# locate-anything

> Self-hosted web UI for NVIDIA LocateAnything-3B: find objects, text, and UI elements in images via plain-language prompts on your GPU.

- **Category:** AI
- **Licence:** Apache-2.0
- **Latest version:** v0.1.3
- **Open source:** oss
- **Languages:** Typescript, Python
- **Platforms:** Docker Compose
- **Tags:** Machine Learning, Ocr, Nvidia, Gpu, Object Detection, Cuda, Typescript, Docker, React, Fastapi, Computer vision, Self Hosted, Tailwindcss, Web Ui, Vision Language Model, Open Vocabulary, Grounding, Phrase Grounding, Document Layout, Gui Grounding, Bounding Boxes, Open Vocabulary Detection, Locate Anything

## Description

locate-anything provides a sleek, mobile-friendly web interface wrapping NVIDIA's LocateAnything-3B vision-language model. You upload an image, enter a natural-language prompt, and receive bounding boxes for object detection, phrase grounding, text detection and OCR, document layout analysis, GUI element grounding, and pointing. The interface includes three speed/quality modes (fast, hybrid, slow), preserves search history for re-running, and offers a GPU preflight check. It requires an NVIDIA GPU with Ampere or newer architecture and roughly 12 GB of VRAM, deployed through Docker Compose with prebuilt images from GHCR or a local build. The underlying model carries a non-commercial license for academic and research use, while the interface code is Apache-2.0.

## Links

- [Homepage](https://github.com/gammahazard/locate-anything)
- [Docker](ghcr.io/gammahazard/locate-anything-backend)
- [GitHub repository](https://github.com/gammahazard/locate-anything)

---
Source: https://selfhost.directory/project/locate-anything