YavorGIvanov/sam.cpp

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1275 stars · 62 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A pure C/C++ implementation of Meta's Segment Anything Model (SAM) for image segmentation inference, built on the ggml tensor library. It converts PyTorch checkpoints to ggml format and runs segmentation locally with an optional SDL2-based GUI.

Use cases

• run segment anything model locally without python
• segment objects in images using C++
• convert SAM pth checkpoints to ggml format
• on-device image segmentation inference
• interactive image segmentation with a native GUI

When to choose

• you need SAM inference in C/C++ without a Python runtime
• you want lightweight, dependency-minimal local segmentation
• you're integrating SAM into a native C++ application

When to avoid

• you need training or fine-tuning of SAM
• you want GPU-accelerated production inference at scale
• you need the latest SAM features or active development

Facets

library · maturity maintenance

machine-learning computer-vision image-processing llm-inference computer-vision image-processing machine-learning windows cpp cross-platform segment-anything ggml image-segmentation inference sdl2 linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="YavorGIvanov/sam.cpp")