GoKawiilYC-backed Hebbian Robotics launches open-source HFlow SDK for robotics data pipelines
Hebbian Robotics, part of YC's Summer 2026 batch, has released HFlow, an open source SDK designed to manage large-scale multimodal data pipelines for robotics and physical AI. The tool automates orchestration, versioning, quality checks, and provenance tracking for datasets combining video, sensor state, and action data, using MCAP as its standard input/output format. The project is currently pre-v1 but functional end-to-end for local use.
GoKawiil's interpretation of the reporting above, not reported fact.
Robotics teams often struggle with messy, fragmented data pipelines that make it hard to verify dataset quality or reproduce results, a bottleneck that slows progress compared to more mature data infrastructure in other AI fields. By open-sourcing tooling previously built in-house by large robotics labs, Hebbian aims to lower the barrier for smaller teams to build reliable, auditable training datasets for physical AI systems.
- HFlow is an open-source SDK for building robotics data pipelines with built-in quality checks.
- It standardizes on the MCAP format to handle synchronized video, state, and action data regardless of data source.
- The tool tracks provenance and renders pipelines as graphs, aiding auditing and reproducibility of datasets.
NVIDIA Jetson Orin Nano Developer Kit — If you're experimenting with robotics and physical AI pipelines like HFlow, the Jetson Orin Nano Developer Kit is the classic on-robot brain for running multimodal perception and control code. It's a compact way to capture camera and sensor streams from real hardware and feed them into the kind of data pipeline this article describes.
See NVIDIA Jetson Orin Nano Developer Kit on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.Source: github.com, 2026-08-31
Published there as: “Launch HN: Hebbian Robotics (YC S26) – Build scalable robotics data pipelines”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.