---
title: How we Built a Fully Open-Source AI Chatbot for TYPO3
url: "https://news.typo3.com/article/how-we-built-a-fully-open-source-ai-chatbot-for-typo3"
description: A modern AI chatbot can run completely on open-source technologies with just one TYPO3 extension. No external providers are needed — just a connection to an LLM.
image: "https://news.typo3.com/fileadmin/_processed_/f/4/csm_Easychat_5_3_Crop_5b3e31c3b0.webp"
date: 2026-09-22
modified: 2026-09-24
categories:
  - "Developer & Technology"
---

# How we Built a Fully Open-Source AI Chatbot for TYPO3

- [Developer & Technology](https://news.typo3.com/article/category/developer-technology)

How we Built a Fully Open-Source AI Chatbot for TYPO3
=====================================================

24 September 2026

![EasyChat Chatbot interface showing three steps: accepting cookie consent, asking a question, and receiving an answer.](https://news.typo3.com/fileadmin/_processed_/f/4/csm_Easychat_5_3_Crop_9fe1b25ca8.webp)

A modern AI chatbot can run completely on open-source technologies with just one TYPO3 extension. No external providers are needed — just a connection to an LLM.

- ![](https://news.typo3.com/typo3temp/assets/t3g/blog/gravatar/bbf959d8e683550c90ae922aff9145d8.jpeg)[Eike Starkmann](https://news.typo3.com/article/author/eike-starkmann)

 The Limitations of Common Chatbot Services
--------------------------------------------

Most chatbot solutions are based on external platforms. In practice, this often means:

- Data is processed outside your own infrastructure
- Vendor lock-in and dependency on a single provider
- Ongoing usage and subscription fees
- Limited control over language models and data storage

 New Paths With EasyChat
-------------------------

At [undkonsorten](https://www.undkonsorten.com), we needed a solution that can be deployed in environments with high data protection standards. Running an AI chatbot within TYPO3 has many advantages:

- Open source instead of SaaS
- Data storage directly in TYPO3
- Free choice of language models (LLM)
- No additional platform and payments required
- Full control of knowledge through internal [retrieval-augmented generation (RAG)](https://en.wikipedia.org/wiki/Retrieval-augmented_generation)

Since chat histories are stored directly in TYPO3, the data remains entirely under the control of the website operator. Furthermore, chats can be deleted automatically with a scheduler task and existing TYPO3 content can be integrated as a knowledge base.

 The Technical Foundation
--------------------------

EasyChat is built entirely on open-source components. [DeepChat](https://deepchat.dev/) serves as the chat frontend and provides the user interface. TYPO3 and [Symfony AI](https://github.com/symfony/ai) process user queries and manage key tasks, including:

- Communication with the LLM
- Storage of chat data
- Consent management
- Request processing via [TYPO3 Reactions](https://docs.typo3.org/permalink/typo3-cms-reactions:introduction)
- RAG/Indexing with the new [TYPO3 Indexer Extension](https://github.com/lochmueller/index)
- Qdrant support as vector database

EasyChat is not locked to a specific provider. It is designed to be model-agnostic. Currently, we use the open-source model *gpt-oss-120b* (via AI hosting in Germany by [TYPO3 partner](https://typo3.com/partners) [Mittwald](https://www.mittwald.de/)). However, you can also connect models like Mistral or ChatGPT directly if desired.

  [  Show larger version for:          ![Chatbot conversation interface showing three message exchanges about life meaning and personal growth](https://news.typo3.com/fileadmin/_processed_/3/7/csm_DeepChat_79879002f6.webp) ](https://news.typo3.com/fileadmin/_processed_/3/7/csm_DeepChat_a6206f09ad.webp)

 Building on TYPO3's Existing Features
---------------------------------------

Luckily TYPO3 is already equipped out-of-the-box with many features we needed for our chatbot application:

- **Admin Interface / Backend Modules**
- **Reactions** to receive and handle incoming chat requests
- [**Scheduler Tasks**](https://docs.typo3.org/permalink/typo3-cms-scheduler:introduction) for automated data cleanup and deletion
- [**Fluid Templating Engine**](https://docs.typo3.org/permalink/t3coreapi:fluid-introduction) for customized chatbot design and theming overrides
- **Content (aka. knowledge) management:** You might already have all the knowledge the chatbot would need as TYPO3 content
- **RAG-Indexing** solutions

Instead of introducing additional third-party systems, we leverage the existing TYPO3 infrastructure.

  [  Show larger version for:          ![Dashboard showing chat sessions table with session IDs, delete actions, and creation timestamps from January 26, 2026](https://news.typo3.com/fileadmin/_processed_/e/9/csm_Backend-Module_15adfb92cb.webp) ](https://news.typo3.com/fileadmin/_processed_/e/9/csm_Backend-Module_8e0b9b5af3.webp)

  [  Show larger version for:          ![Easychat plugin configuration page showing reaction URL, secret, introduction message, and data protection settings](https://news.typo3.com/fileadmin/_processed_/2/8/csm_Content-Element_598e22c9cd.webp) ](https://news.typo3.com/fileadmin/_processed_/2/8/csm_Content-Element_269de1646c.webp)

  [  Show larger version for:          ![Configuration form for Support Chatbot (gpt-oss) with fields for name, model, URL, API key, and system prompt settings](https://news.typo3.com/fileadmin/_processed_/7/c/csm_Configuration_c5b407db5a.webp) ](https://news.typo3.com/fileadmin/_processed_/7/c/csm_Configuration_95c53e2e92.webp)

  [  Show larger version for:          ![Admin panel showing Reactions page for managing incoming HTTP webhooks with reaction type filters and webhook URL details](https://news.typo3.com/fileadmin/_processed_/b/9/csm_Reactions_6f29e657e8.webp) ](https://news.typo3.com/fileadmin/_processed_/b/9/csm_Reactions_bc6b1fbe8b.webp)

 Upcoming Features
-------------------

The extension of course is open source and we warmly invite you to contribute – so it can grow and become a standard TYPO3 chatbot extension.

- **RAG Improvement** — At the moment we are planning on improving the RAG feature so that we can index different kinds of content (`<span>tt_content</span>`, FAQs) and add it to the knowledge database.
- **Vector Databases** — At the moment we support Qdrant, but we will soon be supporting more and more databases like PostgreSQL or Redis.
- **Answer Rating** — Users can rate the answers so that the knowledge base can be improved.
- **Conversation History** — Improved insights of what the clients are actually asking or want to know from the bot in the TYPO3 Backend.

And many more.

 Ready to Get Started?
-----------------------

###  Resources and Links

- [Demo page](https://easychat.undkonsorten.com/)
- [EasyChat in the TYPO3 Extension Repository](https://extensions.typo3.org/extension/easychat)
- [EasyChat on GitHub](https://github.com/undkonsorten/easychat)
- [Documentation](https://github.com/undkonsorten/easychat/blob/develop/Readme.md)

![](https://news.typo3.com/typo3temp/assets/t3g/blog/gravatar/b5c88386e5b1d8fca79d0652427922d2.jpeg)

About the Author

[Eike Starkmann](https://news.typo3.com/article/author/eike-starkmann)

[More posts by this author](https://news.typo3.com/article/author/eike-starkmann)