LocalRAG – Ask AI about your own documents (iOS/Android)

Name: LocalRAG – Ask AI about your own documents (iOS/Android)
Availability: InStock
Author: snakaya

by snakaya·Mar 1, 2026·4 points·1 comment

Visit Project View on HN

AI Analysis

●●SolidSolve My Problem

On-device RAG for 9 document formats, but document Q&A apps are well-trodden.

Strengths

•Native EPUB support is rare—most document AI tools skip ebook formats entirely
•Hybrid four-stage search pipeline with multi-language support suggests thoughtful retrieval tuning
•Model selection (Claude 3.5 Sonnet/Haiku/Opus) with on-device processing keeps data private—real differentiator for sensitive docs

Weaknesses

•Document Q&A is crowded (ChatPDF, Artifact, Ask Your PDF)—no evidence of retrieval quality vs. competitors
•Subscription model ($4.99/9.99 monthly) competes with free/freemium offerings; limited free tier (5 questions/day) is restrictive

Similar Projects

AI/ML●●Solid

LocalRAG – Ask AI about your own documents (iOS/Android)

Offline on-device RAG beats cloud-only competitors like NotebookLM.

Solve My ProblemSlick

snakaya

103mo ago

AI/ML●●Solid

Wax – RAG in a single file (SQLite for AI memory)

Exports a one-file 'brain' and a tiny MemoryOrchestrator API (remember/recall) so you can ditch Docker and hosted vector DBs — token-budgeted, deterministic recall and kill-9-safe durability are concrete wins. The Metal-accelerated vector search plus SQLite FTS5 fallback shows real engineering heft, but it's clearly tuned for the Apple ecosystem and the author is still asking for retrieval/eval feedback.

WizardryNiche Gem

karc14

203mo ago

Developer Tools●●Solid