Deployment ownership
Choose managed cloud, edge, offline or private infrastructure according to the environment.
CONTROL & TRUST / SYSTEM 07
Your robot.
Your infrastructure.
Your data.
Keep control over robot data, runtime location, model selection, retention and action policies across edge and private deployments.
THE OPERATING PROBLEM
From model output to dependable behavior.
A cognitive system can handle identity, memory, voice and environmental signals. That makes architecture and governance product requirements, not a legal appendix.
IronHeart.AI supports deployments where data can remain on-device or inside customer-controlled infrastructure. Teams decide which models run where, what is retained, who can publish behavior and which actions the runtime may invoke.
The objective is operational autonomy: avoid making core functionality dependent on a mandatory third-party cloud while preserving observability, version control and human responsibility.
What IronHeart sells
A configurable cognitive runtime—not a one-size-fits-all robot personality. Partners purchase managed Cloud API access or scope edge, offline, private-cloud and OEM production licensing with integration support.
Data boundaries
Configure where interaction data, knowledge and memory are processed, stored and deleted.
Action governance
Use roles, version history, allowlists and audit events around consequential runtime changes.
THE COMPLETE COGNITIVE LOOP
Six modules.
One interaction state.
A useful embodied system cannot treat voice, memory and action as unrelated calls. IronHeart coordinates the modules around the live person, environment, role and task.
Each module can be configured per robot or product while published versions preserve a reproducible operational state.
01Perception
02Realtime voice
03Persistent memory
04Personality
05Gaze
06Actions
Classify
Map data, users, actions and regulatory requirements for the deployment.
Place
Select cloud, edge and private components for each processing path.
Govern
Apply access, retention, publication and action policies.
Audit
Review configuration versions, deployments and runtime events.
BUY & DEPLOY
Start with the integration path that fits the product.
Primary buyer: Enterprise, government, healthcare, industrial and OEM teams that need explicit control over data and runtime operation.
What to measure: Validate tenant isolation, role enforcement, retention, recovery, audit completeness and safe degraded operation.
Required controls: Team roles, private storage, secret isolation, runtime location, memory policy, action allowlists and immutable published versions.
Cloud API
Prototype and launch with managed realtime runtime services and the published API plans.
Review pricing →Edge & Offline
Scope interaction-critical components for supported device or nearby edge hardware.
Discuss edge deployment →Private Cloud
Run inside customer-controlled infrastructure with an enterprise integration agreement.
Request enterprise scope →| Foundation model for | Social interaction across perception, voice, memory, personality, gaze and actions. |
|---|---|
| Partner retains | Hardware, customer experience, business rules, data policy, safety authority and go-to-market. |
| IronHeart provides | Runtime configuration, cognitive modules, adapter contract, versioned publication and deployment support. |
| Commercial path | Cloud API subscription for evaluation; custom scope for edge, offline, private cloud and OEM production. |
FAQ
Questions before integration.
Does IronHeart require data to be sent to a public cloud?
No. Edge and private deployment options are designed for customer-controlled processing paths.
Are external API keys exposed to the browser?
Production integrations should keep secrets in server-side or infrastructure-level configuration.
Can a published configuration be rolled back?
Versioned publication allows teams to restore prior behavior through a new audited release.
BUILD WITH IRONHEART
What should your robot become?
Tell us about the embodiment, use case and deployment constraints. We will map the fastest evaluation path.