On this page
Jellyfin LLM/"AI" Development Policy
The rise of LLMs as a useful development tool over the last year or so has been significant. The power and flexibility of tools like Claude Code and ChatGPT have given a lot of functionality both to experienced developers and new developers alike. But there are trade-offs.
The Jellyfin project has, from day one, had a major focus on code quality - readability, simplicity, conciseness. This is a mostly manual effort driven by a dedicated team of individuals, and is motivated by a desire to fix the code Jellyfin is based off of which, without beating a dead horse too much, was extremely fragile, spaghettified, and prone to over-engineered complexity.
We are seeing a precipitous rise in contributors using AI within the Jellyfin ecosystem, both in the server and for clients, as well as a rise in criticism and concern about LLMs generally. At this time we are writing this policy to address exactly what we expect and desire with respect to contributions and interactions within our community that may use LLMs. These rules apply to all of our official projects and community spaces.
LLM output is expressly prohibited for any direct communication, including the following: issues or comments
feature requests or comments
pull request bodies or comments
forum/chat/etc. posts or comments In short, if you are posting any of those things, the output must be your own words, explanation, description, etc., not a verbatim dump of an LLM's output. We expect you to understand what you're posting. Violating this rule will result in closure/deletion of the offending item(s). An exception will be made for LLM-assisted translations if you are having trouble accurately conveying your intent in English. Please explicitly note this ("I have translated this from MyLanguage with an LLM") and, if possible, post in your original language as well. LLM code contributions are subject to more granularity below, but the general principle is that "pure 'vibe coding' will be rejected" and "you are responsible for what you commit". We will review in that vein. If the code looks terrible, it will be rejected as such.
The use of LLMs for code is controversial and open to much interpretation. These guidelines are our best effort attempt to ensure that knowledgeable developers who seek to use these tools as a legitimate aid are not overly-hindered, while also preventing an ongoing flood of slop contributions that violate our core ethos above. These apply to all official Jellyfin projects.
... continue reading