mxLore
Active·★ 30·NOASSERTION·Updated 2026-10-12
mxLore is a self-hosted server designed to provide persistent memory for AI coding assistants by storing architectural decisions, specifications, and lessons learned. It integrates with various AI clients like Claude Code and Cursor, enabling multi-project knowledge management and AI-driven insights.
#AI-assisted Development#Knowledge Base#Model Context Protocol#Semantic Search#Multi-Agent System#Code Assistant Memory#Self-hosted#Developer Tooling
01
Features
01Extensive MCP Tools for knowledge management (search, create, update, recall).
02Multi-project support with cross-project search capabilities.
03Hybrid vector and full-text semantic search with MariaDB.
04Multi-Agent system enabling communication across projects.
05Institutional memory for tracking lessons learned and knowledge links.
02
Compatibility
Windows
Operating System
Verified via docs
MariaDB
Database
Verified via docs
AI Coding Assistants
Client Integration
Verified via docs
03
Quick start
1
$ mysql -u root -p -e "CREATE DATABASE mxai_knowledge CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci;"
2
$ copy mxLoreMCP.ini.example mxLoreMCP.ini
04
Use cases
↳Centralized storage and retrieval of architectural decisions and project specifications.
↳Providing persistent memory and context for AI coding assistants like Claude Code and Cursor.
↳Facilitating cross-project knowledge sharing and multi-agent communication in software development.
↳Auto-tuning AI checker rules and tracking lessons learned for skill evolution.
05
Alternatives
zoteus★ 61
⚡ The everything Zotero MCP server: complete Zotero Web API v3 + desktop local API for Claude & any MCP client. Search, safe writes, add-by-DOI, CSL citations, hybrid semantic search, and a scholarly-context graph. TypeScript, local-first.
Hatchdoor★ 61
Self-hosted, agent-native web app and MCP server for your Obsidian-style Markdown vault. Browse, search, and edit notes from a fast UI or from AI agents.
mcp-logseq★ 343
MCP server to interact with LogSeq via its Local HTTP API - enabling AI assistants like Claude to seamlessly read, write, and manage your LogSeq graph.
sample-okf-llm-wiki★ 33
Data Wiki turns data into portable knowledge bundles following Open Knowledge Format (OKF) and serves them to AI agents over the Model Context Protocol (MCP).
crystalline★ 17
Local-first crystalline intelligence for AI agents: the knowledge that endures across sessions, taught as Markdown Domains and captured as Engrams. One Rust binary with MCP server, CLI and hybrid search.
Comments
Log in to leave a comment
No comments yet. Be the first!