Metadata-Version: 2.4
Name: flowfoundry
Version: 0.0.1
Summary: FlowFoundry: a cloud-agnostic agentic workflow core for LangGraph/LangChain.
Author: Mandar Parab
License: Apache-2.0
Keywords: agentic-ai,langgraph,rag,framework,llm
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.12
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: pydantic>=2.7
Requires-Dist: pyyaml>=6.0.1
Provides-Extra: langgraph
Requires-Dist: langgraph>=0.2.0; extra == "langgraph"
Requires-Dist: langchain>=0.2.15; extra == "langgraph"
Provides-Extra: dev
Requires-Dist: pytest>=8.2; extra == "dev"
Requires-Dist: pytest-cov; extra == "dev"
Requires-Dist: ruff>=0.5; extra == "dev"
Requires-Dist: mypy>=1.10; extra == "dev"
Requires-Dist: pre-commit>=3.7; extra == "dev"
Requires-Dist: build>=1.2.1; extra == "dev"
Requires-Dist: twine>=5.1; extra == "dev"
Dynamic: license-file

# FlowFoundry

> **FlowFoundry** is a cloud-agnostic **agentic workflow framework** built on LangGraph and LangChain.  
> It helps you design, test, and run agentic workflows locally or in the cloud, with pluggable connectors for storage, LLMs, rerankers, and external tools.

## Features
- 🔌 Cloud-agnostic core
- 🧠 Multi-LLM per node
- 🧪 Testable with in-memory components
- 🛠️ Extensible for RAG, tool use, DB retrieval, form filing, image interpretation

## Install
```bash
pip install flowfoundry
```

## Quickstart
```python
from flowfoundry import ping
from flowfoundry.hello import hello

print(ping())           # "flowfoundry: ok"
print(hello("dev"))     # "hello, dev!"
```
