GStars
    facebookresearch

    facebookresearch/sam3

    #272 this week

    The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

    backend
    Python
    NOASSERTION
    12.1K stars
    1.8K forks
    12.1K GitHub watchers
    Updated Oct 22, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    Ranks #272 of 2,794 repositories GStars tracks this week (top 10%).

    The project lists 11 contributors on GitHub.

    Gained 46% fewer stars in the last 90 days than in the 90 days before.

    Use Cases & Benefits

    • Provides code and models for promptable segmentation of images and videos using text or visual prompts with the Meta Segment Anything Model 3 (SAM 3).
    • Enables open-vocabulary segmentation with a large concept set and improved discrimination between similar prompts, outperforming prior models on extensive benchmarks.
    • Use for building advanced image segmentation tools that recognize and segment objects based on natural language descriptions or visual cues.
    • Use for video object tracking and segmentation with interactive refinement using text and visual prompts in dynamic scenes.
    • Use for research and evaluation on large-scale open-vocabulary segmentation datasets like SA-Co for benchmarking segmentation accuracy and concept generalization.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    Other

    GitHub could not identify this license; read the LICENSE file before depending on it.

    Community files

    • README: present
    • Contributing guide: present
    • Code of conduct: present

    Watch-outs

    • License not identified by GitHub; read the LICENSE file before depending on it.
    • No GitHub releases; pin a commit or tag instead of a release.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    Meta Superintelligence Labs

    Excerpt from the facebookresearch/sam3 README on GitHub (NOASSERTION license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Forks

    1.8K+154

    Open issues

    365+21

    Compared with peers in Backend

    Fastest-growing repositories GStars tracks in this cohort for the week of Oct 18, by 7-day star growth

    View category →
    facebookresearch/sam3 compared with Backend repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    anthropics/claude-plugins-official43.9K+5.6K35—
    NationalSecurityAgency/ghidra93.2K+4.9K75today
    K-Dense-AI/scientific-agent-skills53.9K+4.0K7521 days ago
    akitaonrails/ai-memory12.8K+3.3K40today
    shiyu-coder/Kronos43.2K+2.4K75—
    facebookresearch/sam312.1K+075—
    Category median43.9K+4.0K75—
    Compare sam3 with claude-plugins-official, ghidra, scientific-agent-skills →

    Also by facebookresearch

    Other repositories from this maintainer that GStars tracks

    Discover Repositories

    Search across tracked repositories by name or description