🔮 प्रमाण

pramana

Nyaya Darshana — 4 Pramanas

Valid Knowledge — the Vedic epistemology

Input/output validation for LLM agents. Schema validation, type checking, constraint enforcement.

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

The ancient Pramana principle from Nyaya Darshana — 4 Pramanas 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 — pramana applies this wisdom to LLM agent engineering.

The concept of प्रमाण (Valid Knowledge — the Vedic epistemology) speaks directly to the technical problem this library solves. When the sages codified this principle in Nyaya Darshana — 4 Pramanas, 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[pramana]
    B --> C{Process}
    C -- Success --> D[Output]
    C -- Error --> E[Handle]
    E --> B
    style B fill:#6b21a8,color:#fff

pip install pramana

Or from source:

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

from pramana import *

# See examples/ for full usage

pramana 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