LLMs may assist with code, but pure vibe coding is rejected: contributors must review, test and explain their changes and handle review themselves. LLM output is prohibited in issues, feature requests, PR bodies, comments and forum posts, except clearly noted LLM translations.
Policy by area
- Code contributionsPatches, pull requests and other changes written with AI tools.
- Friendly
- Contributor takes full responsibility
- A human must review the output
- Issues & bug reportsBug reports, security reports and issues found or written with AI tools.
- Unfriendly
- Only minor help (autocomplete, grammar)
- AI-written textPull request descriptions, issue comments and summaries written by AI.
- Unfriendly
- AI use must be disclosed
- Only minor help (autocomplete, grammar)
In their own words
Code contributions
And again, you are free to use LLMs to assist you, but not as the sole source of code changes.
You must review the output and be able to explain in the PR body - without LLM output as noted above - what is being changed and why.
The changes must be tested.
Issues & bug reports
LLM output is expressly prohibited for any direct communication, including the following:
AI-written text
An exception will be made for LLM-assisted translations if you are having trouble accurately conveying your intent in English. Please explicitly note this
Sources
- Jellyfin LLM/"AI" Policiesjellyfin.org/docs/general/contributing/llm-policies/Snapshot 9 Oct 2026