PageIndex
Reasoning-based vectorless RAG for long documents using a hierarchical tree index, available as open source plus cloud chat, MCP, and API.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for PageIndex, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology. Are you the vendor? Factual corrections are free.
Overview
PageIndex is a reasoning-based, vectorless RAG system for analyzing long professional documents without vector databases or fixed chunking. It builds a hierarchical “table-of-contents” style tree index from a document and performs retrieval via reasoning-driven tree search, aiming for more relevant, traceable results with page/section references. PageIndex can be self-hosted using the open-source repository, or used via a hosted chat platform and integrations such as MCP and an API, with enterprise deployment options for private/on-prem use cases.
Key features
- vectorless rag
- reasoning-based retrieval
- tree index
- document analysis
- pdf qa
- traceable citations
- mcp integration
- enterprise deployment
- no chunking
Use cases
- Building document Q&A and analysis systems for long PDFs without using a vector database.
- Improving retrieval relevance for professional documents by using reasoning-based tree search.
- Providing traceable answers with page and section references for audits and reporting.
- Integrating document analysis into agent workflows via MCP or a hosted API.