Foremai
OverviewDigital TwinSimulation StudioFleet OrchestrationEdge RuntimeData Flywheel
ManufacturingWarehousing & 3PLHumanoidsRobot OEMsEnterpriseSecurity
Developers HubDocumentationSkill MarketplaceIntegrationsAPI ReferenceStatus
AboutCustomersCase StudiesCareersBlogPartners
Pricing
Customers
Sign in Book a demo
Developers

Build physical AI like software

The Fore SDK, CLI, and API let you train skills, run simulations, and orchestrate a fleet with the workflows you already know.

Book a demo Read the docs
Deploys on your robots Validated in NVIDIA simulation No hardware at risk
SDK

Train and deploy in Python

Compose twins, training runs, and deployments as code, versioned and reproducible.

deploy.py
from foremai import Fleet, Studio, Twin

twin  = Twin.load("vantek/line-a")
skill = Studio.train("machine_tend", twin=twin, envs=4096)
skill.validate(gates=["success>0.98", "no_collision"])

fleet = Fleet.connect("vantek/line-a")
fleet.deploy(skill)
fleet.run(goal="keep CNC-3 fed all shift")  # agentic
fore deploybash
$ fore init vantek/line-a
$ fore train machine_tend --envs 4096
$
✓ success 0.991 · 0 collisions
$ fore deploy machine_tend --fleet line-a
✓ live on 8 robots
CLI

Ship from your terminal

The fore CLI wraps the full lifecycle: init, train, validate, deploy.

Developer surface

APIs for the whole loop

Everything the platform does is available programmatically.

Fore SDK

Python-first library for twins, training, and fleets.

Docs

CLI

Scriptable lifecycle from init to deploy.

Docs

Fleet API

REST + streaming control of tasks and telemetry.

Docs

Skill packages

Version, sign, and publish reusable skills.

Resources

Webhooks

Subscribe to fleet events and exceptions.

Docs

Examples

Reference projects for common tasks.

Resources
12ms control loop
Jetson Thor / Orin
TensorRT compiled
OTA skill updates
Edge

Deploy to Jetson

Compile validated policies with TensorRT and run real-time inference on Jetson Thor / Orin at the edge.

  • One-command edge deployment
  • TensorRT-optimized inference
  • Offline-tolerant runtime
See how it works
Scale

Built for real workloads

12ms
edge inference
4096
parallel envs
30+
robot drivers
99.9%
API uptime
Integrations

Works with the stack on your floor

Vendor-agnostic across robots, controllers, and systems of record.

Robots & arms

Universal RobotsFANUCKUKAABBFetchBoston Dynamics

AMRs & humanoids

MiROTTOLocusAgilityApptronikFigure

Controllers & sensors

ROS 2PLCs / OPC-UAIntel RealSenseZividSICKCognex

Systems of record

SAPManhattan WMSBlue YonderNetSuiteSnowflakeDatabricks
Security & safety

Enterprise-grade, safety-first by design

Robots act in the physical world, so every skill is validated before it ever touches hardware.

SOC 2 Type II ISO 27001 GDPR ISO 10218 / RIA R15.06 SSO / SAML Audit logs

Safety gates

Every policy must pass success + collision + force limits in sim before deploy.

Encryption everywhere

AES-256 at rest, TLS 1.3 in transit, per-site key isolation.

Data residency

Run in your VPC or on-prem; telemetry never leaves your boundary.

SSO, SCIM & RBAC

SAML/OIDC, provisioning, and role-based access down to the cell.

Developer FAQ

Questions from builders

The SDK is Python-first, with a REST + streaming API you can call from any language. The CLI wraps common workflows.
Yes. Bring your own Isaac Sim/Lab cluster or use managed NVIDIA compute. Twins and skills are portable across both.
Developer accounts include a simulation sandbox so you can train and validate skills before connecting real hardware.
Get started

Start building on Foremai

Get SDK access and a simulation sandbox for your team.

Get accessRead the docs