JoshuaC215/agent-service-toolkit

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

What it solves

This toolkit provides a complete, production-ready template for building and deploying AI agents. It bridges the gap between defining an agent's logic and providing a functional, user-facing application, saving developers from manually wiring together the backend service, API endpoints, and frontend interface.

How it works

The project uses LangGraph to define the agent's logic, FastAPI to serve that agent via HTTP endpoints, and Streamlit to provide a chat interface. It includes a flexible client library to interact with the service, supports asynchronous request handling, and uses Pydantic for data structure management. Developers can add custom agents to the src/agents directory and expose them automatically through the service.

Who it’s for

This toolkit is for developers who want to build and run LangGraph-based agents without building the surrounding infrastructure from scratch. It is suitable for those who need a robust setup that includes streaming, chat history, and Docker-based deployment.

Highlights

  • Full-stack setup including a LangGraph agent, FastAPI backend, and Streamlit frontend.
  • Supports advanced LangGraph features like human-in-the-loop interrupts, long-term memory, and flow control.
  • Includes a generic client library for building custom applications on top of the agent service.
  • Supports the AG-UI protocol for integration with compatible frontends like CopilotKit.
  • Built-in support for Docker Compose, content moderation, and RAG implementations using ChromaDB.
  • Includes robust unit and integration testing suites.

Related

  • Project
    langchain-ai/agent-chat-ui

    Agent Chat UI is a Next.js front‑end that lets you chat with any LangGraph server. Configure the server URL, assistant ID, and optional LangSmith key, then use the web UI to send messages, stream LLM replies, hide unwanted output via special tags, and display extra “artifacts” in a side panel. The repo includes a quick‑start (`npx create-agent-chat-app`), environment‑variable shortcuts, and production guidance (API‑passthrough proxy or custom authentication).

  • Project
    Shy2593666979/AgentChat

    AgentChat is an open‑source, full‑stack conversational AI platform. It combines a Vue 3 front‑end with a FastAPI + LangChain back‑end to deliver LLM‑driven chat, multi‑agent collaboration, three‑tier memory (short‑term, summarised history, long‑term user prefs), RAG via vector stores, tool calling (including custom OpenAPI tools), and Model‑Context‑Protocol integration. Docker‑compose provides one‑click deployment; the project is MIT‑licensed.

  • Project
    lhh737/LangChain-ReAct-Agent

    A LangChain‑based ReAct agent that combines reasoning, tool calling and RAG, with a Streamlit UI, modular YAML config, and support for Alibaba DashScope models.

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

    A CLI generator that scaffolds a production‑ready FastAPI + Next.js web app with built‑in AI‑agent runtimes, RAG pipelines, authentication, billing, observability and Docker/K8s deployment tooling.

  • Project
    GiovanniPasq/agentic-rag-for-dummies

    A tutorial‑style, open‑source Python project that shows how to build a modular, agent‑driven Retrieval‑Augmented Generation system with LangGraph, hierarchical chunking, conversation memory, query clarification, multi‑agent map‑reduce, self‑correction, and evaluation via RAGAS. Works with Ollama, OpenAI, Anthropic, Google Gemini, Qdrant vector store, and optional Langfuse observability.