00 ·openhorizon documentation
The cognitive layer for physical AI
Give robots and autonomous machines perception, spatial memory, and real-time reasoning. Everything you need, from first install to production deployment.
getting_started.sh
ready$ pip install openhorizon
✓ openhorizon 0.1.0 installed
$ openhorizon run demo
start hereQuickstartInstall the SDK and stream structured perception from a sample dataset in minutes.
perception.rt
liveLIDAR
RGB-D
RADAR
IMU
▸ 6 streams fused · 11.4ms
understandThe cognition loopHow sense → remember → reason turns raw sensors into grounded action.
Core concepts
Every OpenHorizon-powered machine runs the same loop: perception turns sensor streams into structure, spatial memory persists it into a world model, and reasoning plans against both.
perception.rt
liveLIDAR
RGB-D
RADAR
IMU
▸ 6 streams fused · 11.4ms
sensePerceptionFrom camera, lidar, and IMU streams to objects, surfaces, and motion.
world_model.db
Δ commit▸ 3,214 objects · aisle_03 Δ committed
rememberSpatial memoryA persistent, queryable map of places, things, and how they change.
planner.rt
policy ok▸ predict4 intents · 3.1ms
▸ plan3 scored · best 0.92
▸ acttrajectory dispatched
perceive → act latency11.4 ms
reasonReal-time reasoningPlans grounded in live context, within real hardware latency budgets.
For your tools
These docs are built to be read by machines too: every page has a Copy Markdown button, and the full corpus is available at /llms.txt and /llms-full.txt for agents and LLM pipelines.