Ω
ODIN EDGEV1.0
Eon Robotics Ecosystem
Physical-AI Edge Infrastructure

Run physical AIwhere the work happens.

Deploy, manage, and route robot and vision models across local GPUs, facility clusters, and cloud. Offline-resilient, data-safe, unified runtime control from prototype to fleet.

Explore Architecture
Offline-capable runtime Data never leaves facility NVIDIA-certified
odin-agent@seattle-thor-01:~
LOCAL_AUTONOMOUS

$ curl -fsSL https://get.odinedge.com | sh

Downloading Odin Edge Node Runtime v1.0.2...

Checking compatibility with NVIDIA Jetpack SDK: [OK] CUDA 12.2 detected.

Generating node private key and issuing mTLS certificates...

$ odinctl auth login --token env_tok_seattle_0a911xf

✓ Node enrollment succeeded. Name: Thor-Jetson-01 [Seattle Facility]

$ odinctl deploy apply ./examples/hello-inference/deployment.yaml

✓ Staged 1 active deployment. Routing mode: LOCAL_PRIMARY. Local policy loaded.

Six Defensible Engineering Centers

The unified compute and inference plane built for industrial robots, camera grids, and physical workspaces.

Trusted Edge Runtime

A lightweight, memory-safe supervisor layer installed on customer computers. Manages CUDA context, validates schemas, signs outputs, and tracks sub-millisecond latencies.

Physical-AI Artifacts (OMP)

Odin Model Packages (OMP) sign and version neural weights, preprocessing specs, output schemas, camera calibration contracts, and safe motion bounds.

Intelligent Workload Router

A dynamic client-side router that decides where inference runs — local GPU, shared facility server, or cloud fallback — based on latency, data policy, and hardware capacity.

Sensor & Robotics SDK

Standardized adapter layer matching ROS 2, Fanuc, Kuka, or UR joint protocols to input observation formats with microsecond alignment.

Enterprise Release Governance

Automated canary deployments, live shadow execution comparisons, instant rollback triggers, and strict local-only policy enforcement for industrial safety.

Eon Robotics Integration

Odin provides the local GPU and model orchestrator; Eon monitors physical tasks, operator workflows, maintenance dispatches, and enterprise production outcomes.

Hardware-Neutral Deployment Architecture

Odin bridges high-performance hardware and flexible neural runtime configurations.

Eon Workspace

Task Coordination

Owns the customer workflows, facility models, target tasks, maintenance safety, and business dashboards.

Event: task.sort_started
Control FlowNATS JetStream
Odin Edge Core

Inference Routing

Coordinates local GPUs, manages cache, enforces security policies, and monitors execution latencies.

Route: local_gpu fp16
Local NVIDIA GPU

TensorRT within millisecond deadlines.

Facility Compute Pool

Lightweight K3s edge clusters.

Private/Cloud API

Secured remote routing with full policy data sanitization.

What happens after you launch?

1

Runtime Installed

Lightweight agent deployed on your edge hardware. CUDA, drivers, and mTLS configured automatically.

2

Node Enrolled

Your GPU node connects to your facility workspace. Telemetry streams live within seconds.

3

Model Deployed

Push OMP packages via canary or shadow mode. Policy router optimizes where inference runs.

4

Outcome Measured

Latency, accuracy, and drift tracked per deployment. Rollback or promote with one click.

Enterprise Pricing Built on Technical Metrics

No abstract usage formulas. Pay clearly for nodes and support SLA guarantees.

Developer

$0 / forever

Model testing, SDK prototyping, and single-cell trials.

  • 1 Managed Edge Node
  • 1 Facility Workspace
  • ONNX & PyTorch Runtimes
  • Community Support
Recommended
Team & Production

$150 /node/mo

Production inference with unified fleet canary management.

  • Unlimited Edge Nodes
  • TensorRT GPU Optimization
  • Intelligent Policy Router
  • Next-day Hardware Replacement
  • 99.9% Control Plane SLA
Enterprise

Custom / annual

Air-gapped facility requirements with on-premises storage.

  • 100% Air-Gapped Autonomy
  • Custom Robot/Camera Drivers
  • Hardware Certification Program
  • 1-Hour High-Priority SLA
  • SSO & Dedicated Audit Logs