Skip to main content

sam3

Segment Anything 3 — text-, point-, and box-prompted instance segmentation, plus a stateful streaming video tracker that carries object identity through SAM3's memory bank. Use when a workflow needs open-vocabulary masks from an RGB image or needs to follow one object across frames.

Source facts

Repository
graph-robots/open-robot-skills
Last source activity
July 2, 2026 at 19:26
Detected SKILL.md language
English
Stars
58
Forks
8

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer
6 files

Showing SKILL.md

SKILL.md
Source instructions · Read-only preview
namesam3
descriptionSegment Anything 3 — text-, point-, and box-prompted instance segmentation, plus a stateful streaming video tracker that carries object identity through SAM3's memory bank. Use when a workflow needs open-vocabulary masks from an RGB image or needs to follow one object across frames.