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.
AI assistant that can query visual datasets, search the FiftyOne docs, and answer general computer vision questions
| Date | Stars |
|---|---|
| 2026-07-24 | 255 |
| 2026-07-25 | 255 |
| 2026-07-28 | 255 |
| 2026-07-30 | 255 |
| 2026-07-31 | 255 |
| 2026-08-06 | 255 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# VoxelGPT
<div align="center">
[](https://discord.gg/fiftyone-community)
[](https://huggingface.co/Voxel51)
[](https://voxel51.com/blog)
[](https://share.hsforms.com/1zpJ60ggaQtOoVeBqIZdaaA2ykyk)
[](https://www.linkedin.com/company/voxel51)
[](https://x.com/voxel51)
[](https://medium.com/voxel51)
</div>
Wish you could search your images or videos without writing a line of code?
Want to extract insights from your data by asking in plain English? Now you
can! 🎉
VoxelGPT is a [FiftyOne Plugin](https://docs.voxel51.com/plugins/index.html)
that combines the power of large language models (LLMs) and large multimodal
models (LMMs) with [FiftyOne](https://github.com/voxel51/fiftyone)'s computer
vision query language, enabling you to filter, sort, semantically slice and ask
questions about your data using natural language. It can even perform
computations on your dataset for you — with approval, of course!
## Live demo
🚀🚀🚀 You can try VoxelGPT live at [gpt.fiftyone.ai](https://gpt.fiftyone.ai)!
## Capabilities
VoxelGPT is capable of handling any of the following types of queries:
- [Dataset queries](#querying-your-dataset)
- [Computation queries](#computational-queries)
- [FiftyOne library queries](#fiftyone-library-queries)
- [FiftyOne workspace queries](#querying-your-workspace)
- [General machine learning queries](#general-machine-learning-queries)
When you ask VoxelGPT a question, it will interpret your intent and determine
which type of query you are asking. If VoxelGPT is unsure, it will ask you to
clarify.
### Querying your dataset
https://github.com/voxel51/voxelgpt/assets/12500356/5728b067-defc-4db3-8cda-ad8da3523cf4
VoxelGPT can handle the following types of queries about your dataset:
- Answer questions about the schema of your dataset, fields, and runs that
have been performed
- Create a filtered view of your data by constructing and concatenating view
stages.
- Set the view in the FiftyOne App
- Perform aggregations over the entire dataset or a view into the dataset
You can ask VoxelGPT to search your datasets for you. Here's some examples of
things you can ask:
- Show me 10 random samples
- Show me high confidence false positive predictions
- Do I have any images with multiple people?
- What is the average brightness for my images that contain a cat?
Under the hood, VoxelGPT interprets your query and translates it into the
corresponding
[dataset view](https://docs.voxel51.com/user_guide/using_views.html). VoxelGPT
understands the schema of your dataset, as well as things like
[evaluation runs](https://docs.voxel51.com/user_guide/evaluation.html) and
[similarity indexes](https://docs.voxel51.com/user_guide/brain.html#similarity).
It can also automatically inspect the contents of your dataset in order to
retrieve specific entities.
#### Data schema queries
VoxelGPT can answer questions about the schema of your dataset, brain runs,
evaluation runs, and more. Here are some examples:
- What fields do I have in my dataset?
- Do I have any evaluation runs?
- What model did I use to similarity index my dataset?
#### Object detection queries
If your dataset contains one or more
[`fo.Detections`](https://docs.voxel51.com/user_guide/using_datasets.html#object-detection)
field(s), VoxelGPT can filter or match based on the size (relative and
absolute) of bounding boxes, and on the number ofExcerpt of 23,525 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:3db32c5d37064837, topic:computer-vision, desc:computer vision, readme:computer vision
matched fp:3db32c5d37064837, topic:deep-learning
matched fp:3db32c5d37064837, topic:llm
matched fp:3db32c5d37064837, topic:chatgpt