Choose the documentation you need. Explore API references, implementation guides, and best practices.
Integration layer for OTOBO, Znuny/OTRS, and Zammad. Setup, connectors, automation rules, API, and troubleshooting.
On-prem ticket classification. Tag schema, output format, multilingual behavior, backlog tagging, hardware sizing, and evaluation.
Create the technical user and import the restricted Generic Interface webservice.
Environment variables and connectors for OTOBO, Znuny, and Zammad.
Understand how OTAI Studio credits are calculated and consumed.
Install the open-source Zammad MCP Server for Claude, Cursor, and typed Zammad ticket tools.
Open-source internal AI chat for Zammad — LibreChat plus the MCP server, in the cloud or fully on-prem.
Insights, updates, and articles from the team.
![Best Ollama Model for Zammad AI: On-Premise LLM Guide [2026]](/_astro/zammad-ai-hero.C0UUzIJ2.png)
Which Ollama model works best for Zammad 7 AI? A practical, on-premise model guide — the structured-output gotcha, real speed numbers, VRAM sizing, and which local LLM to pick for summaries, title rewriting, and classification.
Build an internal admin chat for your Zammad helpdesk with LibreChat and the Zammad MCP Server. Search tickets, summarize threads, and draft replies — in the cloud or fully on-prem with Ollama and Qwen 3.6.
Set up the free Zammad MCP Server for Claude, Cursor, and other MCP clients. Install with uvx, connect your Zammad API token, and use 30+ helpdesk tools.
