Skip to content
repository radar
RAG & Memory

📑PageIndex

ACTIVE BREAKOUT

VectifyAI/PageIndex · homepage ↗

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

⭐ Very popular: 35k stars, gaining about 192 a week

View on GitHub ↗

repo profile

vintage 2025 1 year old
delivery product
language Python
license MIT

momentum

total stars 35k
stars added last week +192
HN peak 192 pts 11mo ago
weekly downloads 11k /wk · PyPI
binary downloads 64 total · GitHub releases
commits / week 9 accelerating · +79% vs prior mo
issues closed 43% ~2mo to close, median
contributors 14
release cadence weekly
last activity yesterday

durability

backing community / independent independent
openness permissive
bus factor 1 solo
top-author share 61% 6 mo

bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.

since we covered it

monthly average + 3k/mo (+23%/mo) · + 21k total since PR#27

why it's a big deal

  • Targets professional document QA where similarity-based retrieval fails, replacing vector chunking with reasoning over a document's structure so results are relevant rather than merely similar.
  • Helps teams working with financial reports, legal and regulatory filings, technical manuals, and academic texts, where retrieval must be traceable back to specific pages and sections.
  • Reports 99% accuracy on the FinanceBench financial document QA benchmark, and removes the need for a vector database or chunking pipeline.

under the hood

  • Written in Python; builds a hierarchical tree index where each node holds a title, summary, page range, and node id, organizing documents into natural sections instead of fixed-size chunks.
  • Retrieval is a two-step process: generate the tree index, then run reasoning-based tree search with an agentic LLM that navigates the structure using full context.
  • Uses LiteLLM for multi-model support, with optional cloud OCR and tree building, vision-based retrieval over page images, and MCP integration.

Radar summary, generated from the project's public sources

star history

PR#27 · 15k35k now Apr 2025Aug 2026
  1. PR#27 15k 2026-02-11
  2. now 35k + 21k since first covered

curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.

understory

Better known than its recent output, coasting a little on attention.

-24 understory score output 54 · clout 78
Aug 2025 Jul 2026
  • output, commits & releases
  • clout, star velocity

output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →

covered in

  • PR#27 2026-02-11 below the radar

    Vectorless, reasoning-based RAG

similar projects

compare these →
  • 📚 Haystack

    Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

    26k ACTIVE
  • 🧠 Mem0

    Universal memory layer for AI Agents

    63k ACTIVE
  • 📦 LEANN

    leaner, 13k stars

    [MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

    13k ACTIVE

comments

Sign in with GitHub to add your blip on PageIndex.

loading comments…