🌊 अवस्था

avastha

Mandukya Upanishad

States of Being — Jagrat Svapna Sushupti

Persistent state management for LLM agents. Snapshots, rollback, multi-backend storage. Zero dependencies.

Formerly agent-state — Part of the Vedic Arsenal: 100 production-grade Python libraries for LLM agents, each named from the Vedas, Puranas, and Mahakavyas.

The ancient Avastha principle from Mandukya Upanishad finds its modern expression in this library.

Just as the Vedic sages understood that every phenomenon in the universe follows deep patterns — patterns of creation, maintenance, and dissolution — avastha applies this wisdom to LLM agent engineering.

The concept of अवस्था (States of Being — Jagrat Svapna Sushupti) speaks directly to the technical problem this library solves. When the sages codified this principle in Mandukya Upanishad, they were describing not just a spiritual truth but a computational truth that would take humanity millennia to rediscover in silicon.

This is not coincidence. The universe has one nature. The Vedas described it first.

flowchart LR
    A[Input] --> B[avastha]
    B --> C{Process}
    C -- Success --> D[Output]
    C -- Error --> E[Handle]
    E --> B
    style B fill:#6b21a8,color:#fff

pip install avastha

Or from source:

git clone https://github.com/darshjme/avastha.git
cd avastha && pip install -e .

from avastha import *

# See examples/ for full usage

avastha is one of 100 libraries in darshjme/arsenal — each named from sacred Indian literature:

Each library solves one problem. Zero external dependencies. Pure Python 3.8+.

1. Fork the repo
2. Create feature branch (git checkout -b fix/your-fix)
3. Add tests — zero dependencies only
4. Open a PR