🔮 संहार

samhara

Shaiva tradition / Shiva Purana

The Dissolution — Shiva's cosmic ending

State reduction for LLM agents. Accumulate, fold, merge agent state changes.

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

The ancient Samhara principle from Shaiva tradition / Shiva Purana 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 — samhara applies this wisdom to LLM agent engineering.

The concept of संहार (The Dissolution — Shiva's cosmic ending) speaks directly to the technical problem this library solves. When the sages codified this principle in Shaiva tradition / Shiva Purana, 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[samhara]
    B --> C{Process}
    C -- Success --> D[Output]
    C -- Error --> E[Handle]
    E --> B
    style B fill:#6b21a8,color:#fff

pip install samhara

Or from source:

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

from samhara import *

# See examples/ for full usage

samhara 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