Aevone Research Mission

Build Vedic
Superintelligence.

Aevone is building AI systems that understand Vedic knowledge at the level of a master practitioner. Not summaries of the tradition — the tradition itself, formalised at machine scale.

Samay is the first application. The deeper project is a knowledge infrastructure that does not exist yet.

4,000+

Years of oral and written tradition being formalised

Knowledge corpora actively being built or researched

Open research problems named and published below

The Bet

Vedic knowledge systems are formal enough to be represented symbolically — and experiential enough to require neural completion at the edges.

A Jyotishi does not retrieve. They reason from first principles, applying precedence rules to the specific configuration in front of them. The AI should do the same.

The core architectural bet: you can encode the cognitive structure underneath the tradition — not just the words. Commentary-aware embeddings, sutra-to-rule extraction, dasha reasoning with explainable inference steps. These are tractable problems now in a way they were not five years ago.

"यद् भावो तद् भवति" — As the feeling, so becomes the reality.
The tradition understood that knowledge is inseparable from the mind that holds it. — Bhagavad Gita 17.3

Case Study: Raga

Raga is not music. It is a constraint satisfaction system transmitted orally for three thousand years.

72 parent scales (melakarta), hundreds of derived ragas, each with mandatory ascent/descent phrases, permitted ornaments (gamaka), forbidden note combinations, time-of-day constraints, and emotional states grounded in the Natyashastra's taxonomy.

The problem is not that this system is underdocumented. It is that the primary documentation is in performance. When the last exponents of a rare raga perform their last concert, that version of the raga is gone.

We are building acoustic models that can extract the formal grammar of a raga from recordings, disambiguate gharana-specific interpretations, and represent the raga as a queryable constraint system.

Corpus

What we are building the knowledge base from.

JyotishBPHS · Saravali · Phala Deepika · Jataka Parijata · Uttara Kalamrita · Prashna MargaActive

Bhagavad Gita700 verses · Shankara, Ramanuja, Madhva, Tilak commentariesActive

SanskritPanini's Ashtadhyayi · Mahabhashya · Laghu Kaumudi · AmarakoshaBuilding

AyurvedaCharaka Samhita · Sushruta Samhita · Ashtanga HridayamBuilding

Upanishads10 principal Upanishads · Brahmasutra · major Vedanta commentariesBuilding

Natya + RagaNatyashastra · Sangita Ratnakar · gharana recordingsResearch

YogaYoga Sutras of Patanjali · Hatha Yoga Pradipika · Gheranda SamhitaPlanned

Vedic MathBharati Krishna Tirthaji's 16 sutras · Shulba SutrasPlanned

Endangered LanguagesTulu · Gondi · Nihali · Kodava Takk · Kurukh — oral corpus onlyResearch

Open Research Problems

What we have not solved yet.

We are publishing these because they are genuinely hard, because we want collaborators who have thought about them, and because the field benefits from naming problems precisely.

Sutra-to-rule extraction. Formalising Panini's Ashtadhyayi as a computable rule system with full precedence hierarchy — utsarga, apavada, and paribhasha — encoded in a form that supports automated derivation verification.

Commentary-aware embeddings. Standard embeddings treat Shankara's Advaita and Madhva's Dvaita commentaries on the same verse as semantically similar. They are philosophically opposite. We need embedding spaces that preserve doctrinal lineage as a first-class dimension.

Low-resource acoustic modelling for raga. Training phoneme-level ASR on oral traditions with under 100 hours of clean audio, no text transcripts, and multiple speaker-dialects.

Domain-specific evaluation. Building the first publicly available benchmarks for Jyotish reasoning accuracy, Vedic Sanskrit translation quality, and Ayurvedic diagnostic consistency.

Multi-script manuscript digitisation. Devanagari OCR that handles Grantha, Sharada, Nandinagari, and Siddham scripts — with scribal variation and manuscript degradation — at accuracy levels that do not require expert correction on every line.

Jyotish chart reasoning. Formalising Parashari, KP, and Jaimini interpretation as a symbolic reasoning system with auditable inference — not black-box prediction.

Join the research.

We are looking for people who find these problems compelling — not because of the application layer, but because the problems themselves are interesting. You do not need to be Vedic-background. You need to be technically rigorous and willing to work at the intersection of traditions that have never been formalised computationally.

Write to us. Tell us what you're working on and why this matters to you.

Talk to Samay →

NLP / LLM research Sanskrit computational linguistics Jyotish — advanced practitioners Vedanta scholars ASR / speech ML Ethnomusicology OCR / document AI Ayurveda researchers Indic language engineers Evaluation / benchmark design

ॐ

Pranava — the seed from which all knowledge unfolds.

The tradition has survived four thousand years of invasion, colonisation, and modernity. It does not need rescue. What is new is the possibility of preserving its formal structure at machine scale — not as a museum exhibit, but as a living reasoning system that continues to grow.