whereismyai
Agent Service Toolkit
Agent Service Toolkit is an open-source template for running LangGraph AI agents, served by FastAPI and used through a Streamlit chat app.
Agent Service Toolkit is an open-source Python project that shows a complete setup for building and running AI agents with LangGraph. It includes a customizable LangGraph agent using current features such as human-in-the-loop interrupts, long-term memory and supervisors, a FastAPI service that serves agents with streaming and non-streaming endpoints, a client library, and a Streamlit chat interface with voice input and output. Several agents can run in one service and be called by URL path, and every agent is also served over the AG-UI protocol for frontends such as CopilotKit. It includes a basic RAG agent with ChromaDB, content moderation, and a Docker setup for local development. Developers use it as a starting template for their own agent services, and a demo app runs on Streamlit Cloud.
Agent Service Toolkit at a glance
Key features
- LangGraph agent with human-in-the-loop and memory
- FastAPI service with streaming endpoints
- Streamlit chat app with voice input and output
- Multiple agents in one service
- AG-UI protocol support for CopilotKit frontends
- RAG agent example with ChromaDB
- Docker setup
Use it for
- Start a LangGraph project from a working template
- Serve an agent behind an API with a chat front end
- Learn how LangGraph, FastAPI and Streamlit fit together
Alternatives to Agent Service Toolkit
- Agent Vision Toolkit — Gives text-only coding agents task-aware sight
- Fastagent — Deploys chat agents to your own cloud account using one bearer token.
- fast-agent — Improves agent accuracy and cost efficiency via MCP integration.
- LangChain — Compose exactly the agent your use case needs from model, tools, prompt, and middleware.
- Genkit — Provides unified APIs and local developer tools for AI application workflows.
- Agent Toolkit for AWS — Provides official MCP servers and agent skills tailored for AWS services.
- AI SDK — Switch providers easily and stream real-time responses without custom parsing.
- AG-UI — Standardizes agent-user interactions and generative UI for applications.
- CopilotKit — Connects your application to AI agents with generative UI and human approvals.
- Google ADK for Go — Apply standard software engineering practices to AI agent orchestration.
- FastGPT — It uses hybrid retrieval and auto-cleansed data to prevent hallucinations.
- Adyen — Share AI agent resources across coding tools and repositories easily.
All Agent Service Toolkit alternatives