zylon-ai/private-gpt

Prefer upstream unless you specifically want a reduced, older codebase with less UI and backend complexity. This fork is best for narrow, controlled use cases, not for adopters who want current features or broad integration support.

Choose this fork only if you specifically want the Memory Cache backend and can accept an old, highly diverged PrivateGPT codebase. For a general private document-QA platform, upstream is the better default because this fork is stale and likely missing substantial newer functionality.

Choose this fork only if you value its older local-install/GPU tweaks and are comfortable owning the gap to upstream. For most adopters, upstream is the safer default because this fork is materially stale and likely missing many newer capabilities.

Prefer this fork only if its early ingestion-focused changes match your needs and you want a largely frozen snapshot. For most adopters, upstream is the safer choice because this fork is stale and far behind current development.

Choose this fork only if translation-focused behavior is the main requirement and you are willing to own long-term maintenance. For most adopters, upstream is the safer choice because this fork is much older and appears to have shed or missed substantial newer functionality.

Choose this fork only if you specifically want this exact snapshot. If you want the freshest upstream docs or fixes, use upstream instead.

Prefer this fork only if you specifically need its early ingestion and local-setup tweaks and are willing to own a stale codebase. For most adopters, upstream is the safer choice because this fork is far behind and has likely lost newer features, fixes, and backend support.

Choose upstream unless you specifically need this exact frozen snapshot; the fork adds no visible functionality and is slightly behind.