Opening on Vijayadaśamī, 20 October 2026 · Join the list

Sanskrit, with its grammar shown.

Every word of the Bhagavad Gītā and Kālidāsa's Meghadūta, analysed by scholars and checked against Pāṇini's rules. Tap any word to see why it is what it is.

Scholarly annotation and Pāṇini's rules agree
The two sources differ: open for review
The rule engine has no entry for this form yet
Compound member, not yet checked
कर्मण्येवाधिकारस्ते मा फलेषु कदाचन
karmaṇyevādhikāraste mā phaleṣu kadācana
मा कर्मफलहेतुर्भूर् मा ते सङ्गो ऽस्त्वकर्मणि
mā karmaphalaheturbhūr mā te saṅgo 'stvakarmaṇi
Meter: anuṣṭubh (pathyā). ऽ guru, । laghu.
Loading the word analysis…
Two directions, one engine

AI that teaches Sanskrit, and Sanskrit that tests AI.

Learn

Read classical texts with every word explained

The analysis you see above is checked twice: once by scholars who annotated the corpus, once by a working implementation of the Aṣṭādhyāyī. Where they disagree, we show it.

  • LiveReader for the Bhagavad Gītā (700 verses) and the Meghadūta (122 verses): word analysis, sūtra derivations, meter
  • NextPaste any verse and get a verified word-by-word reading
  • NextSpoken Samskritam practice partner
  • NextRecitation coach for meter and pronunciation
Improve AI

A grammar benchmark that no model can talk its way through

Every answer is fixed by Pāṇini's rules or by two independent sources, never by another model. Items and grader are open.

TaskWhat the model must doItems
TiṅantaProduce a verb form from root, lakāra, person and number150
SubantaDecline a stem in a given case and number100
AnalysisIdentify lakāra, puruṣa and vacana of a verb form100
Gītā in contextGive a word's lemma and grammar inside a verse100
ChandasScan a half-verse into guru and laghu syllables50
The Bhagavad Gītā, checked

What the two sources say together

701
verses in the reader
8,982
words checked against Pāṇini's rules
93.0%
where scholars and rules agree
782
step-by-step sūtra derivations

Compound members are not yet checked, so they are left out of the agreement figure.

Join the list

Hear when new texts, voice and the benchmark results arrive.

One email when there is something real to show. No sharing, and you can ask to be removed any time.

I'm here to

Sources

Built on open scholarship

Word analyses: the Digital Corpus of Sanskrit by Oliver Hellwig, licensed CC BY 4.0. Its Gītā follows the critical edition of the Mahābhārata; verse numbers here use the common numbering, which differs in chapter 13. Meghadūta verses are numbered as in the corpus, counted separately in the Pūrvamegha and Uttaramegha.

Grammar engine: Vidyut from the Ambuda project, which implements more than 2,000 rules of the Aṣṭādhyāyī.