JoshuaC215/agent-service-toolkit

Full toolkit for running an AI agent service built with LangGraph, FastAPI and Streamlit

What it solves

It provides a complete, production-ready template for developers to build and deploy AI agent services. It eliminates the need to manually set up the boilerplate for connecting an agent's logic (the "brain") to a web server (the API) and a user interface (the chat app).

How it works

The toolkit integrates several key technologies into a unified stack:

  • LangGraph: Used to define the agent's logic, including advanced features like human-in-the-loop interrupts, long-term memory, and supervisor-led multi-agent flows.
  • FastAPI: Acts as the service layer, providing streaming and non-streaming API endpoints to interact with the agents.
  • Streamlit: Provides a ready-to-use chat interface with support for voice input and output.
  • Pydantic: Ensures data structures and settings are strictly validated.
  • Docker: Packages the entire environment (including a PostgreSQL database for state) for easy deployment.

Who it’s for

Developers who want to quickly prototype or deploy LangGraph-based AI agents without building the infrastructure, API layers, and frontend from scratch.

Highlights

  • Advanced Streaming: Supports both token-based and message-based streaming for a responsive UI.
  • Multi-Agent Support: Allows running multiple different agents within a single service, accessible via unique URL paths.
  • AG-UI Protocol: Compatible with the AG-UI protocol, allowing the service to connect to external frontends like CopilotKit.
  • Integrated RAG: Includes a basic Retrieval-Augmented Generation (RAG) implementation using ChromaDB.
  • Human-in-the-Loop: Implements interrupt() and Command for flow control and human intervention.
  • Built-in Feedback: Integrated star-based feedback system using LangSmith.

Related

  • Project
    vstorm-co/full-stack-ai-agent-template

    A production-ready project generator that scaffolds full-stack AI agent applications using FastAPI and Next.js, featuring built-in RAG, authentication, and enterprise integrations.

  • Project
    Haohao-end/openagent

    A full-stack AI agent platform for building, orchestrating, and publishing AI applications with visual workflows, RAG integration, and OpenAPI delivery.

  • Project
    cloudflare/agents-starter

    A starter template for building AI chat agents on Cloudflare, featuring integrated tool-calling, task scheduling, and vision capabilities powered by the Agents SDK.

  • Project
    NirDiamant/GenAI_Agents

    A comprehensive collection of GenAI agent tutorials and implementations, ranging from simple conversational bots to complex multi-agent systems using frameworks like LangGraph and LangChain.

  • Project
    agentscope-ai/agentscope

    A production-ready agent framework that provides an SDK and a FastAPI-based service to build, deploy and scale multi-agent applications with built-in RAG and tool management.