Metadata-Version: 2.4
Name: chronoscript
Version: 0.0.1
Summary: A temporal script for AI video comprehension (placeholder release for name claim)
Author: tbtomo
License: MIT
Project-URL: Homepage, https://github.com/dataclock-jp/ChronoScript
Project-URL: Repository, https://github.com/dataclock-jp/ChronoScript
Project-URL: Issues, https://github.com/dataclock-jp/ChronoScript/issues
Project-URL: Paper, https://doi.org/10.5281/zenodo.20334163
Project-URL: Paper Artifact, https://github.com/dataclock-jp/monte-carlo-pinpoint
Keywords: video,ai,temporal,comprehension,sync-map,transcription,screenshot,llm,vlm
Classifier: Development Status :: 1 - Planning
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Multimedia :: Video
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Dynamic: license-file

# ChronoScript

A temporal script for AI video comprehension.

> **Status (v0.0.1): Placeholder release for PyPI name claim.**
> The full functional release is expected within ~4 weeks of this placeholder.

## What ChronoScript will be

ChronoScript translates video into a time-indexed script that AI models (LLMs / VLMs)
can read directly. The full release will decompose video into:

- **High-quality frames** at moments of visual change (timestamp-named files)
- **Timestamped transcript** synced to those frames

This gives AI a *time axis* concept for video — something single transcripts or
color-degraded GIF keyframes cannot provide.

## Origin

Developed by [Dataclock](https://github.com/dataclock-jp) as a Python CLI built
around research on AI video comprehension. The coordinate-localization technique
*Monte Carlo Pinpoint* is published as a separate paper artifact:

- Paper / DOI: <https://doi.org/10.5281/zenodo.20334163>
- Paper artifact repository: <https://github.com/dataclock-jp/monte-carlo-pinpoint>

## Disambiguation

ChronoScript is not affiliated with, and is unrelated to:

- `sameeeeeeep/video2ai` (independent project sharing only the descriptive phrase)
- `frame-script/FrameScript` (video editing software)
- `floorsight.io/ChronoEye` (manufacturing assembly process analyzer)
- Other similarly-named projects in adjacent domains.

## License

MIT — see [LICENSE](LICENSE).
