EIDONIX

Agentic analytics & applied AI

Make Better
Decisions

Knowing what to do is just the first step; empowering your people to do it gets it done. Eidonix enables both.

See the work
Project Board AUTO

Approach

Support People, Don't Replace Them

The eighth waste is unused talent: improvement compounds when it's continuous.

The Eighth Waste

Lean counts unused human potential as waste, and an overloaded person doesn't get to think. These tools go after the work that eats hours and gives nothing back: searching, re-running, reformatting, rebuilding an analysis somebody already did last quarter.

The Knowledge Stays

Catalogs, saved analyses, and hard-won context build up inside your own systems. What the team learns stays with the team.

Works With What You Have

Talks to the PLCs, CMMS, databases, and files already in place. Nothing gets replaced to make room.

Solutions

Agentic analytics for decision makers

Cletus

An analytics workspace that investigates a question, runs the analysis, and hands back the work.

Works across sourcesSpreadsheets, shared files, SQL databases, market data, and Eidonix Lens knowledge catalogs.
Runs the analysisSQL, DuckDB, Python, R, and charting inside a controlled sandbox.
Produces real artifactsCharts, native Excel workbooks, and reports you can hand to someone.
Carries knowledge forwardSkills leave with the retiring workforce. Cletus helps you capture and transfer that knowledge to the new generation.
In active use Desktop applicationGo · Svelte
More on Cletus

Knowledge discovery

Eidonix Lens

Turns private documents and selected public-web material into a knowledge base that gets better as people use it.

CatalogsManuals, filings, PDFs, images, and folders. Extraction and OCR run in the background.
Web probesFinds candidate sites, grades them, and crawls the ones worth keeping.
SearchHybrid retrieval with reranking scores, source links, and streamed summaries.
API accessScope application keys to specific catalogs or workspaces.
Live Web application and APIGo · Qdrant · Postgres
More on Eidonix Lens
WAR
Whispers Across Realms Two realms that rarely talk. The floor speaks EtherNet/IP, S7comm, ADS, and FINS. Everything upstream speaks REST, MQTT, and Kafka. WAR ties IT and OT together, and it runs in seven factories today.
WarLink7 factories

Reads the PLCs and republishes the data everywhere else it is needed.

  • Talks to the controls — Allen-Bradley Logix, Siemens S7, Beckhoff ADS, and Omron FINS.
  • Publishes upstream — REST, MQTT, Kafka, and Redis.
  • Soft UDTs — Raw tags grouped into meaningful structures, so downstream systems are not reading addresses.
  • Rules engine — Publishes, webhooks, and writebacks fired on PLC conditions.
Go · Single binary · TUI
WarAlert7 factories

Turns process conditions into messages that reach a person.

  • Watches what matters — PLC tags, ping targets, and WarLink sources.
  • Alert chains — Conditions, timers, schedules, and gate logic combined into a chain.
  • Reaches people — SMS, email, WhatsApp, and webhook delivery.
  • Built in the browser — Chains are configured and tested from a web interface, not a config file.
Go · Web UI

Also in the workshop

go-llm-proxyllm.eidonix.com

One endpoint for every model your tools need.

  • Protocol translation — Anthropic Messages, OpenAI Responses, Chat Completions, and Bedrock Converse, translated automatically so any client reaches any backend.
  • Model multiplexing — Local GPU servers, cloud APIs, and third-party providers behind a single model list.
  • Documents and images — Text extraction from PDFs with an OCR fallback for scans. Images described for models that cannot see.
  • Search and MCP — Web searches run server-side and the results are injected, with an MCP endpoint for agent clients.
  • Key management — Proxy keys carry per-key model restrictions. Backend credentials never leave the server.
Go · MCP · SQLite
eMaint ExplorerIn use

Analytics on top of eMaint X4 maintenance data.

  • Syncs the source — Work orders, charges, PM schedules, and equipment records pulled from the eMaint API.
  • Scores the fleet — Health scoring and KPI trending across sites and over time.
  • Captures what was already solved — Every historic work order and the fix that closed it stays searchable in plain language. A technician describes the symptom and finds the last three times somebody dealt with it, and what worked.
  • Reviews PMs — AI-assisted review of preventive maintenance schedules.
  • Handles multiple sites — Per-user site access and a managed sync queue.
Go · Postgres · pgvector
AndonIn use

Live line status on wall-mounted displays.

  • Screen designer — Cells, presses, buffers, arrows, and headers laid out on a full HD canvas.
  • Live machine state — Decoded from PLC bitfields and streamed from WarLink.
  • Shift aware — Planned minutes per hour, so breaks and planned downtime do not read as faults.
  • Runs standalone — Each station runs on its own, with backup and restore from S3 or a central server.
Go · SQLite · WarLink
ShingoIn use

Automated material transport between storage and the line.

  • Request by type — Operators ask for what they need. The system picks the bin, routes a robot, and tracks delivery.
  • FIFO by default — The oldest eligible material always goes first, enforced by the system.
  • Chain of custody — Every bin carries a QR code scanned at pickup to confirm identity.
  • Survives the network — Edge stations keep tracking local state and queue messages when the link to core drops.
  • Vendor independent — The robot fleet sits behind an interface, so changing vendor does not touch dispatch.
Go · Kafka · Postgres
VibemonDeployed

Vibration and condition monitoring for rotating equipment.

  • Collects continuously — Sensor data from plant equipment into object storage.
  • Keeps trends readable — Long time series reduced and aggregated so months of data stay legible.
  • Warns early — Developing faults surfaced while the repair can still be scheduled.
Python · S3
TicketmaxIn use

Prints markdown straight to thermal receipt printers.

  • Real formatting — Headings, bold, underline, tables, images, QR codes, paper cuts, and the buzzer, from a plain .md file.
  • Any connection — TCP, USB, or serial, with any ESC/POS printer.
  • Tunable output — Paper width and line density configurable per job.
  • Scriptable — Reads a file or stdin, so it drops into an existing work order flow without glue code.
Go · ESC/POS
AkashicEarly

Structured reporting that rolls up without losing the original.

  • Submit, do not email — People submit to a manager they select. Each level consolidates what is beneath it.
  • No telephone effect — Any summary line drills back to the submission it came from.
  • Themes across the org — Recurring topics extracted across submissions and attributed to author, unit, and period.
  • Scope enforced — Visibility is checked on every read, not just on lists.
Go · Svelte · Postgres · Qdrant
DmatixEarly

Data Matrix code generation for part marking.

  • Standard sizes — ASCII payloads encoded across the standard Data Matrix size range.
  • Correct by construction — Code word capacity and error correction layout handled per size.
  • Small — Dependency-light, so it embeds in a labelling or marking step.
Python

Team

Built For Manufacturers

By people who manufacture.

US manufacturing has to get more competitive. That evolution starts on the floor, in the hands of the people who already know the work. Transformation isn't something you buy from a consultant; you build it one piece at a time, with Eidonix.

Eidonix was created by people who carry responsibility for performance, which is a different set of incentives than selling software.

Vanderbilt·Harvard·Toyota·Tier 1
Mechanical EngineeringVanderbilt
FinanceHarvard
Data AnalyticsHarvard

Building cars since 2005.