⚡ यज्ञ
yajna
Rigveda / Bhagavad Gita 3.9
Sacred Ritual — the fire of transformation
Composable pipeline builder for LLM agent workflows. Chain, branch, merge, retry stages. Zero dependencies.
Formerly agent-pipeline — Part of the Vedic Arsenal: 100 production-grade Python libraries for LLM agents, each named from the Vedas, Puranas, and Mahakavyas.
The Vedic Principle
The Rigveda describes Yajna as the sacred fire ritual that connects the human to the divine — each offering transforms, each stage purifies, the output more refined than the input.
yajna is the LLM pipeline as sacred transformation. Raw data enters the fire. Each stage — validate, transform, call, parse, output — is an offering. The pipeline is not a machine. It is a ritual. Each step has its dharma, its place, its function.
"Yajna is born from action" says the Gita (3.14). The pipeline is born from the sequence of intentional acts. Run it with awareness and every token becomes an offering to intelligence itself.
How It Works
flowchart LR
A[Input] --> B[Stage 1: Validate]
B --> C[Stage 2: Transform]
C --> D[Stage 3: LLM Call]
D --> E[Stage 4: Parse]
E --> F[Output]
B -- Error --> G[Retry]
style D fill:#10b981,color:#fff
Installation
pip install yajna
Or from source:
git clone https://github.com/darshjme/yajna.git
cd yajna && pip install -e .
Quick Start
from yajna import *
# See examples/ for full usage
The Vedic Arsenal
yajna is one of 100 libraries in darshjme/arsenal — each named from sacred Indian literature:
| Sanskrit Name | Source | Technical Function |
|---|---|---|
yajna |
Rigveda / Bhagavad Gita 3.9 | Sacred Ritual — the fire of transformation |
Each library solves one problem. Zero external dependencies. Pure Python 3.8+.
Contributing
- Fork the repo
- Create feature branch (
git checkout -b fix/your-fix) - Add tests — zero dependencies only
- Open a PR
⚡ Built by Darshankumar Joshi · @thedarshanjoshi
"कर्मण्येवाधिकारस्ते मा फलेषु कदाचन" Your right is to action alone, never to its fruits. — Bhagavad Gita 2.47
Metadata
Release files for agent-pipeline 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agent_pipeline-0.1.0.tar.gz | 14.6 kB | Without provenance | Details for agent_pipeline-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agent_pipeline-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for agent_pipeline-0.1.0-py3-none-any.whl |
Total release size: 25.6 kB
Release files / agent_pipeline-0.1.0.tar.gz
| Download URL | agent_pipeline-0.1.0.tar.gz |
|---|---|
| Size | 14.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
940e479f5bd8093a1aa09691975a8e02fa524110e03d22bbb07fccc343c55705
|
|
BLAKE2b-256 checksum How to use checksums |
9395d2b0a2882c853d6c5b6d9228b1a4677e0103fced575d03c79b7df6563cab
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.11
|
Release files / agent_pipeline-0.1.0-py3-none-any.whl
| Download URL | agent_pipeline-0.1.0-py3-none-any.whl |
|---|---|
| Size | 11.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
11afd1aebbe41b9b76b66f3a7a8128f06a8b7c15effdfd394eb06c39db0dde7c
|
|
BLAKE2b-256 checksum How to use checksums |
a522346a678dc723b9234354c507b7c736cd1a996f6192a2c8bfbbc9b3fc2e40
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.11
|
Security for agent-pipeline 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.