carloluisito/mindkeg-mcp

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

43
/ 100
Emerging

Implements a RAG (Retrieval-Augmented Generation) pattern with atomic learnings (max 500 chars each) instead of document chunking, supporting semantic search via FastEmbed (local ONNX), OpenAI embeddings, or FTS5 keyword fallback—all backed by SQLite with zero external dependencies. Connects to MCP-compatible agents (Claude Code, Cursor, Windsurf) via stdio or HTTP+SSE transports, with features like auto-categorization, conflict detection, access tracking with relevance decay, encryption at rest, and Prometheus monitoring for enterprise deployments.

Available on npm.

Maintenance 13 / 25
Adoption 4 / 25
Maturity 18 / 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.