Skip to content
AgentRadar
PageIndex

PageIndex

Vectorless, reasoning-based RAG engine achieving 98

Research Agents
8.5 /10
Open Source

Last Updated

2026-06-05

GitHub Stars

33,080

About PageIndex

---

Our Verdict

A research agent that is open-source and self-hostable backed by 33.1k GitHub stars. Vectorless, reasoning-based RAG engine achieving 98.7% accuracy on FinanceBench. Traceable and explainable document retrieval without vector databases..

Features

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

Detailed Ratings

Ease of Use
8.2
Value for Money
8.7
Features
8.5
Support
7.9
Performance
8.6
Overall Rating
8.5 /10

Pros & Cons

Pros

  • Open-source β€” fully self-hostable and auditable
  • Active community with 33.1k GitHub stars
  • No Vector DB
  • No Chunking

Cons

  • Requires technical setup; less hand-holding than managed alternatives
  • Limited third-party reviews and benchmarks

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?

---

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 β€” 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