# VectifyAI/PageIndex

> A vectorless RAG engine that builds a hierarchical tree index of a document and retrieves by LLM reasoning over that tree, the way a human navigates a report. Aimed at long professional PDFs such as financial, legal and technical documents.

- Magnitude: 1.3 out of 10 — Cooling
- Stars: 39,963 total · +3 stars measured 2026-11-03, 00:38–13:59 UTC, ≈ 7 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: MIT · Created: 2025-04-01 · Last push: 2026-11-03
- GitHub: https://github.com/VectifyAI/PageIndex · Homepage: https://pageindex.ai · Page: https://gitnova.dev/en/r/VectifyAI/PageIndex

## Useful for

- Ask a question over a hundreds-page financial report and get an answer traced to a section
- Index a local folder of PDFs and search across them without a vector database
- Drop PageIndex tools into your own agent built on the OpenAI Agents SDK or Claude Agent SDK

## Why it’s here

- Star-counter measurements on 2026-11-03 (UTC), 00:38–13:59: 39960 → 39963 stars (+3). This is the change over that interval.
- Estimated end-of-day forecast: about +7 stars, using observed gains and the previous day.
- Interest is fading: the two-day pace is 21% of the previous week and a half.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 3,440
- Issues and pull requests: 621
- Watchers: 152
- Average over the last week: 19 per day
- Usual pace: 74 per day
- Stars in the last hour (measured): 1
- Latest release: v0.5.1 (2026-11-03)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-05 … 2026-11-03: 66, 123, 121, 64, 31, 19, 17, 32, 30, 20, 25, 74, 28, 21, 66, 81, 41, 75, 78, 65, 89, 82, 44, 35, 23, 16, 17, 20, 15, 3

## Magnitude by day, last 14 days

10-21 2.9, 10-22 2.5, 10-23 2.8, 10-24 2.8, 10-25 2.6, 10-26 3.0, 10-27 2.9, 10-28 2.3, 10-29 2.0, 10-30 1.9, 10-31 1.6, 11-01 1.6, 11-02 1.8, 11-03 1.5

## Hacker News

- Show HN: Vectorless, Reasoning-Based RAG — 8 points, 0 comments: https://news.ycombinator.com/item?id=49918836

## More in this category

1. **NVIDIA/auto-ontology** — 8.8 · Breakout · Language models · Python · +1,111 stars measured 2026-11-03, 00:35–13:47 UTC, ≈ 1,637 by evening
   NVIDIA's Python framework that builds a semantic ontology graph over enterprise metadata, giving LLM agents trusted metric and entity definitions for reliable text-to-SQL.
   Full card: https://gitnova.dev/en/r/NVIDIA/auto-ontology.md
2. **karpathy/nanochat** — 7.2 · Breakout · Language models · Python · +265 stars measured 2026-11-03, 00:30–13:47 UTC, ≈ 462 by evening
   A minimal experimental harness for training LLMs on a single GPU node, covering tokenization, pretraining, finetuning, evaluation and inference. It lets you train a GPT-2-capability model for about $48 and chat with it via CLI.
   Full card: https://gitnova.dev/en/r/karpathy/nanochat.md
3. **p-e-w/heretic** — 6.3 · Breakout · Language models · Python · +415 stars measured 2026-11-03, 00:31–13:47 UTC, ≈ 694 by evening
   A tool for fully automatic removal of censorship (safety alignment) from transformer-based language models using directional ablation and Optuna-based parameter optimization.
   Full card: https://gitnova.dev/en/r/p-e-w/heretic.md
4. **FlashML-org/FreeToken** — 6.0 · Breakout · Language models · Python · +374 stars measured 2026-11-03, 00:31–13:47 UTC, ≈ 647 by evening
   A Mixture-of-Experts inference engine for running frontier-scale open-weight MoE models (290B+) on consumer hardware — GPUs, CPUs, and host memory. Aimed at users who want to run frontier models locally.
   Full card: https://gitnova.dev/en/r/FlashML-org/FreeToken.md
5. **FareedKhan-dev/kimi-k3-in-c** — 5.7 · Breakout · Language models · C · +214 stars measured 2026-11-03, 00:32–13:47 UTC, ≈ 348 by evening
   A portable C99 inference engine that runs the 2.78-trillion-parameter Kimi K3 model on a single CPU within 8.24 GB of RAM, with no BLAS, framework, or GPU. The model streams from disk, and memory only affects speed.
   Full card: https://gitnova.dev/en/r/FareedKhan-dev/kimi-k3-in-c.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-03 14:05 UTC, updated every 30 minutes.