MESkit
Try MESkitView on GitHub

Source-available MES toolkit

Know your floor. Hit your deadlines. Answer any audit.

Stop chasing data across spreadsheets. Ask MESkit what's happening on your floor and get a real answer.

Source-available MES with production tracking, quality alerts, and built-in analytics. Free to self-host.

Last updated: March 7, 2026

Get Started FreeView on GitHub

What is MESkit?

Source-available MES with built-in analytics and natural language queries.

Summary

MESkit is a source-available MES toolkit with built-in analytics, quality alerts, and a natural language interface. It routes both UI actions and plain English commands through one Zod-validated tool layer backed by an ISA-95-aligned Postgres schema. The result: every button has a voice equivalent, and every voice command follows the same guardrails as a button click.

MetricValue
Typed tool operations20+ Zod-validated server actions
ISA-95-mapped tables12 Postgres tables via Supabase
Smart features3 (Quality alerts, Planning, Natural language)
LicenseBSL 1.1 (free to self-host)
Roadmap milestones6 (M1 scaffold through M6 MQTT)

North Star

The product vision MESkit is building toward.

Summary

See problems before they stop your line. MESkit monitors machine health, surfaces quality trends, and helps you plan production \u2014 so your team acts on insights instead of chasing data.

Monitor

The Machine Health Monitor detects degradation signals from sensor telemetry and surfaces alerts before failures happen.

Milestone M6

Plan

The Production Planner evaluates constraints — backlog, deadlines, alternative capacity — and computes rescheduling options.

Milestone M5

Act

The intelligence layer acts on decisions through the tool layer — updates schedules, notifies operators, adjusts production flow.

Available from M1

In the MVP, these layers operate independently. Post-MVP, the Monitor triggers the Plan, which triggers the Act — closing the coordination loop. See the roadmap for milestone details.

MESkit grows with you

Start with visibility. Add traceability when your customers demand it. Add compliance when regulations require it.

Know your floor

Replace end-of-shift walkabouts with real-time dashboards. See WIP, yield, and quality events as they happen — and ask MESkit questions instead of digging through spreadsheets.

Production tracking · Quality logs · Natural language interface

Answer any audit

When a customer asks what happened to lot 4472, you have the answer in seconds — full route history, quality events, and operator actions. No manual reconstruction.

Lot traceability · Quality Monitor · Defect analytics

Meet what's coming

EU CSRD and Digital Product Passport requirements are pushing carbon and traceability obligations down supply chains onto small shops. MESkit gives you the infrastructure to comply before your biggest customer asks.

Carbon footprint per batch · Blockchain-anchored records · OEM-ready exports

Core facts

Canonical product facts for both human readers and AI answer engines.

Key facts

  • Category: Source-available MES toolkit with built-in analytics (BSL 1.1 — free to self-host).
  • Identity: Source-available MES with production tracking, quality alerts, and natural language queries. Operators stay in command.
  • Standards: ISA-95 aligned data model with 15 mapped Postgres tables.
  • Tool layer: 26 Zod-validated server actions shared by UI and intelligence layer.
  • Smart features: Ask MESkit (natural language queries), Quality Monitor, Production Planner.
  • North Star: Predict machine failure and coordinate the response via three automation layers (Monitor, Plan, Act) — operators stay in command.
  • Roadmap: 6 milestones. M1–M3 complete (scaffold, Build Mode, Configure Mode). M4 (Run Mode + Simulator) in progress.
  • Stack: Next.js, Supabase, Claude API (tool-use), TypeScript.

Summary

MESkit is built around a single operational contract: typed tools. UI screens and AI agents are peers that call those tools with schema-validated input, then persist to the same Supabase-backed ISA-95 model.

How it works

The product loop is identical for UI-driven and chat-driven workflows.

Define product
Build route
Move units
Collect data
Visualize
...or ask MESkit

Human interface

Build, Configure, Run, and Monitor modes provide direct control over lines, routes, units, and analytics.

Natural language

The chat panel maps intent into explicit tool calls. Every response is grounded in real MES operations.

Natural language example

Illustrative chat flow: user intent becomes deterministic tool calls.

Ask MESkitExample interaction
User: Scrap SMX-00044, solder defect
→ search_units(serial_number='SMX-00044')
→ create_quality_event(unit_id=..., event_type='scrap', result='fail')
→ scrap_unit(unit_id=...)
MESkit: SMX-00044 scrapped. Defect logged as critical.

One tool layer for UI and agents

Unified architecture means no split logic path.

UI Buttons ────────┐ ├─> Tool Layer (typed + validated) ──> Supabase Postgres Natural Language ──┘ Intelligence Layer reads and writes through the same tool contracts.

See the full architecture breakdown on the architecture page.

ISA-95 credibility

MESkit data structures keep standard manufacturing terms explicit.

ISA-95 levelMESkit conceptTables
Level 0-2Physical assetslines, workstations, machines
Level 3Execution + qualityunits, unit_history, quality_events
Future bridgeMQTT ingestionmqtt_messages

Architecture snapshot

Four-layer design with a future MQTT transport bridge.

Frontend (Next.js) ↓ Tool Layer (Server Actions + Zod) ↓ Intelligence Layer ↓ Supabase (Postgres, Auth, Realtime) ↓ MQTT Broker (M6)

FAQ quick answers

Answer-ready blocks for common discovery prompts.

Mini FAQ

What is MESkit?

MESkit is a source-available Manufacturing Execution System toolkit aligned to the ISA-95 standard. It routes both human UI actions and natural language commands through a single typed tool layer — 20+ Zod-validated server actions backed by 15 ISA-95-mapped Postgres tables. Built on Next.js and Supabase, MESkit includes built-in quality alerts, production planning, and a natural language interface so operators can ask questions instead of clicking through menus.

How does the natural language interface work?

MESkit's natural language interface uses the same typed operations as UI buttons. When a user gives a plain English command, the system selects from registered tools, validates input against Zod schemas, and executes against Supabase. Every button has a voice equivalent, and every voice command follows the same guardrails as a button click.

Is MESkit production-ready today?

MESkit has completed M1 through M3 (scaffold, Build Mode, and Configure Mode). M4 — Run Mode and the Production Simulator — is in progress. The public six-milestone roadmap tracks progress toward full production readiness, with the simulation-first model letting teams validate line flow before connecting real hardware via MQTT in M6.

Explore next