---
title: "llms.txt adoption: who's actually shipping it"
url: https://memory.wiki/qKRfGtCa
updated: 2026-05-14T18:15:49.480Z
hub: https://memory.wiki/hub/demo
bundle_count: 1
concept_count: 12
source: "memory.wiki"
---
# llms.txt adoption: who's actually shipping it

> Snapshot 2026-05-01. I'll re-run this every quarter.

## What llms.txt is, briefly

A plain-text discoverability file at the root of a site (`/llms.txt`) that tells AI agents what's available, in what shape, and where to fetch it. Inspired by `robots.txt` and `sitemap.xml`. Drafted by Jeremy Howard.

## Who's shipping it today

**Actively maintained, production:**

- Vercel — `vercel.com/llms.txt`. Comprehensive, includes per-product child files.
- Cloudflare — `developers.cloudflare.com/llms.txt`. Less comprehensive but on the public docs index.
- Anthropic Docs — `docs.anthropic.com/llms.txt`. Includes both `llms.txt` and `llms-full.txt`.
- Resend — `resend.com/llms.txt`. Short, tasteful, links the SDK reference.
- Trigger.dev — `trigger.dev/llms.txt`. Includes self-hosting docs.
- mdfy — every public hub auto-exposes `/llms.txt` for that hub's surface.

**Considering / partial:**

A handful of devtool platforms have it on a roadmap or under feature flag. Names withheld here — not yet public commitments.

## The pattern

It's **devtool companies first.** Every site shipping `llms.txt` today is either a developer platform, an SDK provider, or an AI/ML company. Consumer-facing sites haven't moved.

Two readings of why:

1. **The audience overlap.** Devtool customers ARE AI users. The feedback loop is short — a Cursor user complains they can't get good context from your docs, you ship llms.txt the next week.
2. **The build cost is trivial when your docs are already in markdown.** It's a couple lines of script to generate. Companies whose docs sit in WordPress or proprietary CMSes have a real build problem.

## Where mdfy fits

We make `llms.txt` part of the *user's* URL, not just the platform's. Any user's hub gets its own `/llms.txt`. Any AI tool can fetch it. That extends the standard's reach from "the sites the LLM-providers pay attention to" to "every user who's published anything."

## Followup

Watch HuggingFace, Replicate, and OpenAI's developer docs. If they ship it by end of Q3 2026 it tips into mainstream; if not, it stays a devtool convention.


---

## Concepts in this document
- **mdfy** _(entity)_
  A tool that stores project context and decision history, integrated into Cursor via custom rules.
- **Knowledge Management** _(tag)_
  Domain of organizing, storing, and retrieving information for human and AI use.
- **Obsidian** _(entity)_
  The primary subject being tested for import functionality and markdown compatibility.
- **Vercel** _(entity)_
  Early production adopter with comprehensive llms.txt implementation including per-product child files.
- **llms.txt** _(concept)_
  Plain-text discoverability standard for AI agents at site root, analogous to robots.txt and sitemap.xml.
- **Letta** _(entity)_
  Extracted memory system that infers behavioral patterns and work-shape preferences from conversation history with loose but contextually interesting extraction.
- **Multi-hop reasoning** _(concept)_
  GraphRAG's capability to answer comparative questions across documents by traversing graph structure; advantage over vector-only retrieval.
- **Mem0** _(entity)_
  Extracted memory system that produces factual, direct summaries from conversation history with strong extraction quality but limited stylistic or contextual nuance.
- **Community detection** _(concept)_
  Graph clustering technique (Leiden algorithm) that GraphRAG uses for structural priors; identified as improvement candidate for mdfy.
- **RAG Systems** _(tag)_
  Broad category of retrieval-augmented generation approaches for enhancing AI with external knowledge.
- **GraphRAG** _(entity)_
  Microsoft's knowledge-graph-based retrieval system that uses community detection for multi-hop reasoning; primary subject of analysis.
- **Extracted memory** _(concept)_
  AI-generated user profiles automatically inferred from conversation history without direct user authorship, central to both Mem0 and Letta approaches.

## Concept relations (within this doc's concepts)
- **Mem0** implements **Extracted memory**
- **Letta** implements **Extracted memory**
- **Mem0** is type of **Extracted memory**
- **Letta** is type of **Extracted memory**
- **mdfy** should adopt from **Community detection**
- **GraphRAG** enables capability **Multi-hop reasoning**
- **GraphRAG** uses for clustering **Community detection**

## Bundles containing this document
- [AI memory research: the public frontier](https://memory.wiki/b/wpwVCSDF)
  > Side-by-side notes on Mem0, Letta, Microsoft GraphRAG, Karpathy's LLM Wiki, llms.txt adoption.

_Hub canonical:_ https://memory.wiki/hub/demo
_Concept digest:_ https://memory.wiki/raw/hub/demo?digest=1&compact=1