---
library_name: other
license: other
tags:
- agastya
- native-foundation-model
- from-scratch
- random-initialization
- model-provenance
- india
pipeline_tag: text-generation
---

# Agastya AGI v01 — Bramha Medha Native INDIA

Publisher: Rabbit Industries Pvt Ltd
Evidence release: R1 — 2026-09-30
Canonical public evidence: https://zippri.com/agastya-native-brain-evidence/

## Status

This is a public provenance and model-card repository. It does not redistribute proprietary model weights, raw corpus, full tokenizer vocabulary, or private architecture source.

Published evidence records:
- fresh random initialization at step 0
- teacher weight ancestry: ZERO
- third-party weight ancestry: false
- third-party tokenizer artifact import: false
- unique parameter count: 1,264,715,776
- tokenizer vocabulary size: 98,320
- canonical context: 4,096 tokens
- Clean-P0 R2 acceptance: PASS

## Canonical lineage

Agastya corpus -> Agastya tokenizer -> Agastya architecture -> RANDOM INITIALIZATION -> Agastya pretraining -> Agastya post-training -> Agastya Native Brain

## Independent verification

Independent third-party verification remains PENDING. The repository includes a public verification protocol that a qualified evaluator can follow.

## Citation

See CITATION.cff.

## Persistent identifier

Reserved Zenodo DOI: [10.5281/zenodo.23054425](https://doi.org/10.5281/zenodo.23054425)

This DOI was reserved before publication so it could be embedded into the immutable R1 evidence artifacts. It becomes registered when the Zenodo record is published.