run-llama/llama_index

Prefer this fork only if you need its older tool-calling/doc-oriented snapshot or want a frozen experimental baseline. If you want current features, active maintenance, or low upgrade risk, upstream is the better choice.

Prefer this fork only if you need the older, simpler codebase or its early ingestion tweaks. For new work, upstream is the safer choice because this fork is stale and materially behind.

Prefer this fork if you need its added server, local-model, or backend-specific capabilities and are willing to own upgrade work. Prefer upstream if you want active maintenance, current fixes, and the broadest compatibility.

Choose this fork only if you need the older codebase or its legacy examples; choose upstream if you want an actively maintained, current LlamaIndex with newer integrations and ongoing fixes.

Prefer this fork only if you need its specific local fixes or a curated snapshot. If you want the full upstream integration surface and lower maintenance burden, upstream is the safer choice.

Prefer this fork only if you need a pinned, already-customized baseline and can accept missing newer upstream work. If you want current LlamaIndex capability or active maintenance, upstream is the better choice.

Prefer this fork only if you need its frozen, customized snapshot and are willing to own long-term maintenance. If you want current LlamaIndex capabilities or easier upgrades, upstream is the better default.