Your AI agent. Your equipment. Connected in 30 seconds.

40% of industrial AI projects get cancelled because agents can't talk to equipment. Forge connects them. 14 protocols. 18 manufacturers. One universal data layer. Your agent gets clean, normalized, governed data from any machine on the floor.

Get started free β†’ Rescue a stalled pilot, $25K β†’
claude mcp add --transport http forge https://mcp.foundrynet.io/mcp --header 'Authorization: Bearer YOUR_API_KEY'
forge.normalize_telemetry({ data: {"Spindle_Speed": 2200, "spd_load": 85}, oem: "fanuc" })
{ spindle_speed_rpm: 2200, spindle_load_pct: 85, coverage: 100%, confidence: 0.97 }
Your agent understands the machine. Took 30 seconds.

The problem

Industrial AI keeps failing. Here's why.

The Tower of Babel

Your factory floor speaks five protocols. Your AI agent speaks none of them. A Fanuc CNC speaks FOCAS. A Siemens PLC speaks PROFINET. A KUKA robot speaks KRL. Your agent sees raw bytes and gives up. 40% of agentic AI projects will be cancelled by 2027 (Gartner) because of this.

Dirty data kills agents

88% of AI pilots never reach production (IDC). The number one cause: the data is not AI-ready. Different vendors use different names for the same measurement. Different units. Different scales. Your agent can't tell if "4.2" means millimeters per second or inches per hour. Only 15% of enterprises have AI-ready industrial data (Fivetran 2026).

No governance, no trust

Your agent makes a decision. Nobody knows why. Nobody approved it. Nobody can prove what happened. In an industrial setting, that is not a bug, it is a liability. 84% of CIOs lack a formal process for tracking AI accuracy (Gartner).

The solution

Forge solves all three.

CONNECT

14 protocols: MQTT, Modbus TCP, Modbus RTU, OPC UA, SNMP, BACnet, ROS2, J1939/CAN, MAVLink, MTConnect, EtherNet/IP, PROFINET, REST, CSV. Point Forge at your equipment. It auto-detects the protocol and starts reading. No PLC programming. No sensor installation. No downtime.

NORMALIZE

16,908 cross-OEM field mappings across 18 manufacturer families. Your Fanuc's "Spindle_Speed" and your Haas's "spd_rpm" become one universal field: spindle_speed_rpm. Self-healing normalization handles tag renames, unit mismatches, and vendor quirks. Your agent gets clean, universal data from every machine.

GOVERN

Every agent action goes through a supervised approval workflow. Predictions create alerts. Alerts require human approval before execution. Every reading, prediction, and action is hash-chained and tamper-evident. Your AI operates with supervised autonomy, and you can prove everything that happened.

How it works

From raw protocols to working agent in four steps.

  1. 01

    Connect your equipment

    Forge reads from any PLC, controller, or sensor through 14 industrial protocols. No hardware to install. No PLC code to write. Your existing equipment is already compatible.

  2. 02

    Your data normalizes automatically

    Raw vendor tags become universal fields. 16,908 mappings. Self-healing handles the messy reality of factory floors: renamed tags, drifting sensors, offline equipment.

  3. 03

    Connect your AI agent

    One line. Your agent calls 30 MCP tools: normalize, predict, diagnose, calculate OEE, generate shift reports, manage work orders. Works with Claude, Cursor, LangChain, CrewAI, AutoGen, or any MCP-compatible client.

    claude mcp add --transport http forge https://mcp.foundrynet.io/mcp --header 'Authorization: Bearer YOUR_API_KEY'
  4. 04

    Govern and verify

    Every agent action is supervised and recorded. Your operations team sees what every agent is doing, approves actions, and has a tamper-evident record of everything that happened.

Built-in intelligence

What Forge does when no other agent is connected.

The kernel ships with a built-in intelligence agent that proves the platform works on your data. Everything below runs on the same normalized data layer your agents will use.

Predict
Failure predictions validated 30 hours before breakdown on NASA benchmark data. Per-machine calibration.
Operate
Real-time OEE. Energy consumption with anomaly detection. Automatic shift reports with an AI narrative.
Diagnose
Root-cause analysis using telemetry correlation and AI reasoning. Spare parts prediction with cost estimation.
Act
Supervised automations with an approval workflow. CMMS integration. Work order drafting with parts and costs.
18 manufacturers normalized| 366 canonical fields| 16,908 cross-OEM mappings| 30 MCP tools| 14 protocols

Deploy

Runs anywhere your equipment lives.

EDGE

Docker on any 4 GB Linux host, NUC, or industrial PC. Your data never leaves your building.

CLOUD

Hosted at forge.foundrynet.io. Instant sandbox. Full MCP gateway.

FLEET

AWS Greengrass component. Azure IoT Edge module. Deploy to thousands of devices through your existing edge infrastructure.

HYBRID

Edge for real-time intelligence. Cloud sync for fleet analytics and cross-site learning.

Pricing

Start free. Pay when agents go to production.

Forge Connect
Free
3 machines. Keyless sandbox. Instant access. All 14 protocols. All 30 MCP tools. Your agent talks to simulated equipment in 30 seconds. No credit card. No sales call.
Get sandbox key β†’
Forge Runtime
$999/month
Production deployment. 25 machines included. $29/machine beyond 25. All protocols. Governed agent execution. Tamper-evident work records. Deploys on Greengrass, Azure IoT Edge, or standalone Docker.
Start Runtime β†’
Runtime Enterprise
Talk to us
A standalone agent in a Docker container. Deploys in 30 seconds. Normalizes across every OEM family. No integration project. No consultants. No lock-in. It works or rip it out. Site license. On-prem deployment. SSO, audit exports, SLA, multi-site fleet management. AWS and Azure Marketplace available.
[email protected] β†’
Forge API
Pay per call from $0.01
For developers and AI agents. No subscription, no minimum. Free: identify, coverage, mapping. Then $0.01 normalize, $0.05 predict, $0.25 health index and OEE, $1.00 diagnose and shift report. Premium actions (work orders, exports, valuations, certificates) billed on every tier. At ~1,000+ calls/month, Runtime saves money.
Get API key, free β†’
Forge Monitoring
$49/machine/month
Our built-in agent, turnkey. Failure predictions, real-time OEE, shift reports, energy, AI diagnostics. For operators who want intelligence without building their own agent.
Start with the built-in agent β†’
Pilot Rescue
$25,000 fixed
Your industrial AI pilot is stalled on the data layer. We connect your agent to your equipment in one week. 14 protocols. Normalized. Governed. Recorded. Fee credited against Runtime Enterprise.
Rescue my pilot β†’

Verticals

One kernel. Every industry.

Same runtime. Different equipment. Pick your vertical.

AI agents for manufacturing

CNC, robotics, and mixed-vendor lines. Connect your agents to Fanuc, Siemens, Haas, ABB, KUKA, and 13 more through one data layer.

Explore β†’

AI agents for data centers

UPS, PDUs, CRAC units, and power systems. Your capacity planning and cooling optimization agents get normalized, verified data from every vendor.

Explore β†’

AI agents for energy

Solar inverters, wind turbines, battery storage, and grid assets. Cross-vendor normalization for your energy optimization agents.

Explore β†’

AI agents for cold chain

Refrigeration controllers across sites and vendors. Your compliance and quality agents get verified temperature data from every unit.

Explore β†’

Talk to us

See Forge on your equipment

Tell us what you're working with. We'll show you what Forge does with your data.

Or just email [email protected]. No sales pitch. Just a demo on your data.