# LLVM: AI-friendly with conditions

> Contributors may use any tools, but a human must read and review all LLM-generated code or text, stay fully accountable, and label substantial tool-generated content, for example with Assisted-by. Agents acting without human approval are banned, and AI tools may not be used on good first issues.

- What it is: A collection of modular compiler and toolchain technologies, including Clang. (Programming language)
- Homepage: https://llvm.org/
- Repository: https://github.com/llvm/llvm-project
- Overall stance: AI-friendly with conditions (Mostly friendly). AI-assisted contributions are accepted with extra rules, such as disclosing AI use, or AI is banned for issues or written text.
- Last classified: 2026-10-09 (manual review, high confidence)
- Policy last changed: 2026-10-09
- Web page: https://areweaifriendly.com/projects/llvm/

## Policy by area

- **Code contributions**: AI-friendly with conditions (AI use must be disclosed; Contributor takes full responsibility; A human must review the output; Output must be license-compatible; No autonomous agents)
- **Issues & bug reports**: AI-friendly with conditions (AI use must be disclosed; A human must review the output)
- **AI-written text**: AI-friendly with conditions (AI use must be disclosed; A human must review the output)

## In their own words

- Code contributions: "Contributors must read and review all LLM-generated code or text before they ask other project members to review it. The contributor is always the author and is fully accountable for their contributions." (https://llvm.org/docs/AIToolPolicy.html)
- Code contributions: "Contributors are expected to be transparent and label contributions that contain substantial amounts of tool-generated content." (https://llvm.org/docs/AIToolPolicy.html)
- Code contributions: "An important implication of this policy is that it bans agents that take action in our digital spaces without human approval, such as the GitHub @claude agent." (https://llvm.org/docs/AIToolPolicy.html)
- Code contributions: "Using AI tools to regenerate copyrighted material does not remove the copyright, and contributors are responsible for ensuring that such material does not appear in their contributions." (https://llvm.org/docs/AIToolPolicy.html)
- Issues & bug reports: "Issues or security vulnerabilities" (https://llvm.org/docs/AIToolPolicy.html)
- AI-written text: "it is strongly recommended that contributors write PR descriptions themselves (if needed, using tools for translation or copy-editing)." (https://llvm.org/docs/AIToolPolicy.html)
- AI-written text: "Comments and feedback on pull requests" (https://llvm.org/docs/AIToolPolicy.html)

## Sources

- [LLVM AI Tool Use Policy](https://llvm.org/docs/AIToolPolicy.html), fetched 2026-10-09