Observed arrival · 2026-09-28
BOAR puts offline AI on an Android phone
BOAR runs a small AI model and searchable knowledge library on an Android phone, with answers that show their sources.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Android users needing offline reference and reasoning
- Worth noticing
- The optional Wikipedia Vital Articles pack is listed as 49,832 articles in 164 MB.
Field notes
The setup is a one-time network step: the app fetches Qwen2.5-1.5B-Instruct and an embedding model, then searches its built-in library with keywords and on-device embeddings. The page lists imports for TXT, Markdown, CSV, JSON, and PDF, plus the option to find and run another GGUF model. It says answers expose their source articles and runtime measures; the homepage’s sample outputs are abridged and are not a benchmark.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue