TabbyML/tabby
Read the upstream summary on the left, browse the cached forks below it, and load each fork comparison into the right-hand panel.
TabbyML/tabby
TabbyML/tabby is an actively maintained, self-hosted AI coding assistant. It targets on-premises deployment, advertises an open API for integration, and supports consumer-grade GPUs. The repository is large and multi-language, with Rust, Node.js/JavaScript, container tooling, and a documentation site.
Jump straight into Discofork's strongest cached fork picks, or open a compare view in one click.
Choose a fork to inspect
Prefer upstream unless you explicitly want an older, frozen copy. This fork adds no visible functionality and is materially behind current upstream.
Choose this fork only if its specific integrations and product direction match your deployment needs. If you want the current upstream feature set and a lower-maintenance path, upstream looks safer.
Choose this fork only if you need its specific custom provider/auth/indexing changes and are comfortable losing upstream chat/knowledge/page capabilities. For most adopters, upstream is safer because it is active and much less divergent.
Choose this fork if you specifically want a VSCode-first, local-context-oriented Tabby and do not need the newer upstream platform features. Choose upstream if you want active maintenance, broader server functionality, and ongoing feature development.
Prefer this fork only if you need its specific 2024-era behavior or the added admin/auth endpoints; otherwise upstream is the safer choice because this fork is stale and materially behind.
Choose this fork only if you need its specific customizations and are willing to own a large rebase gap. If you want current Tabby features or low-maintenance adoption, upstream is the safer choice.
Choose this fork only if its editor-plugin and prompt/indexing customizations are the goal. For most adopters, upstream is the safer default because this fork is far behind and likely requires substantial maintenance to stay current.
Choose this fork only if you want an almost-unmodified Tabby baseline. If you want the latest model-provider, auth, and indexing features, upstream is the better choice.
Prefer upstream unless you specifically need this older snapshot; the fork adds no visible capabilities and mainly lags behind current Tabby.