Self-hosted knowledge server for AI coding agents. 39 MCP tools, institutional memory, skill evolution. Works with Claude Code, Cursor, Windsurf, and any MCP client.
Every AI coding session starts from zero. Your decisions, your specs, your lessons — gone.
Not a toy. Not a demo. 39 production tools forged through months of daily use across real projects.
Each project connects to its own mxLore server through a dedicated proxy. Teams stay autonomous — different databases, different API keys, different knowledge. One developer can seamlessly work across all of them.
Each team runs their own mxLore instance with their own knowledge base. A developer working across teams switches context automatically — the per-project proxy routes to the right server.
Client A's architecture decisions never leak into Client B's knowledge base. Separate servers, separate databases, complete isolation. One laptop, multiple clients.
Department-level knowledge silos by design. The mobile team's lessons stay separate from the backend team's decisions. Cross-team knowledge sharing is opt-in via project relations, not forced.
From flat files to full knowledge management.
| Capability | CLAUDE.md | Memory MCP | mxLore |
|---|---|---|---|
| Persistent knowledge | File only | Key-value | Structured DB |
| Cross-project search | No | No | Full-text + relations |
| Multi-developer | No | No | ACL + per-dev keys |
| Decision tracking (ADRs) | Manual | No | First-class doc type |
| Skill evolution | No | No | Auto-tuning + metrics |
| Institutional memory | No | Basic | Recall + gate levels |
| Session orchestration | No | No | Workflows + team agents |
| AI batch maintenance | No | No | 12 boot-time jobs |
| Admin UI | No | No | Web dashboard |
| Multi-server / Multi-team | No | No | Per-project server |
| Self-hosted | Local file | Varies | Your server |
From zero to institutional memory in minutes.
/mxSetup — a local skill that configures everything. No MCP connection needed to start. Just your server IP + API key.Every number from actual deployment. No inflated benchmarks.
One command. Five skills. Zero manual steps.
No JSON editing. No config wikis. One skill does everything.
# 1. Download the setup skill (one-liner) mkdir -p ~/.claude/skills/mxSetup curl -o ~/.claude/skills/mxSetup/SKILL.md https://raw.githubusercontent.com/MicrotronX/mxLore-skills/main/mxSetup/SKILL.md # 2. In Claude Code: run mxSetup with your API key /mxSetup mxk_your_api_key_here # mxSetup asks: Server URL? → http://localhost:8080/mcp # Downloads skills from GitHub, installs proxy, configures MCP # Done in ~15 seconds. 39 tools ready.
# Start your session — orchestrator loads context automatically /mxOrchestrate resume # Plan a feature — spec, plan, and decisions tracked in DB /mxPlan "Add user authentication with OAuth2" # AI recalls relevant decisions automatically you: "How did we handle token refresh last time?" # → mx_recall finds ADR-0042 + 3 related lessons # Review your code — skills learn from your feedback /mxDesignChecker /mxBugChecker # Save everything — session notes, state, lessons extracted /mxSave
Server under BSL 1.1, skills under MIT. Use freely, contribute freely.
One-time purchase. All features. All updates. Forever yours.
Shared knowledge that survives context switches. Each team runs their own server — one developer can work across multiple teams seamlessly. Stop re-explaining architecture to your AI.
Architectural decisions tracked and enforced. See which AI suggestions your team accepts or overrides. Data-driven skill evolution.
Self-hosted, GDPR-compliant, audit-ready. Your code knowledge never leaves your infrastructure. Full access logs and revision history.
/mxSetup configures each connection individually.Deploy in minutes. 15-second onboarding. Your infrastructure, your data, your rules.