{"data":{"slug":"pageindex","name":"PageIndex","tagline":"MIT self-hosted vectorless tree-RAG core — local mode with your own LLM key","category":"agents","categoryName":"AI Agents","url":"https://pageindex.ai","github":"https://github.com/VectifyAI/PageIndex","pricing":"open-source","hook":"PageIndex builds a table-of-contents tree over a long document and lets the model reason its way down the tree instead of pulling top-k vector chunks — and `pip install -U pageindex` now runs that index/retrieve/chat loop entirely on your machine.","whatsGood":"MIT (VectifyAI/PageIndex). PyPI `pageindex` (v0.2.21) local mode: index, retrieve, and chat locally with your own LLM key (e.g. OPENAI_API_KEY), index stored in a local directory, no vector DB and no PageIndex account. Tools drop into the OpenAI Agents SDK, Claude Agent SDK, or your own framework. Published OSS benchmark covers exactly the local no-OCR setup. Useful when long, structured, text-heavy PDFs (filings, manuals, contracts) defeat chunk-and-embed RAG. ★~38,648.","theCatch":"Cloud: OCR and image understanding, Metadata, Folders, the MCP server, and the PageIndex File System (corpus-scale indexing) are PageIndex Cloud only — need a PageIndex API key. Local mode is text-heavy PDFs, one document tree at a time. Not a duplicate of the pageindex-mcp gem: that one is the freemium hosted MCP surface; this is the self-hosted MIT tree-RAG core you run in your own code. Your LLM key pays for every index and query — tree reasoning is token-hungry on big docs. SDK is young (0.2.x); pin it.","verdict":"MIT self-hosted tree-RAG core for long text-heavy PDFs with your own LLM key — not the freemium pageindex-mcp; OCR, folders, metadata, MCP, and File System are cloud.","addedAt":"2026-10-05","featured":false,"domain":"AI Agents","subSpecialty":"RAG","subcategory":"RAG","tags":["self-host","local-first","permissive","rag","vector","active"],"capabilities":["rag","pdf","self-host"],"surfaces":["Self-host"],"ecosystem":["Python"],"licenseModel":"OSS/MIT","githubStars":39264,"starsPerWeek":485,"access":"free","archived":false,"repo":{"createdAt":"2025-04-01","pushedAt":"2026-10-19","license":"MIT","archived":false,"checkedAt":"2026-10-19"}},"related":[{"slug":"claude-code","name":"Claude Code","tagline":"Terminal-first coding agent with deep repository context"},{"slug":"cursor","name":"Cursor","tagline":"The AI-first code editor that understands your codebase"},{"slug":"devin","name":"Devin","tagline":"Autonomous AI engineer for defined engineering tasks"},{"slug":"stagehand","name":"Stagehand","tagline":"AI-native browser automation that mixes code and natural language"},{"slug":"browser-use","name":"Browser Use","tagline":"Open-source framework for LLM-driven browser agents"}],"links":{"self":"/api/gems/pageindex","html":"/gems/pageindex","markdown":"/gems/pageindex.md","category":"/api/gems?category=agents","categoryPage":"/stacks/agents"}}