Back to directory

LlamaIndex

LlamaIndex is an open-source Python framework for building agentic applications, developed alongside LlamaParse, the company's own platform for agentic document parsing, extraction and indexing.

Visit website (opens in a new tab)developers.llamaindex.ai
LlamaIndex

The OSS framework offers a starter package bundling core LlamaIndex with a selection of integrations, or a core package that a developer combines with specific integration packages, of which more than three hundred exist, for a chosen LLM, embedding model and vector store. LlamaParse is a separate, focused platform covering agentic OCR and parsing across more than 130 document formats, structured data extraction, splitting large documents, and building end-to-end document agents with a workflow builder, usable either standalone or together with the OSS framework.

The README states that the company's current focus has shifted from the general-purpose orchestration framework toward document parsing and extraction as agents increasingly become the primary consumers of documents.

MIT licensed.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.