Production Ready · v2.2.0

Your AI never forgets.

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.

mxLore — claude code session

What happens after CLAUDE.md?

Every AI coding session starts from zero. Your decisions, your specs, your lessons — gone.

Without mxLore

  • Every session starts from scratch — AI has no memory
  • CLAUDE.md grows to 500+ lines, nobody reads it
  • Decisions are made, forgotten, then contradicted
  • Skills are static — no learning from mistakes
  • Each developer maintains their own context files
  • Cross-project knowledge? Copy-paste at best

With mxLore

  • AI recalls decisions, specs, and lessons automatically
  • Structured knowledge DB replaces bloated markdown
  • Decisions tracked as ADRs with full history
  • Skills evolve — auto-tuning based on real feedback
  • Shared team knowledge with per-developer access
  • Cross-project search, relations, and recall

Built for real workflows

Not a toy. Not a demo. 39 production tools forged through months of daily use across real projects.

39 Production MCP Tools
Search, create, update, recall, orchestrate. Every tool battle-tested in real codebases, handling real complexity.
mx_search, mx_recall, mx_create_doc ...
Institutional Memory
AI never forgets decisions, specs, or lessons. mx_recall retrieves context instantly with gate-matrix scoring and auto-learn.
mx_recall + recall_outcome
Skill Evolution
11 skills that learn over time. Auto-tuning adjusts rules based on feedback. Skills get smarter with every session.
auto-tuning threshold: 10
/mxOrchestrate — One Command, Full Workflow
Your AI has a conductor. It coordinates plans, specs, decisions, code reviews, and health checks. Calls the right skill at the right time. Add your own Superpowers — the orchestrator picks them up automatically.
mxPlan · mxSpec · mxDecision · mxDesignChecker · mxBugChecker · mxHealth · mxSave · + your skills
Self-Hosted
Your server, your data, your rules. No cloud dependency, full GDPR compliance. Single binary, no runtime dependencies. Just download and run.
zero external dependencies
Battle-Tested Metrics
Not theoretical. Every feature proven across real projects with real teams. Conflict detection, confidence scoring, decision replay.
350+ docs managed · production-proven
Multi-Server / Multi-Team
Different teams, different servers, one developer. Each project connects to its own mxLore instance. No central bottleneck — teams stay autonomous.
per-project proxy · zero config overlap

One developer. Multiple teams. Zero overlap.

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.

Project A → Proxy A →
Server A ERP Team · own DB · own API key
Project B → Proxy B →
Server B Mobile Team · own DB · own API key
Project C → Default →
Global Server no .mcp.json — uses global config

Dev Teams

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.

Agencies & Consultants

Client A's architecture decisions never leak into Client B's knowledge base. Separate servers, separate databases, complete isolation. One laptop, multiple clients.

Enterprise

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.

How does mxLore compare?

From flat files to full knowledge management.

CapabilityCLAUDE.mdMemory MCPmxLore
Persistent knowledgeFile onlyKey-valueStructured DB
Cross-project searchNoNoFull-text + relations
Multi-developerNoNoACL + per-dev keys
Decision tracking (ADRs)ManualNoFirst-class doc type
Skill evolutionNoNoAuto-tuning + metrics
Institutional memoryNoBasicRecall + gate levels
Session orchestrationNoNoWorkflows + team agents
AI batch maintenanceNoNo12 boot-time jobs
Admin UINoNoWeb dashboard
Multi-server / Multi-teamNoNoPer-project server
Self-hostedLocal fileVariesYour server

Three steps. Then AI remembers everything.

From zero to institutional memory in minutes.

Deploy Server
Download the binary. Point it at your MariaDB. Schema auto-creates on first boot.
mxLoreMCP.exe
Connect Your AI Agent
Run /mxSetup — a local skill that configures everything. No MCP connection needed to start. Just your server IP + API key.
/mxSetup <api-key>
AI Remembers
Every decision, spec, and lesson persisted. Skills auto-tune. Memory compounds across sessions.
mx_session_start

Production metrics, not marketing

Every number from actual deployment. No inflated benchmarks.

39
MCP Tools
search, recall, batch, agents
12
Skills
self-evolving with auto-tuning
<50ms
Response Time
p95 tool call latency
12
Batch Jobs
automated AI boot tasks

Watch a complete session

One command. Five skills. Zero manual steps.

mxLore — workflow demo

15 seconds. That's it.

No JSON editing. No config wikis. One skill does everything.

Setup (once per developer)
# 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.
First session — using skills, not raw calls
# 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

Source available, dual licensed

Server under BSL 1.1, skills under MIT. Use freely, contribute freely.

Server
BSL 1.1
Business Source License. Full source access. Converts to Apache 2.0 after the change date.
  • Full source code access
  • Self-host on your infrastructure
  • Modify for your needs
  • Converts to Apache 2.0
Skills & Tooling
MIT
All 11 skills, setup scripts, and client tooling are fully open source under MIT.
  • Use anywhere, no restrictions
  • Fork and modify freely
  • Commercial use allowed
  • Community contributions welcome

Simple pricing. No subscriptions.

One-time purchase. All features. All updates. Forever yours.

Free
€0
Non-commercial use. Open source projects, students, evaluation.
  • All 39 MCP tools
  • All 11 skills
  • Unlimited projects
  • Full source code access
  • Community support (GitHub Issues)
Commercial
€399 €149
Early Adopter price until June 30, 2026. One-time payment, use forever.
  • Everything in Free
  • Commercial production use
  • Unlimited servers & developers
  • All future updates included
  • Priority email support

Built for teams who ship, not demo.

Dev Teams

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.

CTOs & Architects

Architectural decisions tracked and enforced. See which AI suggestions your team accepts or overrides. Data-driven skill evolution.

Regulated Industries

Self-hosted, GDPR-compliant, audit-ready. Your code knowledge never leaves your infrastructure. Full access logs and revision history.

Frequently asked questions

Do I need Delphi to use mxLore?
No. We provide pre-built Windows binaries. Just download, configure the INI file, and start. Delphi is only needed if you want to compile from source.
Does it work with Cursor, Windsurf, or Cline?
Yes. mxLore speaks standard MCP (Model Context Protocol). Any MCP-compatible client can connect — Claude Code, Cursor, Windsurf, Cline, Copilot CLI, and others.
Does it run on Linux or macOS?
Currently Windows only (x64). Linux/Docker support is planned for a future release. The MCP protocol is platform-independent — only the server binary is Windows-specific.
What does it cost?
Free for non-commercial use. Commercial license: €149 one-time (Early Adopter, regular €399). Unlimited servers, unlimited developers, all updates included. No subscriptions. Contact info@microtronx.com for licensing.
Do I need a Claude API key?
Only for the optional AI Batch feature (automatic summaries, tagging, stale detection). The core MCP server works without any AI API key — it's a pure knowledge database.
How does it compare to just using CLAUDE.md?
CLAUDE.md is great for project rules but doesn't scale. mxLore adds structured storage, cross-project search, decision tracking, skill evolution, multi-developer access, and institutional memory that persists across sessions.
Is my data sent to any cloud service?
Never. mxLore is fully self-hosted. Your data stays on your infrastructure. The only external call is the optional AI Batch feature which uses your own Claude API key — and even that can be disabled.
Can one developer connect to multiple mxLore servers?
Yes. Each project in your .mcp.json can point to a different mxLore instance. The per-project proxy keeps everything separated — your ERP team's server stays independent from your mobile team's server. /mxSetup configures each connection individually.

Ready to give your AI a memory?

Deploy in minutes. 15-second onboarding. Your infrastructure, your data, your rules.