Models on records
Gradient boosting on tables such as inspection and fleet data.
AI Development
XGBoost development services for models on tabular data
We have no published XGBoost build. Our Python 3.13 back ends hold the records such a model would learn from, and we say plainly that we have not trained one in a published build.
0Published builds on XGBoost
3.4.1Latest patch release, 14 Aug 2026
3.4.0Previous release, 4 Aug 2026
10 daysBetween those two releases
What we build
What we would take on with XGBoost
Models behind an API
A FastAPI service in front of a trained model.
Evidence beside the score
A prediction that shows what drove it.
Upgrades
Moves onto 3.4 and a supported Python version.
Architecture
Where XGBoost would sit
A boosted model on the fleet data
Data
PostgreSQL and PostGISStops, legs, geofences
MQTT telematicsPosition and engine data
Model
XGBoost modelWhere it would sit
FastAPIPython 3.13
Use
Dispatch consoleSixteen live screens
Illustration. A dashed outline marks where the technology would sit. We have no published build on it.
Releases
XGBoost 3.4 releases
The latest XGBoost releases
4 Aug 2026
XGBoost 3.4.0
The latest minor release.
14 Aug 2026
XGBoost 3.4.1
The latest patch release.
Source: XGBoost documentation, release notes, xgboost.readthedocs.io, checked 5 November 2026. The documentation names no minimum Python version.
Builds
The closest builds we can show you
Logistics, fleet operations
TruckFleet Labs
Stops, legs and telematics in PostGIS and Redis, the data a boosted model would learn from.
112 to 97 kmOne route after route sequencing
AI product, in-house
Sales OS
A graded brief with six scored axes, where every score carries its evidence.
1 creditOpens all six tabs of an account brief
Fit check
When XGBoost is the right call
Pick XGBoost when
- Your data is a table with many features
- You need a strong baseline fast
- You can explain the result to a user
Look elsewhere when
- You need a published XGBoost build to inspect, which we do not have
- The job is images or text, where deep learning fits
- You have too few labelled rows
Explore
Same job, other tools
Where we used it
Stack
What XGBoost usually sits beside
scikit-learnPython
Apache Airflow
Docker
PyTorch
KubernetesFAQs
What buyers ask first
Which XGBoost version is current?
XGBoost 3.4.1, a patch release from 14 August 2026. Version 3.4.0 came out on 4 August 2026.
Do you have a published XGBoost build?
No. We say so on the first call and show the nearest work, which is Python data builds with PostGIS and a sync queue.
XGBoost or scikit-learn?
XGBoost is a gradient boosting library and scikit-learn is a wider toolkit. We say which fits your data on the first call, and we have no published build on either.
Who owns the code and the cloud accounts?
You do, from the first commit. Repositories and cloud accounts stay in your name.
Tell us what your table has to predict
Thirty minutes on your data, your labels and your XGBoost version. No sales pitch.