Metadata-Version: 2.4
Name: promptframe
Version: 0.1.0
Summary: LLM-agnostic prompt management — YAML-based storage, typed loading, and a fluent builder API.
Author-email: Anik Mallick <anik.mallick.code@gmail.com>
License: MIT
Project-URL: Repository, https://github.com/AnikMallick/promptframe
Keywords: llm,prompt,prompt-engineering,yaml
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Libraries
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: pydantic>=2.0
Requires-Dist: pyyaml>=6.0
Provides-Extra: ui
Requires-Dist: streamlit>=1.30; extra == "ui"
Provides-Extra: dev
Requires-Dist: pytest>=7; extra == "dev"
Requires-Dist: ruff; extra == "dev"
Requires-Dist: mypy; extra == "dev"
Requires-Dist: build; extra == "dev"
Requires-Dist: twine; extra == "dev"
Dynamic: license-file

# promptframe
 
> LLM-agnostic prompt management — YAML storage, typed loading, structured output support, and a fluent builder API.
 
**This package is under active development. Full release coming soon.**
 
## What it will do
 
- Store and version prompts as structured YAML files
- Load prompts as typed Python objects with attribute access
- Decouple LLM field instructions from Pydantic models via `model_attribute_id`
- Compose prompts from components using a fluent builder API
- Support markdown skill files (`SKILL.md`) as reusable instruction documents
- Ships with a Streamlit UI for browsing, playground, and building prompts visually
## Status
 
`0.1.0` is a name reservation. Watch this repo for the first real release.
 
