PageIndex

Python library that builds a tree index of long documents and has an LLM reason through it to retrieve answers, without a vector database or chunking.

Harness by VectifyAI

IndexedMIT★ 39,601

Write a review

Install

From the package registry. Read the repository before you give any tool access to your data.

pip install pageindex

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

PageIndex is a retrieval engine for long documents that replaces a vector index with a hierarchical tree index and uses LLM reasoning to search it. It works in two steps, generating a tree for each document and then searching it, and the README says it needs no vector database and no chunking. A PageIndex SDK runs in local mode with the user's own LLM key or against PageIndex Cloud. It is a retrieval component rather than a general agent framework.

Use cases: knowledge-base, document-processing

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Languages: PythonREADME
Packages: pageindex (pypi)README
Deploys to: local, pageindex-cloudREADME
Model providers: openai, anthropicREADME
Maturity: Betagithub.com

Facts extracted by Claude Sonnet 5.5 from the linked sources on Oct 24, 2026; reviewed Oct 24, 2026. Wrong fact? Tell us.

Alternatives

Frameworks for the same language with a similar way of orchestrating agents.

Compare and alternatives

Signals

Stars: 39,601
Forks: 3,426
Open issues: 51
Weekly downloads: 43,597
Last commit: Oct 24, 2026 (3 days ago)
Last release: Oct 24, 2026 (3 days ago)
Last package publish: Oct 24, 2026 (3 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Packages: pypi pageindex
License: MIT
Repository: github.com/VectifyAI/PageIndex
Website: pageindex.ai
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README github-graphql