STO-WARP
Star Trek Online screenshot recognition + ML training, distributed as a standalone Python package.
What is this?
STO-WARP combines two tools in one package:
WARP (Weaponry & Armament Recognition Platform) — reads your in-game screenshots from the PC version of Star Trek Online and automatically fills in your SETS build. Detects equipment, traits, bridge officers, and ship information using computer vision and machine learning. Console screenshots (PlayStation, Xbox) are not supported.
WARP CORE — trainer interface built into WARP. Review and correct recognition results, confirm annotations, and contribute corrections to the community model so recognition improves for everyone.
Technology
- WARP — recognition pipeline (OCR + layout detection + icon matching). Reads STO screenshots and emits structured slot/item results.
- WARP CORE — Qt trainer UI for reviewing recognition output and fine-tuning the EfficientNet / MobileNetV3 models that drive WARP.
Install
The recommended way to install sto-warp is via our universal installation scripts, which will automatically configure an isolated environment using pipx.
Linux / macOS:
curl -sSL https://raw.githubusercontent.com/raman78/sto-warp/main/install.sh | bash
Windows (PowerShell):
Invoke-WebRequest -Uri "https://raw.githubusercontent.com/raman78/sto-warp/main/install.ps1" -OutFile "install.ps1"; .\install.ps1; Remove-Item "install.ps1"
Windows (.exe installer):
Prefer a traditional installer? Download the latest sto-warp-<version>-setup.exe from
the Releases page —
no Python or terminal required. See INSTALLATION.md for details.
On first launch sto-warp registers itself in your system menu — Start Menu on Windows, Launchpad / Spotlight on macOS, Activities / KRunner on Linux — so subsequent runs can be started by clicking the icon instead of opening a terminal.
For manual installation methods and more details, see INSTALLATION.md.
Data and models
On first run sto-warp downloads:
- ML models (
icon_classifier.pt,screen_classifier.pt) from the Hugging Face hub. - Cargo / ship / trait JSON from public STO data repositories, including
the community
STOCD/SETS-Data. More than one source is tried in turn, so one of them being briefly unreachable does not stop the download. - Community knowledge (
knowledge.json), admin icon equivalence map, and a seed tarball of confirmed crops.
A small setup splash blocks the launcher on the very first start
until all of the above finish, so the application opens with a
complete data set. On every later run the cache is refreshed
silently in the background. Everything is cached under
~/.config/warp/ (or $XDG_CONFIG_HOME/warp/ when set). Nothing is
committed to this repository. See docs/WARP_GUIDE.md for the
user-facing walkthrough and docs/SYNC_ARCHITECTURE.md for the
technical view.
License
GPL-3.0 — see LICENSE.
Project docs
- INSTALLATION.md — install methods (pipx,
.exeinstaller, native packages). CHANGELOG.md— release notes.PROJECT_CONTEXT.md— design context.CLAUDE.md— repository rules for AI-assisted development.docs/— technical deep-dives (BOFF / trait / ship-info detection, ML pipeline, …), indexed indocs/README.md.
1 maintainer
Metadata
1 maintainer
Release files for sto-warp 1.0.37
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| sto_warp-1.0.37.tar.gz | 1.2 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| sto_warp-1.0.37-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 2.5 MB
Release files / sto_warp-1.0.37.tar.gz
| Download URL | sto_warp-1.0.37.tar.gz |
|---|---|
| Size | 1.2 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9aaa4d72cccbc58c8a9db84aef2245bc3ce2cbffe141c97ee89ad8d6bcf76213
|
|
BLAKE2b-256 checksum How to use checksums |
dc32cef5ad0d37e826c467914a01ab518210a7ac1080e35c90cb3d268ef5704b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 5, 2026.
Transparency logRelease files / sto_warp-1.0.37-py3-none-any.whl
| Download URL | sto_warp-1.0.37-py3-none-any.whl |
|---|---|
| Size | 1.3 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
277d7c94a4fc6e5155888cbbf5fa49708ee8f9116c5ba41dac0b86f132d8d886
|
|
BLAKE2b-256 checksum How to use checksums |
757a29f68113b8d81e5d4a38c807dab1979d142e29eb0f9ac4e0da37ffcd0c8b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 5, 2026.
Transparency log
