Introducing agent-service-toolkit, a new open source toolkit for running an AI agent as a service using LangGraph, FastAPI and Streamlit.
- View the repo GitHub - JoshuaC215/agent-service-toolkit: Full toolkit for running an AI agent service built with LangGraph, FastAPI and Streamlit
- Try the app: https://agent-service-toolkit.streamlit.app/
- Watch the video: https://www.youtube.com/watch?v=VqQti9nGoe4
I wanted to build a few agents for personal projects using the Compound AI Systems approach, and found that LangGraph is the most advanced framework with the features I needed today. But serving and interacting with the agent was painful and complicated unless I wanted to use LangGraph Cloud (still in closed beta), and that wouldn’t support my own infrastructure.
I built agent-service-toolkit to solve this problem so I can focus on just the agent logic and core AI systems for my projects in the future. It uses async-first and FastAPI to be blazing fast and production-ready, with a Streamlit app for easy sharing and rapid iteration.
