Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
BoxMOT: Pluggable Python and C++ SOTA multi-object tracking modules with support for axis-aligned and oriented bounding boxes
| Date | Stars |
|---|---|
| 2026-07-24 | 8249 |
| 2026-07-25 | 8249 |
| 2026-07-28 | 8253 |
| 2026-07-30 | 8258 |
| 2026-08-06 | 8261 |
| 2026-08-15 | 8273 |
| 2026-08-18 | 8272 |
| 2026-08-19 | 8273 |
| 2026-08-20 | 8274 |
| 2026-08-21 | 8273 |
| 2026-08-22 | 8276 |
| 2026-08-23 | 8275 |
| 2026-08-24 | 8277 |
| 2026-08-25 | 8279 |
| 2026-08-26 | 8280 |
| 2026-08-27 | 8283 |
| 2026-08-28 | 8284 |
| 2026-08-29 | 8285 |
| 2026-08-30 | 8284 |
| 2026-08-31 | 8285 |
| 2026-09-02 | 8284 |
| 2026-09-03 | 8283 |
| 2026-09-04 | 8285 |
| 2026-09-05 | 8287 |
| 2026-09-06 | 8287 |
| 2026-09-08 | 8289 |
| 2026-09-09 | 8292 |
| 2026-09-10 | 8293 |
| 2026-09-13 | 8292 |
| 2026-09-14 | 8293 |
| 2026-09-16 | 8295 |
| 2026-09-17 | 8298 |
| 2026-09-18 | 8299 |
| 2026-09-19 | 8300 |
| 2026-09-20 | 8301 |
Today
+1 stars today
This week
+9 stars this week
This month
+28 stars this month
Momentum
48.0
growth rate 0.11%/day
<div align="center" markdown="1">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="docs/logo/logo_white.png">
<source media="(prefers-color-scheme: light)" srcset="docs/logo/logo_black.png">
<img width="400"
src="docs/logo/logo_black.png"
alt="BoxMOT logo">
</picture>
<p><b>Pluggable Python and C++ multi-object tracking modules for axis-aligned and oriented bounding box detections from any model.</b></p>
[](https://github.com/mikel-brostrom/boxmot/actions/workflows/ci.yml)
[](https://badge.fury.io/py/boxmot)
[](https://pepy.tech/project/boxmot)
[](https://github.com/mikel-brostrom/boxmot/blob/master/LICENSE)
[](https://badge.fury.io/py/boxmot)
[](https://doi.org/10.5281/zenodo.8132989)
[](https://colab.research.google.com/drive/18nIqkBr68TkK8dHdarxTco6svHUJGggY?usp=sharing)
[](https://discord.gg/tUmFEcYU4q)
[](https://deepwiki.com/mikel-brostrom/boxmot)
<a href="https://trendshift.io/repositories/13239" target="_blank"><img src="https://trendshift.io/api/badge/repositories/13239" alt="mikel-brostrom%2Fboxmot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"></a>
---
[Docs](docs/index.md) • [Installation](docs/getting-started/installation.md) • [Modes](docs/modes/index.md) • [API Reference](docs/python/index.md) • [Trackers](docs/trackers/index.md) • [Contributing](CONTRIBUTING.md)
<img width="640"
src="https://github.com/mikel-brostrom/boxmot/releases/download/v12.0.0/output_640.gif"
alt="BoxMOT demo">
</div>
BoxMOT provides independent detector, segmentor, appearance-encoder, and tracker
components built around validated Torch structures. Pipelines compose those
components; the CLI owns sources, outputs, materialized datasets, evaluation,
tuning, research, and ReID workflows.
## Why BoxMOT
- One interface for `track`, `materialize`, `time-variant`, `eval`, `tune`, `research`,
`train-reid`, `eval-reid`, `compare-reid`, `export`, and native `build`
workflows.
- Swappable components with explicit capabilities and requirements.
- Immutable, keyed Parquet builds with reusable detections, masks, and
embeddings.
- Support for both AABB and OBB tracking paths.
- Optional production-ready native C++ tracker implementations with the same metrics as the Python path, opted into via `--tracker-backend cpp` and embeddable in standalone C++ projects via CMake (see [Native C++ Integration](docs/native/index.md)).
- A structured Python API for embedding components and pipelines in applications.
## Installation
BoxMOT supports Python `3.10` through `3.13`.
```bash
pip install boxmot
boxmot --help
```
The default package uses the standard PyPI PyTorch build. Source checkouts and
CI can explicitly select the lockfile-backed `cpu` or `cu130` profile. For
those profiles and mode-specific extras such as `yolo`, `service`, `evolve`,
`research`, `onnx`, `openvino`, and `tflite`, see the
[installation guide](docs/getting-started/installation.md).
## Benchmark Results
<div align="center" markdown="1">
<!-- START TRACKER TABLE -->
<table>
<thead>
<tr>
<th rowspan="2" align="left"><sub>Tracker key</sub></th>
<th rowspan="2" align="center"><sub>Status</sub></th>
<th colspan="3" align="center"><sub>MOT17 ablation</sub></th>
<th colspan="3" align="center"><sub>SportsMOT val</sub></th>
<th colExcerpt of 12,915 characters
Read on GitHub
Mike
3.5k
46
mikel brostrom
46
40
24
20
15
11
10
Raif Olson · Dartmouth College
9
Johnny · NVIDIA · Spain
5
Justin Ruan · Taiwan
5
4
3
Chanwut (Mick) Kittivorawong · United States
3
mikel brostrom
3
Shanliang Yao · Yancheng Institute of Technology · China
3
3
Armin Mehri · Computer Vision Center · Spain
2
2
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:0d68e06232fad596, topic:yolo, desc:object tracking, readme:object tracking
matched fp:0d68e06232fad596, topic:tensorrt
matched fp:0d68e06232fad596, topic:deep-learning