GStars
    TabbyML

    TabbyML/tabby

    Self-hosted AI coding assistant

    ai
    developer-tools
    codegen
    coding-assistant
    coding-language
    developer-experience
    gen-ai
    Rust
    NOASSERTION
    33.9K stars
    1.8K forks
    181 GitHub watchers
    Updated Nov 9, 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.

    The project lists 116 contributors on GitHub.

    Peaked at #42 in the weekly ranking the week of Apr 12, its best in the past year.

    Use Cases & Benefits

    • Provides a self-hosted AI coding assistant that integrates with IDEs to enhance developer productivity through code generation and contextual code understanding.
    • Enables on-premises deployment without cloud dependency, supporting consumer-grade GPUs and offering an open API for seamless integration with existing developer tools.
    • Use for teams seeking a private, secure alternative to cloud-based AI coding assistants to maintain code confidentiality and control over AI infrastructure.
    • Use for developers wanting to integrate AI-powered code completion and chat-based code assistance directly within popular IDEs like VSCode, Vim, and IntelliJ.
    • Use for engineering teams aiming to build a centralized knowledge engine that indexes internal documentation and code repositories to deliver precise, context-aware coding help.

    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.

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

    From the README

    You can find our documentation here.

    The easiest way to start a Tabby server is by using the following Docker command:

    For additional options (e.g inference type, parallelism), please refer to the documentation page.

    Excerpt from the TabbyML/tabby 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+18

    Open issues

    345+16

    Compared with peers in AI

    Fastest-growing repositories GStars tracks in this cohort for the week of Nov 8, by 7-day star growth

    View category →
    TabbyML/tabby compared with AI repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    D4Vinci/Scrapling101.1K+6.3K756 days ago
    thedotmack/claude-mem115.8K+4.7K75today
    heygen-com/hyperframes82.3K+4.0K75today
    harry0703/MoneyPrinterTurbo142.0K+3.8K753 days ago
    github/spec-kit149.2K+2.6K75today
    TabbyML/tabby33.9K—45—
    Category median115.8K+4.0K75—
    Compare tabby with Scrapling, claude-mem, hyperframes →

    Discover Repositories

    Search across tracked repositories by name or description