masci/banks

LLM prompt language based on Jinja. Banks provides tools and functions to build prompts text and chat messages from generic blueprints. It allows attaching metadata to prompts to ease their management, and versioning is first-class citizen. Banks provides ways to store prompts on disk along with their metadata.

68
/ 100
Established

Based on the README, here's a technical summary: Supports multimodal content including images and video within Jinja-based templates, while integrating with LiteLLM to enable in-prompt LLM completions and function calling during rendering. Features built-in caching strategies, async/await support, and a registry system for reusable prompt templates across applications—enabling composable prompt pipelines without manual message serialization or model-specific APIs.

123 stars. Used by 2 other packages. Available on PyPI.

Maintenance 13 / 25
Adoption 12 / 25
Maturity 25 / 25
Community 18 / 25

How are scores calculated?

Stars

123

Forks

22

Language

Python

License

MIT

Last pushed

Mar 09, 2026

Commits (30d)

0

Dependencies

7

Reverse dependents

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/masci/banks"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.