Retriever is now open source
pip install retriever-coreGitHub →
Get started
Start with a camera.
Run the live webcam Flow graph from Retriever Hub. It detects red and blue objects, then streams the result to Rerun on your machine.
Camera demo from Hub
pip install "retriever-core[demo]"
retriever demo webcam --seconds 60 --visualize rerun --refreshThe command fetches openretriever/webcam-demo, opens your webcam, and logs detections to Rerun. Runtime only, no demos? pip install retriever-core.
Run the camera demo
Load the live webcam color-detection Flow graph from Hub and view its detections in Rerun.
Camera demo →
ConceptsLearn the concepts
Flows, clocks, and sync policies — and how one graph runs in-process for debugging or on a backend for real.
Runtime guide →
DebuggingDebug and replay
Render the graph, step it locally with normal breakpoints, record a run, and replay exactly what each node consumed.
Debugging guide →
ExamplesExplore robot examples
Perception, memory, language, and simulation examples in GoldenRetriever, plus reusable payload types through the Hub.
GoldenRetriever examples →
Pipeline visuals
