# Buddhist AI projects. One entry per project. Rendered into directory/README.md by scripts/build.py.
# Fields:
#   name, url, org        who made it and where to find it
#   kind                  one of the project kinds in scripts/check.py
#   what                  one or two plain sentences: what it does
#   languages             language names, or [any]
#   open                  how open it is: license of code, data or models, or "free to use, closed source"
#   updated               last activity we saw (YYYY-MM), or "" if we could not tell
#   tasks                 knowledge-base task ids it helps with (optional)
# Keep entries neutral: describe, do not rank. Add a new entry at the end of its kind.

# Translation and dictionaries
- name: Dharmamitra
  url: https://dharmamitra.org/
  org: Dharmamitra team (UC Berkeley and partners)
  kind: Translation and dictionaries
  what: Machine translation, grammar analysis and search for Buddhist source languages. Its MITRA models are published on Hugging Face.
  languages: [Sanskrit, Tibetan, Classical Chinese, Pali, English]
  open: free web app; many models open (Hugging Face buddhist-nlp)
  updated: 2026-11
  tasks: [translation, text-translation-alignment]
- name: 84000
  url: https://84000.co/
  org: 84000
  kind: Translation and dictionaries
  what: Translates the Tibetan Buddhist canon (Kangyur and Tengyur) into English. Publishes its TEI files and translation memory on GitHub, and a public position on AI translation of canonical texts.
  languages: [Tibetan, English]
  open: free to read; data on GitHub (license not stated)
  updated: 2026-10
  tasks: [translation, text-translation-alignment]
- name: Monlam AI
  url: https://monlam.ai/
  org: Monlam
  kind: Translation and dictionaries
  what: Tibetan AI tools in one web app - translation, speech to text, text to speech and OCR.
  languages: [Tibetan, English]
  open: free to use; web app code open (MIT)
  updated: 2026-09
  tasks: [translation, ocr]
- name: Digital Pāḷi Dictionary
  url: https://www.dpdict.net/
  org: Digital Pāḷi Dictionary team
  kind: Translation and dictionaries
  what: Pali to English dictionary with grammar data and a compound splitter. The full database is on GitHub.
  languages: [Pali, English]
  open: open data on GitHub (see repo for license)
  updated: 2026-11
  tasks: [segmentation, term-extraction]
- name: Dharmamitra dictionaries and lexicon
  url: https://github.com/dharmamitra/dharmamitra-stardict-dictionaries
  org: Dharmamitra team
  kind: Translation and dictionaries
  what: StarDict dictionaries and a lexicon built from Dharmamitra's parallel text collection.
  languages: [Sanskrit, Tibetan, Classical Chinese, English]
  open: open on GitHub (license not stated)
  updated: 2026-11
  tasks: [term-extraction]
- name: Buddhist AI Translator (慧译通)
  url: https://github.com/xr843/Buddhist-AI-Translator
  org: xr843 (community)
  kind: Translation and dictionaries
  what: AI translator for Buddhist texts with support for Sanskrit, Pali and Tibetan terms.
  languages: [Chinese, Sanskrit, Pali, Tibetan, English]
  open: open source (MIT)
  updated: 2026-08
  tasks: [translation]
- name: Digital Dictionary of Buddhism (DDB)
  url: https://www.buddhism-dict.net/ddb/
  org: A. Charles Muller
  kind: Translation and dictionaries
  what: Online dictionary of East Asian Buddhist terms, started in 1995. Visitors can search as "guest" with a limited number of searches per day.
  languages: [Classical Chinese, English]
  open: free guest searches; license not stated
  updated: ""
  tasks: [term-extraction]
- name: Dzongkha NLP (GovTech Bhutan)
  url: https://v2.nlp.tech.gov.bt/background
  org: GovTech Agency Bhutan with DCDD and CST
  kind: Translation and dictionaries
  what: Dzongkha-English machine translation built on Meta NLLB (about 700,000 sentence pairs), Dzongkha speech to text and text to speech, and a chatbot prototype. For testing and research only.
  languages: [Dzongkha, English]
  open: license not stated
  updated: ""
  tasks: [translation]
- name: Dzongkha NLP (CST)
  url: https://nlp.cst.edu.bt
  org: College of Science and Technology (Royal University of Bhutan) with DCDD
  kind: Translation and dictionaries
  what: Web app with Dzongkha-English translation, Dzongkha speech to text and text to speech.
  languages: [Dzongkha, English]
  open: license not stated
  updated: ""
  tasks: [translation]

# Text libraries and search
- name: BDRC - Buddhist Digital Resource Center
  url: https://www.bdrc.io/
  org: BDRC
  kind: Text libraries and search
  what: The largest digital library of Tibetan texts (scans, e-texts and catalog). In 2026 it started an initiative to build open Buddhist datasets for AI, and it publishes OCR models and datasets on Hugging Face.
  languages: [Tibetan, Sanskrit, Chinese, Pali]
  open: free library; many datasets CC0
  updated: 2026-11
  tasks: [ocr, entity-extraction]
- name: OpenPecha
  url: https://openpecha.org/
  org: OpenPecha (WeBuddhist)
  kind: Text libraries and search
  what: Open Tibetan texts and the tools and datasets to work with them (OCR, speech, translation, outlines). Datasets and models are on Hugging Face.
  languages: [Tibetan, English]
  open: open data and code (licenses vary)
  updated: 2026-08
  tasks: [ocr, toc-extraction, translation]
- name: WeBuddhist app
  url: https://webuddhist.com/
  org: WeBuddhist
  kind: Text libraries and search
  what: App that connects readers to Buddhist scriptures in several languages.
  languages: [Tibetan, English, more]
  open: free app (code on GitHub, license not stated)
  updated: 2026-11
- name: SuttaCentral
  url: https://suttacentral.net/
  org: SuttaCentral
  kind: Text libraries and search
  what: Early Buddhist texts with parallels across languages and many translations. Texts and parallels are on GitHub (sc-data).
  languages: [Pali, Chinese, Sanskrit, Tibetan, English, many translations]
  open: code and data on GitHub; many translations CC0
  updated: 2026-11
  tasks: [text-translation-alignment, citation-mapping]
- name: CBETA
  url: https://www.cbeta.org/
  org: Chinese Buddhist Electronic Text Association
  kind: Text libraries and search
  what: Digital edition of the Chinese Buddhist canon, with an online reader (CBETA Online), XML files on GitHub and an API.
  languages: [Classical Chinese]
  open: free to read; most texts CC BY-NC-SA 4.0 (some collections not CC)
  updated: 2026-11
  tasks: [citation-mapping, edition-collation]
- name: SAT Daizōkyō Text Database
  url: https://21dzk.l.u-tokyo.ac.jp/SAT/
  org: University of Tokyo
  kind: Text libraries and search
  what: Searchable Taishō edition of the Chinese Buddhist canon.
  languages: [Classical Chinese]
  open: free to use
  updated: ""
- name: DILA Authority Databases
  url: https://authority.dila.edu.tw/
  org: Dharma Drum Institute of Liberal Arts
  kind: Text libraries and search
  what: Reference data on people, places, times and catalogs for Buddhist studies. Also on GitHub.
  languages: [Classical Chinese, English]
  open: free; data on GitHub
  updated: 2026-11
  tasks: [entity-extraction]
- name: DharmaNexus
  url: https://dharmanexus.org/
  org: Dharmamitra team (successor of BuddhaNexus)
  kind: Text libraries and search
  what: Finds parallel and similar passages across the Pali, Sanskrit, Tibetan and Chinese canons.
  languages: [Pali, Sanskrit, Tibetan, Classical Chinese]
  open: free to use; BuddhaNexus code GPL-3.0
  updated: 2026-11
  tasks: [citation-mapping, text-commentary-alignment]
- name: FoJin
  url: https://fojin.app/
  org: xr843 (community)
  kind: Text libraries and search
  what: Buddhist text platform with more than 10,000 texts from over 600 sources and search across languages.
  languages: [Classical Chinese, Pali, Sanskrit, Tibetan, English]
  open: open source (Apache-2.0)
  updated: 2026-11
- name: Deer Park
  url: https://deerpark.app/
  org: deerpark.app
  kind: Text libraries and search
  what: Reader for Chinese Buddhist texts. An agent skill lets AI agents look up and read texts through its public URLs.
  languages: [Classical Chinese]
  open: free to use; skill open source (MIT)
  updated: 2026-09
- name: Tipitaka.lk
  url: https://tipitaka.lk/
  org: Path Nirvana
  kind: Text libraries and search
  what: The Buddha Jayanthi Tipitaka of Sri Lanka with its Sinhala translation, plus other Pali editions.
  languages: [Pali, Sinhala]
  open: free; code on GitHub
  updated: 2026-11
- name: Tipitaka.org (Chaṭṭha Saṅgāyana)
  url: https://www.tipitaka.org/
  org: Vipassana Research Institute
  kind: Text libraries and search
  what: The Pali canon of the Sixth Council in many scripts.
  languages: [Pali]
  open: free to read
  updated: ""
- name: Digital Pali Reader
  url: https://digitalpalireader.online/
  org: Digital Pali Reader project
  kind: Text libraries and search
  what: Pali canon reader with built-in dictionary lookup.
  languages: [Pali, English]
  open: free to use
  updated: ""
- name: GRETIL
  url: https://gretil.sub.uni-goettingen.de/
  org: Göttingen State and University Library
  kind: Text libraries and search
  what: Collection of Sanskrit and other Indic e-texts, including many Buddhist texts.
  languages: [Sanskrit, Pali]
  open: free to download (terms per text)
  updated: ""
- name: Digital Sanskrit Buddhist Canon
  url: https://www.dsbcproject.org/
  org: University of the West and partners
  kind: Text libraries and search
  what: Sanskrit Buddhist texts in digital form.
  languages: [Sanskrit]
  open: free to read
  updated: ""
- name: Adarshah
  url: https://adarshah.org/
  org: Dharma Treasure
  kind: Text libraries and search
  what: Digital Tibetan canon (Kangyur and Tengyur) with search.
  languages: [Tibetan]
  open: free to use
  updated: ""
- name: Lotsawa House
  url: https://www.lotsawahouse.org/
  org: Lotsawa House
  kind: Text libraries and search
  what: Translations of Tibetan Buddhist texts, often with the Tibetan source.
  languages: [Tibetan, English, many translations]
  open: free to read
  updated: ""
  tasks: [text-translation-alignment]
- name: CBETA semantic search (CBSS)
  url: https://cbetaonline.dila.edu.tw/cbss/
  org: Dharma Drum Institute of Liberal Arts and CBETA
  kind: Text libraries and search
  what: Ask questions in plain language and get matching passages from the CBETA canon, with AI summaries of the top passages (built on the OpenAI API).
  languages: [Classical Chinese, Chinese]
  open: free to use; license not stated
  updated: 2025-12
  tasks: [buddhist-knowledge-qa]
- name: Kanseki Repository (漢リポ)
  url: https://kanripo.org/
  org: Kanseki Repository
  kind: Text libraries and search
  what: Premodern Chinese texts kept as GitHub repositories, with a Buddhist section (KR6). The web server has been down since February 2026.
  languages: [Classical Chinese]
  open: license not stated
  updated: 2026-02
- name: Thai Tipitaka program
  url: https://sourceforge.net/p/thaitipitaka
  org: ajsun and bistechn (community)
  kind: Text libraries and search
  what: Desktop program with the Thai Royal, Mahachula and Mahamakut Thai Tipitaka editions and two Pali editions in Thai script.
  languages: [Thai, Pali]
  open: open source (GPL-2.0)
  updated: 2019-06
- name: BUDSIR
  url: https://www.mahidol.ac.th/budsir/history.htm
  org: Mahidol University
  kind: Text libraries and search
  what: Search system for the Pali Tipitaka and commentaries in Thai and Roman script, in use since 1988.
  languages: [Pali, Thai]
  open: license not stated
  updated: ""
- name: Tipitaka Sajjhaya
  url: https://sajjhaya.org/node/20
  org: World Tipitaka Foundation (Bangkok)
  kind: Text libraries and search
  what: The Sixth Council Pali Tipitaka in Roman script, with notation for recitation and audio recordings.
  languages: [Pali, Thai]
  open: all rights reserved
  updated: ""
- name: 5000-years.org
  url: https://5000-years.org/en/books/all
  org: 5000-years.org
  kind: Text libraries and search
  what: Khmer Buddhist site with Dhamma books, recorded Dhamma talks and chanting, videos, and a link to an online Khmer Tipitaka.
  languages: [Khmer]
  open: license not stated
  updated: ""
- name: Nepalese-German Manuscript Cataloguing Project (NGMCP)
  url: https://ngmcp.fdm.uni-hamburg.de/mediawiki/index.php/NGMCP
  org: University of Hamburg with the National Archives of Nepal
  kind: Text libraries and search
  what: Catalogue of the Nepalese manuscripts that the Nepal-German Manuscript Preservation Project microfilmed (more than 114,500 items in Sanskrit, Newari, Nepali and other languages).
  languages: [Sanskrit, Newari, Nepali]
  open: license not stated
  updated: ""

# OCR and digitization
- name: BDRC Tibetan OCR app
  url: https://github.com/buda-base/tibetan-ocr-app
  org: BDRC
  kind: OCR and digitization
  what: Offline app for Tibetan OCR. The models are on Hugging Face (BDRC/tibetan-ocr).
  languages: [Tibetan]
  open: open source (MIT)
  updated: 2025-12
  tasks: [ocr]
- name: BDRC OCR and layout models
  url: https://huggingface.co/BDRC
  org: BDRC
  kind: OCR and digitization
  what: More than 40 models for Tibetan OCR, line and layout detection, script type and page orientation, with matching datasets.
  languages: [Tibetan]
  open: open models (licenses vary)
  updated: 2026-10
  tasks: [ocr, annotation-detection]
- name: Namgyal OCR
  url: https://github.com/eric86y/Namgyal-OCR
  org: Tibetan Manuscript Project Vienna
  kind: OCR and digitization
  what: OCR for Tibetan manuscripts.
  languages: [Tibetan]
  open: open source (MIT)
  updated: 2024-12
  tasks: [ocr]
- name: Sinhala and Pali OCR model
  url: https://huggingface.co/pathnirvana/sinhala-pali-ocr-lightonocr-1b
  org: Path Nirvana
  kind: OCR and digitization
  what: OCR model for old Sinhala and Pali prints, trained on its own open dataset.
  languages: [Sinhala, Pali]
  open: open model on Hugging Face
  updated: 2026-11
  tasks: [ocr]
- name: Kim Hán Nôm
  url: https://kimhannom.fit.hcmus.edu.vn/
  org: University of Science, VNU-HCM (Center for Computational Linguistics)
  kind: OCR and digitization
  what: OCR for printed and handwritten Hán and Nôm texts (Buddhist scripture is one document type), transliteration into Quốc ngữ and experimental translation. Web, mobile apps and API.
  languages: [Hán-Nôm, Classical Chinese, Vietnamese]
  open: free to use; license not stated
  updated: 2026-07
  tasks: [ocr]
- name: NDL Kotenseki OCR
  url: https://github.com/ndl-lab/ndlkotenocr_cli
  org: National Diet Library (Japan)
  kind: OCR and digitization
  what: OCR for digitized pre-modern Japanese and Chinese books (version 3), run with Docker.
  languages: [Japanese, Classical Chinese]
  open: CC-BY-4.0
  updated: 2025-09
  tasks: [ocr]
- name: Typhoon OCR
  url: https://huggingface.co/scb10x/typhoon-ocr1.5-2b
  org: SCB 10X
  kind: OCR and digitization
  what: Open vision-language OCR models for Thai and English documents. Output is Markdown with tables and figures.
  languages: [Thai, English]
  open: Apache-2.0 (plus OpenTyphoon terms)
  updated: 2026-01
  tasks: [ocr]
- name: Khmer Manuscript Heritage Project
  url: https://khmer-manuscripts.bdrc.io/
  org: BDRC with Digital Divide Data and FEMC/EFEO
  kind: OCR and digitization
  what: Digital copies of 11,596 Khmer manuscripts (more than 1.4 million pages), plus digitized FEMC microfilms.
  languages: [Khmer]
  open: license not stated
  updated: ""
- name: Digital Library of Lao Manuscripts
  url: https://digital.crossasia.org/digital-library-of-lao-manuscripts/?lang=en
  org: National Library of Laos, University of Passau, Staatsbibliothek zu Berlin
  kind: OCR and digitization
  what: Images of more than 12,000 Lao, Lan Na and Tai Lue manuscripts from the Preservation of Lao Manuscripts Programme, with downloadable sets.
  languages: [Lao, Northern Thai, Tai Lue]
  open: free to view and download; ask before publishing; license not stated
  updated: ""
- name: EAP813 Siberian Buddhist book heritage
  url: https://eap.bl.uk/node/3516
  org: Buryat State University; British Library Endangered Archives Programme
  kind: OCR and digitization
  what: 334 digitized Buddhist manuscripts from private collections in Buryatia and Zabaikalsky Krai. The page does not list the languages.
  languages: [Tibetan, more]
  open: research use only
  updated: ""
- name: EAP529 Dambadarjaa Monastery manuscripts
  url: https://eap.bl.uk/node/3086
  org: Monsound and Vision Foundation; British Library Endangered Archives Programme
  kind: OCR and digitization
  what: 51 Buddhist manuscripts (7,400 sheets, 1860s to 1920s) from a monastery in Mongolia. The page does not list the languages.
  languages: [Classical Mongolian, Tibetan]
  open: research use only
  updated: ""

# Language tools
- name: Botok
  url: https://github.com/WeBuddhist/Botok
  org: WeBuddhist
  kind: Language tools
  what: Tibetan word tokenizer in Python.
  languages: [Tibetan]
  open: open source (Apache-2.0)
  updated: 2026-10
  tasks: [segmentation]
- name: pyewts
  url: https://github.com/WeBuddhist/pyewts
  org: WeBuddhist
  kind: Language tools
  what: Converts Tibetan Unicode to and from Wylie (EWTS) transliteration.
  languages: [Tibetan]
  open: open source (Apache-2.0)
  updated: 2026-07
- name: bophono
  url: https://github.com/Esukhia/bophono
  org: Esukhia
  kind: Language tools
  what: Tibetan phonetics engine in Python.
  languages: [Tibetan]
  open: open source (MIT)
  updated: 2026-11
- name: lucene-bo
  url: https://github.com/buda-base/lucene-bo
  org: BDRC
  kind: Language tools
  what: Tibetan text analyzer for Lucene and Elasticsearch search.
  languages: [Tibetan]
  open: open source (Apache-2.0)
  updated: 2026-11
- name: ByT5 Sanskrit analyzers
  url: https://github.com/dharmamitra/byt5-sanskrit-analyzers
  org: Dharmamitra team
  kind: Language tools
  what: Models for Sanskrit word splitting (sandhi), lemmas and grammar tags, and OCR post-correction.
  languages: [Sanskrit]
  open: code on GitHub; models on Hugging Face
  updated: 2024-11
  tasks: [segmentation, text-cleanup]
- name: Pali script tools (paliscript)
  url: https://github.com/5w0rdf15h/paliscript
  org: 5w0rdf15h (community)
  kind: Language tools
  what: Python library and command line tool for Pali transliteration between Thai, Sinhala, Roman and other scripts.
  languages: [Pali]
  open: open source (license not stated)
  updated: 2026-02

# Speech
- name: OpenPecha speech models
  url: https://huggingface.co/openpecha
  org: OpenPecha (WeBuddhist)
  kind: Speech
  what: Tibetan speech-to-text models, including models for the teachings of specific teachers, with training data and a benchmark.
  languages: [Tibetan]
  open: open models (licenses vary)
  updated: 2026-05
- name: SuttaCentral Voice
  url: https://github.com/sc-voice/sc-voice
  org: SuttaCentral Voice
  kind: Speech
  what: Reads suttas from SuttaCentral aloud with text-to-speech.
  languages: [Pali, English, German, more]
  open: open source (MIT)
  updated: 2026-11
- name: dharma-transcribe
  url: https://github.com/retiform-labs/dharma-transcribe
  org: Retiform Labs (community)
  kind: Speech
  what: Transcription pipeline for recorded Dharma teachings in several languages.
  languages: [Tibetan, English, more]
  open: open source (MIT)
  updated: 2026-11
- name: Thonburian Whisper
  url: https://biodatlab.github.io/blog/thonburian-whisper-2024
  org: Mahidol University (biodatlab)
  kind: Speech
  what: Whisper models fine-tuned for Thai speech recognition, including smaller distilled versions.
  languages: [Thai]
  open: license not stated
  updated: 2025-01

# AI models
- name: MITRA models (buddhist-nlp)
  url: https://huggingface.co/buddhist-nlp
  org: Dharmamitra team
  kind: AI models
  what: About 60 models for Buddhist languages - translation (Gemma, Qwen, NLLB and mBART based), embeddings, sentence alignment, tagging and OCR.
  languages: [Tibetan, Sanskrit, Classical Chinese, Pali, English]
  open: open models (licenses vary)
  updated: 2026-08
  tasks: [translation, text-translation-alignment, ocr]
- name: Tibetan BERT and RoBERTa models
  url: https://huggingface.co/KoichiYasuoka/roberta-base-tibetan
  org: Koichi Yasuoka (Kyoto University)
  kind: AI models
  what: Tibetan language models, with versions for part-of-speech tagging.
  languages: [Tibetan]
  open: open models
  updated: ""
  tasks: [segmentation]
- name: Buddhist Sanskrit BERT
  url: https://huggingface.co/Matej/bert-base-buddhist-sanskrit
  org: Matej (Hugging Face user)
  kind: AI models
  what: BERT model trained on Buddhist Sanskrit texts.
  languages: [Sanskrit]
  open: open model
  updated: ""
- name: MLotsawa and Tibetan speech models
  url: https://huggingface.co/billingsmoore
  org: billingsmoore (community)
  kind: AI models
  what: Tibetan to English translation models (MLotsawa) and Tibetan speech recognition models, with open datasets.
  languages: [Tibetan, English]
  open: open models
  updated: 2026-07
  tasks: [translation]
- name: Monlam Tibetan RoBERTa
  url: https://huggingface.co/MonlamAI/tibetan_RoBERTa_S_e6
  org: Monlam AI
  kind: AI models
  what: Tibetan masked language model (fill-mask).
  languages: [Tibetan]
  open: license not stated
  updated: 2025-04
- name: Sun-Shine and TIB-STC
  url: https://github.com/Vicentvankor/sun-shine
  org: UESTC, Tibet University and others
  kind: AI models
  what: Tibetan language model based on Llama-3.1-8B, trained on TIB-STC, a Tibetan corpus of about 11 billion tokens. The repo says the code and model release is coming soon.
  languages: [Tibetan]
  open: Apache-2.0 (badge in repo)
  updated: 2025-03
- name: SinLlama
  url: https://huggingface.co/polyglots/SinLlama_v01
  org: University of Moratuwa and partners (polyglots)
  kind: AI models
  what: Llama-3-8B extended with Sinhala vocabulary and further training on Sinhala text. Base model, not instruction-tuned. Not Buddhist-specific.
  languages: [Sinhala]
  open: Llama 3 license (same as base model)
  updated: ""
- name: Gemma-SEA-LION-v4-27B-IT
  url: https://huggingface.co/aisingapore/Gemma-SEA-LION-v4-27B-IT
  org: AI Singapore
  kind: AI models
  what: Gemma 3 based 27B chat model for Southeast Asian languages, including Burmese, Khmer, Lao, Thai and Vietnamese. Not Buddhist-specific.
  languages: [Thai, Lao, Khmer, Burmese, Vietnamese, more]
  open: MIT
  updated: 2025-08
- name: Xunzi models for Chinese classics
  url: https://github.com/Xunzi-LLM-of-Chinese-classics/XunziALLM
  org: Nanjing Agricultural University with Zhonghua Book Company
  kind: AI models
  what: "Open models (Qwen, Baichuan2 and ChatGLM3 based) for ancient Chinese texts: translation into modern Chinese, punctuation, word segmentation and entity extraction."
  languages: [Classical Chinese, Chinese]
  open: Apache-2.0
  updated: 2024-05
  tasks: [translation]
- name: NLLB Russian-Tuvan models
  url: https://huggingface.co/slone/nllb-rus-tyv-v2-extvoc
  org: SLONE
  kind: AI models
  what: NLLB-200-600M with an extended vocabulary, fine-tuned for Russian-Tuvan translation. No scores published.
  languages: [Tuvan, Russian]
  open: CC-BY-NC-4.0 (non-commercial)
  updated: ""
  tasks: [translation]
- name: NLLB-200 Buryat-Russian
  url: https://huggingface.co/SaranaAbidueva/nllb-200-bxr-ru
  org: Sarana Abidueva
  kind: AI models
  what: NLLB-200 fine-tuned for Buryat-Russian translation. Reported BLEU is about 13 (Russian to Buryat) and 20 (Buryat to Russian).
  languages: [Buryat, Russian]
  open: MIT
  updated: ""
  tasks: [translation]

# Chatbots and Q&A
- name: NORBU
  url: https://norbu-ai.org/en/norbu
  org: Buddhist Channel (Malaysia)
  kind: Chatbots and Q&A
  what: Chatbot that answers questions about Buddhism from Buddhist sources.
  languages: [English, more]
  open: free to use, closed source
  updated: ""
  tasks: [buddhist-knowledge-qa]
- name: BuddhaBot-Plus
  url: https://www.kyoto-u.ac.jp/en/news/2025-03-03
  org: Kyoto University
  kind: Chatbots and Q&A
  what: Chatbot based on Buddhist scriptures, built on ChatGPT. Used with monks and nuns in Bhutan, and in Buddharoid, a humanoid robot monk made with Teraverse Inc. and shown at Shoren-in temple in Kyoto (not for sale).
  languages: [Japanese, English]
  open: closed
  updated: 2026-06
  tasks: [buddhist-knowledge-qa]
- name: Compassion Bot
  url: https://www.awakin.ai/about/
  org: Awakin.ai
  kind: Chatbots and Q&A
  what: Chatbot that draws on teachings of many traditions, Buddhism included.
  languages: [English]
  open: free to use
  updated: ""
- name: Roshibot
  url: https://nozeninthewest.com/roshibot/
  org: Jiryu Mark Rutschman-Byler
  kind: Chatbots and Q&A
  what: Zen chatbot.
  languages: [English]
  open: free to use
  updated: ""
- name: Master-skill
  url: https://github.com/xr843/Master-skill
  org: xr843 (community)
  kind: Chatbots and Q&A
  what: Framework for Buddhist AI personas that answer from sources (using FoJin) and know their limits.
  languages: [Chinese, English]
  open: open source (license not stated)
  updated: 2026-11
  tasks: [buddhist-knowledge-qa]

# Agent skills and tools
- name: Dharmamitra Claude Code agent
  url: https://github.com/dharmamitra/dharmamitra-claude-code-agent
  org: Dharmamitra team
  kind: Agent skills and tools
  what: Starter pack for agent-based translation, critical editions and finding parallel passages.
  languages: [Sanskrit, Tibetan, Classical Chinese, Pali]
  open: open on GitHub (license not stated)
  updated: 2026-11
  tasks: [translation, edition-collation, citation-mapping]
- name: Tripitaka MCP server
  url: https://github.com/dhamma-seeker/tripitaka-mcp
  org: dhamma-seeker (community)
  kind: Agent skills and tools
  what: Gives AI assistants access to the full Pali Tipiṭaka (about 444,000 segments, aligned with SuttaCentral).
  languages: [Pali, English]
  open: open source (license not stated)
  updated: 2026-11
  tasks: [citation-mapping, buddhist-knowledge-qa]
- name: Deer Park skill
  url: https://github.com/briansun/deerpark-skill
  org: briansun (community)
  kind: Agent skills and tools
  what: Agent skill to search and read Chinese Buddhist texts on deerpark.app.
  languages: [Classical Chinese]
  open: open source (MIT)
  updated: 2026-09
- name: buddhist-canons skill
  url: https://github.com/luohy-qh/buddhist-canons
  org: luohy-qh (community)
  kind: Agent skills and tools
  what: Agent skill built from 19 canons (2,494 texts) as searchable evidence cards that keep the source text apart from AI summaries.
  languages: [Classical Chinese]
  open: open source (license not stated)
  updated: 2026-07
  tasks: [buddhist-knowledge-qa]
- name: Chinese kepan outliner
  url: https://github.com/aaronbao1/chinese-kepan-outliner
  org: aaronbao1 (community)
  kind: Agent skills and tools
  what: Claude skill that recovers the kēpàn (科判) outlines of classical Chinese Buddhist texts.
  languages: [Classical Chinese]
  open: open source (MIT)
  updated: 2026-11
  tasks: [toc-extraction]
- name: BuddhistAI skills
  url: https://github.com/BuddhistAI/buddhist-skills
  org: BuddhistAI
  kind: Agent skills and tools
  what: The best measured skill for each Buddhist task, per language, plus shared community skills.
  languages: [Tibetan, more]
  open: open source (MIT)
  updated: 2026-11
  tasks: [toc-extraction]

# Practice and teaching
- name: Meditatewith.ai
  url: https://meditatewith.ai/
  org: Vince Horn
  kind: Practice and teaching
  what: Experiments with AI for guided and social meditation.
  languages: [English]
  open: free to use
  updated: ""
- name: my-dharma.md
  url: https://github.com/BuddhistAI/buddhist-prompts/tree/main/personal-ai-setup-english/shoukei-matsumoto-my-dharma
  org: Shoukei Matsumoto
  kind: Practice and teaching
  what: A personal file that tells an AI assistant about your practice and how you want it to talk about the Dharma.
  languages: [English]
  open: CC0
  updated: 2026-11
- name: Dharma lesson planner
  url: https://github.com/BobConscious/dharma-lesson-planner
  org: BobConscious (community)
  kind: Practice and teaching
  what: App that drafts lesson plans for Buddhist studies classes from source material.
  languages: [English]
  open: open source (MIT)
  updated: 2026-07

# Research and community
- name: Intellexus
  url: https://www.kc-tbts.uni-hamburg.de/projects/intellexus.html
  org: University of Hamburg, Reichman University and partners
  kind: Research and community
  what: EU-funded research project on AI for Buddhist texts in Sanskrit and Tibetan. Makers of DharmaBench.
  languages: [Sanskrit, Tibetan]
  open: research code open (Apache-2.0)
  updated: 2026-10
- name: Tsadra Dharma AI Project
  url: https://www.tsadra.org/ai-tools-for-tibetan-buddhist-translation/
  org: Tsadra Foundation with Dharmamitra
  kind: Research and community
  what: Webinars, slides and case studies on using AI tools in Tibetan translation work, and a Discord community for Dharma translation and AI.
  languages: [Tibetan, Sanskrit, English]
  open: free
  updated: ""
  tasks: [translation]
- name: Buddhism & AI Initiative
  url: https://www.engagedbuddhists.ai/
  org: Buddhism & AI Initiative
  kind: Research and community
  what: Maps who works where Buddhism and AI meet, in six domains (its "Field Framework"), and brings the field together.
  languages: [English]
  open: free to read
  updated: ""
- name: BuddhistAI benchmarks
  url: https://buddhistai.github.io/buddhist-benchmarks/
  org: BuddhistAI
  kind: Research and community
  what: Open benchmarks and leaderboards for Buddhist tasks. Ranks models and skills by top performance and best value.
  languages: [Tibetan, Thai, more]
  open: open source (MIT)
  updated: 2026-11

# Other lists
- name: Awesome Tibetan NLP
  url: https://github.com/tibetan-nlp/awesome-tibetan-nlp
  org: tibetan-nlp
  kind: Other lists
  what: List of Tibetan NLP tools and data.
  languages: [Tibetan]
  open: open
  updated: 2020-07
- name: SuttaCentral awesome list
  url: https://github.com/suttacentral/awesome
  org: SuttaCentral
  kind: Other lists
  what: Projects built on SuttaCentral texts and data.
  languages: [Pali, English]
  open: CC0
  updated: 2026-07
- name: awesome-buddhist-dharma
  url: https://github.com/yuqianyi1001/awesome-buddhist-dharma
  org: yuqianyi1001 (community)
  kind: Other lists
  what: Collection of Buddhist study resources, mostly in Chinese.
  languages: [Chinese]
  open: open
  updated: 2026-10
- name: Related benchmarks (BuddhistBench)
  url: https://github.com/BuddhistAI/buddhist-bench/blob/main/docs/related-benchmarks.md
  org: BuddhistAI
  kind: Other lists
  what: Benchmarks on Buddhism and other religions, with license and import status.
  languages: [any]
  open: MIT
  updated: 2026-11
