Luxonis
OAK 4: spatial AI camera that runs Linux, with up to 52 TOPS
Details
- External ID
- 46231792
- Source
- HN
- Company
- —
- Product
- Luxonis
- Website domain
- luxonis.com
- Launched
- Dec. 11, 2025
- Cohort
- —
- Upvotes
- 18
- Upvotes percentile
- 0.6354961832061069
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
Hey everyone. This is Hunter, CPO at Luxonis! We built OAK 4 (www.luxonis.com/oak4) to eliminate the need for cloud reliance or host computers in robotics & industrial automation. We brought Jetson Orin-level compute and Yocto Linux directly to our stereo cameras.This allows you to run full CV pipelines (detection + depth + logic) entirely on-device, with no dependency on a host PC or cloud streaming. We also integrated it with Hub, our fleet management platform, to handle deployments, OTA updates, and collect "edge case" (Snaps) for model retraining.For this generation, we shipped a Qualcomm QCS8550. This gives the device a CPU, GPU, AI accelerator, and native depth processing ISP. It achieves 52 TOPS of processing inside an IP67 housing to handle rough whether, shock, and vibration. At 25W peak, the device is designed to run reliably without active cooling.Our ML team also released Neural Stereo Depth running our proprietary LENS(Luxonis Edge Neural Stereo) models directly on the device. Visit www.luxonis.com to learn more!
Enrichment
- Theme
- lightweight and on-device AI runtimes
- Vertical
- Horizontal
- Function
- Hardware & robotics
- Audience
- B2B
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- spatial ai camera that runs linux
- Manually corrected
- False
Could you build this?
No Luxonis OAK 4 is custom physical hardware featuring stereo vision sensors, embedded Yocto Linux, onboard neural accelerator ASICs (52 TOPS), and industrial IP67 casing.
What it would actually take: Building this requires custom PCB layout, embedded Linux/BSP development, sensor fusion engineering (stereo CMOS + IMU synchronization), custom thermal and mechanical housing design, and low-level NPU/VPU driver optimization to run real-time neural stereo depth algorithms at low power.
Discussion
12 comments analyzed.
Competitors mentioned: Jetson Orin Nano, ZED cameras, RealSense cameras
Concerns raised: Root access and custom image building capabilities, Whether on-device compute is sufficient without host PC
Feature requests: OS-level support (currently enterprise-only), Native root access and custom containerized applications
Competitors
Other products that read as similar to this one — 28 launches clear the similarity bar, closest 8 shown.
Attention rank: #11 of 29 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 37 days after the earliest competitor.
- Vpzzo · ph · 2026-09-15 · 1 upvotes · similarity 0.37
- X4_VR · github · 2026-09-26 · 20 upvotes · similarity 0.36
- Dipole Labs: Shooting lasers to solve the billion-dollar bottleneck inside AI datacenters · yc · 2026-08-13 · 9 upvotes · similarity 0.36
- vaivar · github · 2026-09-15 · 7 upvotes · similarity 0.35
- dlss5-neural-amd · github · 2026-09-09 · 19 upvotes · similarity 0.34
- AMD-NR---OptiScaler · github · 2026-09-20 · 18 upvotes · similarity 0.34
- Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac · hn · 2026-07-29 · 919 upvotes · similarity 0.34
- LumaDock - Blackwell GPU VPS · ph · 2026-09-14 · 2 upvotes · similarity 0.33
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a hardware & robotics tool for Fintech yet.