary need is for a general-purpose document-chunking RAG system rather than atomic, curated learnings.

AI-assisted-development software-engineering developer-tools code-analysis knowledge-management
Maintenance 10 / 25
Adoption 4 / 25
Maturity 20 / 25
Community 8 / 25

How are scores calculated?

Stars

8

Forks

1

Language

TypeScript

License

MIT

Last pushed

Mar 09, 2026

Commits (30d)

0

Dependencies

6

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/carloluisito/mindkeg-mcp"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.