- Home
- Image Annotation Software
- MakeSense.ai
MakeSense.ai
What it is
makesense.ai is a browser-based tool for labeling photos and preparing datasets for computer vision projects. It supports point, line, rectangle, polygon, and label annotations. Listed model-assisted options include YOLOv5, SSD pretrained on COCO, and PoseNet; users can also load their own YOLOv5 models exported in TensorFlow.js format. Supported exports include CSV, YOLO, VOC XML, VGG JSON, and COCO JSON, while imports include YOLO, VOC XML, and COCO JSON. Format support varies by annotation type, and some combinations are not yet available. The project says images are not sent to a server and that AI features run using TensorFlow.js. It works in a browser across operating systems and also documents local setup and Docker hosting at localhost:3000. The project describes it as suitable for small computer vision deep-learning projects and dataset preparation. It is free to use, licensed under GPL-3.0, and credits Piotr Skalski as author and copyright holder.
For and against
For
- Offers five annotation types, including polygons and labels.
- Model-assisted labeling includes YOLOv5, SSD, and PoseNet.
- Exports include CSV, YOLO, VOC XML, VGG JSON, and COCO JSON.
- Images are not sent to a server, according to the project.
- Local and Docker setup are documented.
Against
- Some annotation and import/export combinations are not supported yet.
- Custom models must be YOLOv5 exports in TensorFlow.js format.
- The project describes its focus as small computer vision projects.
The verdict
makesense.ai covers common image-labeling workflows with several annotation types, model-assisted options, and dataset exports. Check the format matrix for the specific annotation and import/export combination you need.
Who it suits
It suits people preparing labeled image datasets for small computer vision projects. It may also suit users who want a browser-based tool or documented local hosting options.
Plans and prices
Free
browser photo labeling · no image upload to server
Read 21 Oct 2026 · github.com
On the record
- AI models
- Its listed AI integrations include YOLOv5, SSD pretrained on COCO, and PoseNet.github.com · read 7 Oct 2026
- Annotation features
- The tool supports point, line, rectangle, polygon, and label annotations.github.com · read 7 Oct 2026
- API and SDK documentation
- The public documentation presents no product API or SDK; its documented extensibility is local code, model loading and inference-server connection.skalskip.github.io · read 21 Oct 2026
- Cross-platform
- The project describes itself as cross-platform because it runs in a browser across operating systems.github.com · read 21 Oct 2026
- Cross-platform use
- The project says it works in a browser across operating systems and requires no complicated installation.github.com · read 7 Oct 2026
- Custom models
- Users can load their own YOLOv5 models exported to TensorFlow.js format.github.com · read 7 Oct 2026
- Docker self-hosting
- The repository includes Docker instructions for running the application locally.github.com · read 21 Oct 2026
- Documentation
- The public documentation contains separate pages for imports, exports, shortcuts and local setup.skalskip.github.io · read 21 Oct 2026
- Export formats
- Supported exports include CSV, YOLO, VOC XML, VGG JSON and COCO JSON, depending on annotation type.skalskip.github.io · read 21 Oct 2026
- Image classification
- Image-level labels are available for classification tags.deepwiki.com · read 21 Oct 2026
- Implementation stack
- The application is written in TypeScript and uses React with Redux.github.com · read 21 Oct 2026
- Import formats
- Supported imports include YOLO and COCO JSON for rectangles and COCO JSON for polygons; other combinations are marked unsupported or not applicable.skalskip.github.io · read 21 Oct 2026
- Independent praise: privacy
- CheckThat.ai characterizes the tool as free, open-source, browser-based and processing data locally for privacy.checkthat.ai · read 21 Oct 2026
- Independent use
- Researchers have used MakeSense.ai in scientific image-labeling work, including X-ray scattering datasets.journals.iucr.org · read 21 Oct 2026
- Intended users
- The project describes the tool as suitable for small computer vision deep learning projects and dataset preparation.github.com · read 7 Oct 2026
- Latest release
- The releases page lists version 1.11.0-alpha dated 20 December 2022 as the latest release shown.github.com · read 21 Oct 2026
- Licence
- The code is released under the GNU GPL-3.0 licence.github.com · read 21 Oct 2026
- Limit: batch workflows
- The same paper reports that MakeSense.ai lacks batch labeling and similarity-based annotation suggestions.journals.iucr.org · read 21 Oct 2026
