Linux Kernel Developers Consider Adding AGENTS.md To Help Guide AI/LLM Agents
Linux kernel developer Sasha Levin has proposed adding an AGENTS.md file to the kernel source tree to guide AI and LLM agents. The file is intended to direct these agents to existing documentation, ensuring they adhere to kernel development standards such as proper attribution. While testing showed improved compliance with the file, some developers have raised concerns about increased token consumption.
- ▪Sasha Levin proposed introducing an AGENTS.md file to the Linux kernel to provide instructions for AI agents.
- ▪The proposed file links to the kernel's README and documentation on coding assistants to standardize AI behavior.
- ▪Testing revealed that without the file, AI agents often failed to use correct attribution tags or added unauthorized Signed-off-by lines.
- ▪Objections to the patch include concerns that directing AI to read the entire README will significantly increase token consumption.
Phoronix files mainly under tech. We currently carry 464 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Phoronix |
| Canonical URL | https://www.phoronix.com/news/Linux-Considers-AGENTS-MD |
| Publication time | Thu, 24 Sep 2026 20:53:14 -0400 |
| Retrieval time | 2026-09-25T01:05:28.283Z |
| Last seen | 2026-09-25T01:05:28.283Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | AUtlWbFpH6YM · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Linux Kernel Developers Consider Adding AGENTS.md To Help Guide AI/LLM Agents Written by Michael Larabel in Linux Kernel on 24 September 2026 at 08:53 PM EDT. Add A Comment While the Linux kernel continues to be bombarded with patches from AI/LLM agents, to date the kernel hasn't carried an AGENTS.md Markdown file with instructions catering to AI/LLM agents. But a patch set out today would finally introduce one. Longtime Linux developer Sasha Levin who has worked on other AI initiatives for the kernel like helping to determine patches for back-porting to the stable kernel tree and AI-powered merge conflict resolution is now looking to add an AGENTS.md to the kernel source tree. The proposed AGENTS.md is just linking to the Linux kernel's README file.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Phoronix.