BibCrit: An AI-Assisted Web Application for Biblical Textual Criticism BibCrit is an open-source, browser-based toolkit that applies large language model analysis to the methods and problems of biblical textual criticism. It requires no software installation and streams structured scholarly analysis in real time via Server-Sent Events. The application integrates eight tools in a single interface: MT/LXX Divergence Analyzer — word-level comparison of the Masoretic Text and the Septuagint, classifying each divergence as a translation technique, theological tendency, scribal error, or evidence for a divergent Hebrew Vorlage, with confidence scores and competing scholarly hypotheses Back-Translation Workbench — word-by-word retroversion of a LXX passage to its probable Hebrew Vorlage, following Tov's retroversion methodology, with per-word confidence levels and translation strategy annotations Scribal Tendency Profiler — five-axis radar chart scoring an LXX book's translator on literalness, anthropomorphism reduction, messianic heightening, harmonization, and paraphrase rate, with supporting textual evidence Numerical Discrepancy Modeler — analysis of numerical divergences between MT, LXX, and the Samaritan Pentateuch (patriarchal ages, census figures, temple dimensions, royal chronology), ranking competing explanations by confidence DSS Bridge Tool — comparison of a biblical passage across Dead Sea Scrolls manuscripts, the MT, and the LXX, identifying which scrolls attest the passage and how they align with each tradition Theological Revision Detector — identification of potentially theologically motivated alterations including anthropomorphism avoidance, messianic heightening, polemical changes, and harmonization Patristic Citation Tracker — analysis of how Church Fathers through the 5th century cited a passage, what text form their quotations reflect, and what this reveals about early textual transmission Manuscript Genealogy — stemmatic visualization of a biblical book's transmission from proto-text through manuscript families (MT, LXX, DSS, SP, Peshitta, Targum, Vulgate) to modern critical editions Corpus and data sources: The MT corpus uses the ETCBC morphological database (Eep Talstra Centre for Bible and Computer, Vrije Universiteit Amsterdam). The LXX corpus uses STEP Bible data (Tyndale House, Cambridge). DSS and patristic analysis draws on Claude's training knowledge of published critical editions. Technical stack: Python/Flask backend, Anthropic Claude API (claude-sonnet-4-5) for analysis, D3.js for radar chart visualization, Supabase for analysis caching with local JSON fallback, Server-Sent Events for real-time streaming. All analysis results are cached and available via an open data REST API under Apache 2.0. Languages: English and Spanish. License: Apache 2.0 Submitted for peer review to the Journal of Open Source Software (JOSS).