Skip to content
Hot eventDeveloping

Brazilian developer releases experimental Aurora GeoXAI geospatial MVP

1 reports1 reporting sourcesUpdated 20 h ago

Start here

AI digest

A Brazilian developer, Impulso Digital Soluções em I.A. Ltda., has released Aurora GeoXAI v0.1.0, an experimental open-source Python MVP for inspecting geospatial images and producing traceable analysis reports. It runs locally on CPU without a GPU, token, database or paid service, and accepts PNG, JPEG, TIFF and GeoTIFF files up to 100 MB and 50 million pixels. The original code is under Apache-2.0. The baseline uses NumPy, Rasterio, Pillow and scikit-learn with deterministic MiniBatchKMeans on RGB previews; it is not a PyTorch deep-learning engine. The project states that model XAI, production and forensic use are explicitly unvalidated, and that it has no funding, partnership or certification from Finep, CDTI, MCTI, SETAD or MLCommons. A reference CI workflow exists in the docs folder but is not active, so no CI badge is shown.

Generated from reports · updated 20 h ago

Report timeline

Follow the reports to see the event from different sides.

November 15
  1. Hacker News · AI
    Aurora GeoXAI: An Experimental Open Geospatial AI MVP from Brazil

    An independent Brazilian developer has released Aurora GeoXAI v0.1.0, an experimental open Python MVP for geospatial image inspection and traceable analysis reports that runs locally on CPU. The baseline uses NumPy, Rasterio, Pillow and scikit-learn with deterministic MiniBatchKMeans on RGB previews; it is not a PyTorch deep-learning engine, and model XAI, production and forensic use are explicitly unvalidated. The project frames itself as a sovereignty manifesto answering official digital-sovereignty rhetoric with inspectable code, and declares no funding, partnership or certification from Finep, CDTI, MCTI, SETAD or MLCommons.

Heat for this event

Current, comparable range
6
Peak, comparable range
10November 15 21:00
Change in 24 hours
–

The trend compares the same participants over hours observed continuously, so its range can be narrower than the current heat count. Hover or tap the chart for hourly heat; the arrow keys move through it.