tgo

Why we included this project

Support teams that have outgrown a single chatbot will find TGO a useful way to test what agent-based handling can do. You can assemble several specialized AI agents, each aimed at a different business scenario, and back them with a RAG knowledge base built from your own documents, Q&A pairs, or crawled website content. It also routes conversations across multiple channels and hands off to a human agent when the AI runs out of confidence, which is the part most demo projects skip. The one-command bootstrap and Docker Compose development setup make it easy to try on your own server. If you are weighing whether agent-based support can take over part of your ticketing flow, this is a concrete, self-hostable system to test against real conversations.