README.md
LlamaIndex is a data framework for LLM applications: load data, build indexes, and query them with retrieval-augmented generation or agentic workflows.
pip install llama-index
Explore / LlamaIndex
run-llama
LlamaIndex
Data framework for connecting custom data sources to LLMs — ingestion, indexing, retrieval.
51,752 7,972 Python MITupdated yesterday
Continue your stack
What teams reach for next — and why each earns a place beside LlamaIndex. Ranked by curator confidence.
Pairs well with
Ragas
Evaluation toolkit for your RAG and agent pipelines — faithfulness, relevance, and more.
Why it fitsEvaluate your RAG pipeline's retrieval and answer quality.
MemMachine
Long-term memory layer for AI agents — episodic (graph), profile (SQL) and working memory behind Python/TS SDKs, REST and MCP; ships LangChain, LangGraph, CrewAI and LlamaIndex integrations.
Why it fitsDocumented LlamaIndex integration — LlamaIndex retrieves from your data, MemMachine recalls what the user said and prefers across sessions; the two retrieval planes compose.
xberg
Rust-core document-intelligence engine with 15 language bindings: turns 96 formats — PDF, Office, images, audio, code — into clean text, tables and RAG-ready chunks. Library, CLI, REST or MCP.
Why it fitsXberg is a stronger document reader/extraction layer than LlamaIndex's built-in loaders; plug it in as the ingestion front-end (96 formats, OCR, transcription, chunking) and let LlamaIndex handle indexing, retrieval and query orchestration.
Alternative to See all + compare →
txtai
All-in-one AI framework around an embeddings database — dense, sparse, graph and relational fused — with pipelines, workflows, agents and MCP/web APIs. Python, bindings for JS/Java/Rust/Go.
Why it fitsSame job — the data-to-LLM framework layer. LlamaIndex bets on a vast connector ecosystem; txtai bets on one coherent embeddings database with pipelines and workflows built in.
cocoindex
Rust-core incremental indexing engine: declare Target = F(Source) in Python and it keeps vector/graph/relational targets fresh forever, reprocessing only the delta — with per-row lineage.
Why it fitsBoth connect LLMs to your data, at different layers: LlamaIndex is the retrieval framework (loaders, indexes, query engines) typically run as batch ingestion; CocoIndex is the incremental sync engine that keeps whatever store you target continuously fresh, delta-only, with lineage.
PageIndex
Vectorless, reasoning-based RAG — builds a hierarchical tree index from long documents so an LLM retrieves by relevance instead of similarity. No chunking, no embeddings, no vector DB.
Why it fitsBoth index documents for LLM retrieval; llamaindex is the general vector/index data framework, PageIndex is a reasoning-tree approach purpose-built for long documents.