PageIndex
Vectorless, reasoning-based RAG engine for accurate document retrieval
Visit pageindex.ai ↗What is PageIndex?
PageIndex is a document retrieval system that replaces vector databases with hierarchical tree indexing and LLM reasoning. It achieves 98.7% accuracy on FinanceBench by mimicking how humans read documents—reasoning through structure rather than semantic similarity. The platform offers a chat app for analyzing long professional documents, an open-source SDK for local or cloud deployment, and a file system layer for scaling to millions of documents.
Designed for users handling complex, contextual documents that demand domain expertise and multi-step reasoning, PageIndex provides traceable, explainable retrieval without vector databases or chunking. According to the project, it was built using Claude for code assistance.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered PageIndex automatically. Evidence: GitHub VectifyAI/OpenKB; repo has AGENTS.md, CLAUDE.md. View source.
Similar vibe-coded apps
#2 this week
Manage teams of AI agents to run your business from one dashboard
Agent development environment for running multiple coding agents in parallel
AI converts documents into natively editable PowerPoint presentations
Open-source video production system directed by AI agents
Open-source AI job search agent that runs locally in your CLI
Open-source desktop client for DeepSeek Harness with plugin architecture
Open-source Android agent that runs on-device with no root required