LabelU vs Supervisely
LabelU
github.comSupervisely
supervisely.comSide by side
| Figure | LabelU | Supervisely |
|---|---|---|
| Price from | — | €199/mo |
| Free plan | — | Yes |
| Free trial | — | Yes |
| Open source | — | — |
| Web | Yes | Yes |
| Windows | Yes | — |
| macOS | Yes | — |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 0 | 3 |
| Spec score · AI Data Labeling Tools | 7.4 (#16) | 7.8 (#12) |
| Intended users | The README describes the platform as suited to annotation work supporting complex data analysis and model training. | The Community plan is described for open-source projects, individuals, ML researchers and small teams. |
Plans
In their own words
LabelU
LabelU is an open-source platform for annotating image, video, and audio data, with tools for both manual work and model-assisted labeling. Image annotations include 2D bounding boxes, semantic segmentation, polylines, and keypoints; video and audio support segmentation, classification, and information extraction. Users can load pre-annotated data and refine it, or use AI services to detect and segment image objects, including batch work with progress tracking. LabelU imports annotation data from S3-compatible storage such as AWS S3 and MinIO, and exports JSON, COCO, and MASK formats. Its model server exposes a unified HTTP API with POST / and GET /health endpoints. Local deployment uses Miniconda, Python 3.11, pip, and a server at http://localhost:8000/. SQLite is included, with MySQL installation and migration also supported. Reference models have stated hardware requirements: Florence-2 and GroundingDINO plus SAM ViT-B each need about 4GB VRAM; SAM 3 needs about 8GB and CUDA 12.6 or later. LabelU is free and released under Apache 2.0.
Supervisely
Supervisely is a computer vision platform for curating data, labeling images, video, 3D and medical imagery, and building production models. Its labeling workflows cover images, video, LiDAR and DICOM, with AI-assisted labeling and tracking. Teams can train, evaluate and deploy models, including through active-learning workflows. Data tools include search, visualization and quality statistics, plus connections to AWS, Google Cloud and Azure storage. A JSON API, Python SDK and AppEngine support integrations and workflow automation. Community is free with 5 GB of storage, 10,000 files and two members; projects in free teams are archived after 30 days of inactivity. Pro is listed at €199/mo, with 50 GB and 50,000 files; add-ons are available. Enterprise has custom pricing and can be self-hosted or cloud deployed, including on private networks without outside internet access. Supervisely says uploaded or generated customer data is private and not shared or used by the service. It was released in August 2017 and is headquartered in Tallinn, Estonia.