Sutraya is a search-first library and reader for ancient texts — Pāli, Sanskrit, Tibetan, Classical Chinese, and related Dharma languages — with grounded Ask chat, translation, OCR, and a layered manuscript reader.
The goal is a single place to find a passage, read it in context, ask questions with citations, and move between root text, translation, and tools without losing your place. The library grows through curated imports and open digital corpora; personal reading history, saved items, and drafts stay scoped to your account (or a single local reader on your machine).
Sutraya stands on work from projects that have pushed open access and AI tooling for Dharma languages. Two stand out as major innovators and resources we rely on every day.
Dharmamitra builds AI tooling for the languages of the Dharma — OCR, machine translation, and large language models trained on Buddhist corpora. Sutraya’s OCR and Translate workflows follow Dharmamitra’s MITRA stack (including Auto / BDRC / Surya OCR and MITRA Translate modes), so classical Asian text can move from scan to editable translation inside the library.
OpenPecha is an open, collaborative platform for digitizing Tibetan texts — machine-readable pecha, OCR, search, and annotation. It has helped define how Tibetan literary heritage can be shared as structured data, and it remains a cornerstone of the broader open pecha ecosystem that Sutraya aims to connect with as the catalog grows.
Beyond these partners, Sutraya draws from many digital text projects and corpora — SuttaCentral, CBETA, 84000, BDRC-aligned collections, and others. Browse the full FoJin-aligned catalog, with homepage links and ingest status, on the Sources page.
Sutraya