Skip to content
AgentRadar
PageIndex

PageIndex

Vectorless, reasoning-based RAG engine achieving 98

Research Agents Open Source

Last Updated

2026-06-05

GitHub Stars

33,080

Last Updated

2026-07

About PageIndex

- 🔥 Agentic Vectorless RAG — A simple agentic, vectorless RAG example with self-hosted PageIndex, using OpenAI Agents SDK. - Scale PageIndex to Millions of Documents — PageIndex File System is a file-level tree indexing layer that lets PageIndex reason over an entire corpus, not just a single document, enabling massive-scale document search. - PageIndex Chat — Human-like document analysis agent platform for professional long documents. Also available via MCP or API. - PageIndex Framework — Deep dive into PageIndex: an agentic, in-context tree index that enables LLMs to perform reasoning-based, context-aware retrieval over long documents. - Vectorless RAG: A minimal, hands-on example of reasoning-based RAG using PageIndex. No vectors, no chunking, and human-like retrieval.

Features

No Vector DB
No Chunking
Better Traceability & Explainability
Context-Aware Retrieval
Human-like Retrieval
Self-host

Pros & Cons

Pros

  • Active community with 33.1k GitHub stars
  • No Vector DB
  • No Chunking

Use Cases

Literature reviewInformation gatheringSummarizationCitation

Who Is It For?

Teams and individuals looking for research and information synthesis who value open-source flexibility and control.

#agentic-ai#agents#ai#ai-agents#context-engineering#core

Frequently Asked Questions

What is PageIndex?

Vectorless, reasoning-based RAG engine achieving 98.7% accuracy on FinanceBench. Traceable and explainable document retrieval without vector databases.

How much does PageIndex cost?

PageIndex is open-source and free to self-host. See https://github.com/VectifyAI/PageIndex for installation instructions.

Is PageIndex open source?

Yes — PageIndex is open source with 33.1k stars. The source code is on GitHub at https://github.com/VectifyAI/PageIndex.

Who should use PageIndex?

Teams and individuals looking for research and information synthesis who value open-source flexibility and control.

Related Agents

Links & Resources

AR Reviewed by AgentRadar · Reviewed on · How we rate

Profiles are AI-assisted from public information — not independently hands-on tested.