Core runtime APIs
Connect voice state, voice processing, knowledge retrieval, memory and runtime events.
DEVELOPER PLATFORM / SYSTEM 08
Connect the cognitive layer to the product you already own.
Integrate IronHeart voice, memory, knowledge, event hooks and robot runtime controls through APIs, SDKs and server-side adapters.
THE OPERATING PROBLEM
From model output to dependable behavior.
IronHeart.AI is infrastructure, not a replacement for the partner’s application, robot controls or customer experience. APIs and server-side adapters connect cognitive modules to the systems already responsible for identity, hardware, business rules and observability.
Teams can begin with managed realtime voice and knowledge APIs, then introduce persistent memory, event hooks and hardware adapters as the product matures. Edge and private deployment are scoped around the target hardware and data boundary.
The integration contract keeps drafts and published behavior separate so a failed external sync does not destroy configuration work or an existing production version.
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.
Adapter boundary
Validate connections and push published configuration from server-side integration code.
Deployment lifecycle
Test, publish, inspect status and roll back versioned robot behavior.
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
Authenticate
Create server-side credentials and define team and robot scope.
Configure
Create the robot profile, modules, policies and external connections.
Test
Run controlled conversations and inspect adapter status and events.
Publish
Deploy an immutable version to cloud, edge or private infrastructure.
BUY & DEPLOY
Start with the integration path that fits the product.
Primary buyer: Engineering teams, robot OEM platform groups and systems integrators that need a stable programmatic interface.
What to measure: Track integration time, connection reliability, end-to-end latency, configuration drift, failed sync recovery and release traceability.
Required controls: Server-side credentials, scoped adapters, schema validation, rate limits, published versions and audit logs.
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.
Where is the API documentation?
Current public documentation is available at docs.hidoba.com and production integration is scoped with the IronHeart team.
Can we integrate our own models?
Private and custom stacks can be scoped where the adapter and deployment requirements are defined.
What happens if an external adapter fails?
Drafts and published versions remain intact; the UI can show recoverable connection and sync states.
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.