SDKs for Physical AI.

Five SDKs, each grown from a research track at AHOY Labs. Three run in production across AHOY and partner products. Two are moving out of research.

Live

Vision

Cameras in, detections, tracks, counts and events out. Govern the data, gate the model, run it on your own GPUs.

Live

Knowledge and reasoning

Knowledge graph + RAG, so your applications reason over private data with every answer traceable to its source.

Live

Voice

Every stage of the voice pipeline, self-hosted: clean, transcribe, identify, reason and speak.

Coming soon

Security

Secure data tokenization and orchestration at scale. Currently in development.

Coming soon

Generative AI

Multimodal generative AI capabilities for diverse applications. Currently in development.

Swipe for all 5

In the AHOY stack

Where each SDK plugs in.

Five layers, from sensing to infrastructure. The lab builds the first two; AHOY runs the rest.

1.0
Perception
Reads vision, audio and sensor data at the edge.
Perception, Voice
2.0
Reasoning
Builds context with knowledge graphs, tuned to your data.
Data Intelligence
3.0
Decisioning
Picks the best action at machine speed.
AHOY platform
4.0
Execution
Orchestrates assets and workflows live.
AHOY platform
5.0
Infrastructure
Edge, on premises, sovereign or public cloud.
AHOY platform

Get started

Research that leaves the lab and runs on your terms: your hardware, your data, your sovereignty.