PixelRAG
StarTrail-org
Pixel-native retrieval: renders documents as screenshots and searches over the images with a vision embedding model.
What is PixelRAG?
A retrieval system that renders documents (web pages, PDFs, images) as screenshots and retrieves over the images directly with a fine-tuned vision-language embedding model, instead of parsing HTML or text. It ships a CLI, a hosted search API over a pre-built index of millions of Wikipedia pages and a Claude Code plugin, and comes from the same Berkeley lab (StarTrail-org) as LEANN.
Pros & Cons
Pros
- Apache-2.0 with code, FAISS indexes and LoRA adapter weights published openly, not just an API
- Credible authorship: the same Berkeley lab behind the already-trusted LEANN
- Usable today with a one-line install plus a live hosted API and a Claude Code plugin
Cons
- Very young (v0.3.0, ~28 days), so the API and CLI surface will likely churn
- Headline accuracy and cost numbers (e.g. +18% over text RAG) are unverified project claims
- Local indexing needs a GPU and a heavy vision model; the convenient path leans on the hosted endpoint
License
Apache-2.0 (OSI-open)
When it is interesting
Retrieval over visually rich documents (tables, charts, layouts) where HTML-to-text parsing loses signal.
When it is too early
If you need a stable, versioned, fully self-hosted retrieval stack rather than a fast-moving v0.x plus a hosted index.
This repo featured in the 2026-07 edition of the Open-Source AI Radar.
langextract
Python library from Google for LLM-powered structured extraction with source grounding.
LEANN
StarTrail-org
RAG on everything - graph-based vector index claiming 97% storage savings for private on-device search.
turbovec
RyanCodrai
Rust vector index with TurboQuant compression (ICLR 2026) - SIMD kernels, online ingest.