Automated neural net architecture discovery
KeplrAI gives every critical asset in a plant its own maintenance intelligence. Assets predict failures, trigger parts procurement, and coordinate repairs — across downstream and midstream.
Automated neural net architecture discovery launched on June 5, 2017 with 5 votes and more than 50% of that year's launches. The site was still online in September 2026, 9 years on.
What it does
Critical assets stream pressure, temperature, and vibration into historians no one reads. Maintenance runs on calendars and tribal knowledge. Every asset learns its own failure signatures and predicts the next breakdown. An AI agent then coordinates the response: parts, work orders, dispatch. Every repair makes it sharper. One continuous loop per asset. Field data flows back into the model. Every repair makes the next prediction sharper. Plug into the plant's existing DCS, SCADA, PLCs, and historians (PI, Aspen IP.21, Honeywell PHD). Read-only integration. No rip-and-replace. Plug into the plant's existing DCS, SCADA, PLCs, and historians (PI, Aspen IP.21, Honeywell PHD). Read-only…from cusp.keplr.io
Does a similar job
all alternatives →
API for free deep learning models2016 · openapi.keplr.io · ▲26KeplrAI gives every critical asset in a plant its own maintenance intelligence. Assets predict failures, trigger parts procurement, and coordinate repairs — across downstream and midstream.
Hyperparameter Optimization as a Service2016 · keplr.io · ▲6KeplrAI gives every critical asset in a plant its own maintenance intelligence. Assets predict failures, trigger parts procurement, and coordinate repairs — across downstream and midstream.
Applying the Unix philosophy to neural networks2019 · github.com · ▲251Neural network inference the Unix way. Contribute to cloudkj/layer development by creating an account on GitHub.
- ARA realtime dashboard for Keras neural nets2016 · tryhera.com · ▲87
Cortex – machine learning infrastructure for developers2019 · github.com · ▲86Production infrastructure for machine learning at scale - cortexlabs/cortex
Set of trained deep learning models for computer vision2016 · github.com · ▲127Keras code and weights files for popular deep learning models. - fchollet/deep-learning-models
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Show HN post ↗
Launched alongside, June 2017
the whole month →- GP
Work · 2017 · demandrush.com
Monica helps you remember the people you care about: what is happening in their life, important dates, previous conversations, and when to get back in touch. Private, open source, self-hostable.
Dev tools · 2017 · monicahq.com
The growth guide by DemandCurve.com and Julian Shapiro
Growth · 2017 · julian.com