# Readable > Free tool that turns your website into an llms.txt file and clean markdown copies that AI agents can read. No login, no wallet, public pages only. # Make your website readable by AI agents. Source: https://agentreadable.site/ [NEW The Pons Readability Index, monitor alerts and a CLI](https://agentreadable.site/pons/) Paste a URL. Readable reads up to 30 public pages, strips menus, scripts and banners, and writes an llms.txt plus clean markdown copies for you to upload to your own site. [Check a score](https://agentreadable.site/check/) - No login - No wallet - Public pages only - Up to 30 pages - robots.txt respected - Free An llms.txt as Readable writes it, for an illustrative token site. The files work wherever you can upload them - Next.js - Vite - Astro - SvelteKit - WordPress - GitHub Pages - Netlify - Cloudflare Pages - Any static host The difference ## From unreadable to agent-ready in _one_ upload. Agents skim. A site built for browsers hides its text behind menus, scripts and banners. Readable writes the version agents read in one request, and shows the score it will get before you upload anything. - Every check of the score is explained, with the pages that fail it. - The score after upload is projected honestly, never padded. - Pages that need JavaScript are flagged, not guessed. - llms.txt - llms-full.txt - pages/\*.md Example scan. The sites and figures are illustrative. How it works ## Four steps, no account. Readable only reads what a visitor could read. You stay in charge of your site: it never asks for a login, a wallet or access to your hosting. 1. ### Paste your URL Readable reads your robots.txt first, then your homepage. Login and admin pages are never touched. robots.txt → homepage 2. ### We read and clean Up to 30 pages, closest first. Menus, scripts and banners go; the text and its structure stay. 30 pages · 70–95% smaller 3. ### Download and upload One zip with llms.txt, llms-full.txt and a markdown file per page. Put it in your site's web root. readable.zip → /public 4. ### Check your score The checker reads your site the way an agent would and scores it from 0 to 100, with a badge and daily monitoring if you want them. /check · /badge · /monitor What a scan keeps ## Noise out, text in. Every page is edited down to what a reader needs, then written as markdown that agents can read in one request. Struck out - navigation menus - scripts - cookie banners - pop-ups - hidden elements - tracking pixels - footers - share buttons Kept - headings - paragraphs - lists - tables - code - links - image text 70–95% smaller than the HTML, page by page 30 pages per scan, closest to your homepage first 0 logins, wallets or cookies | File | What it is | | --- | --- | | `llms.txt` | Site title, one-line summary, and your pages grouped into About, Tokenomics, Docs and Optional. | | `llms-full.txt` | Every page's markdown in one file, for agents that want everything at once. | | `pages/*.md` | One clean markdown copy per page, linked from llms.txt. | The score ## One score, from 0 to 100. The checker fetches your `/llms.txt` and the pages it lists, the way an agent would. Five checks, the same rules everywhere. [Check any site →](https://agentreadable.site/check/) 1. An llms.txt with a title and sections At /llms.txt, with an H1 title and at least one section. 20 pts 2. A summary under the title One line in a blockquote: what the site is. 15 pts 3. Markdown copies of the listed pages Proportional: each listed page counts. 25 pts 4. Text without JavaScript The listed pages show their content as served. 20 pts 5. Links that resolve Every link in llms.txt answers 2xx. 20 pts **Not readable** 0–49 **Needs work** 50–79 **Agent-readable** 80–100 Read this first ## What Readable can't promise. llms.txt is young. Here is what it does today, and what this tool is not, before you rely on either. Not guaranteed today - AI products are not required to read llms.txt. Some agents and developer tools fetch it when they find it; many don't. We can't promise any specific AI will use it. - llms.txt is a community proposal ([llmstxt.org](https://llmstxt.org/)), not an official standard. The format can still change. - It is not an SEO tool. Don't expect search ranking changes. - Pages that only show content after JavaScript runs can't be converted. Readable flags them instead of guessing. What this is not - Not a security audit, and not a safety check for any token. - Not investment advice. - Not hosting: you download the files and upload them yourself. - Not a browser: no headless rendering, no JavaScript execution. - No login, no wallet connection, no access to your hosting. More tools ## Keep it readable. The same checks, wherever you need them: on a page, in your README, in your inbox, or in CI. [Checker](https://agentreadable.site/check/) Score any site Five checks in a few seconds, with what to fix for each one. [Badge](https://agentreadable.site/badge/) Show your score A live SVG badge for your README or site footer. [Monitor](https://agentreadable.site/monitor/) Know when it breaks A daily re-check with Telegram or webhook alerts. No account. [Index](https://agentreadable.site/pons/) Pons Readability Index How readable are the websites of tokens launched on Pons? Ranked weekly. [Command line](https://agentreadable.site/docs/#cli) npx agentreadable Scan and check from your terminal, or fail a CI build below a score. [Docs](https://agentreadable.site/docs/) How it all works The score, the crawler, the upload, privacy and limits. ## Make your site _readable_. One URL, a few seconds, and a zip of files you can upload today. Free. No account. Public pages only. # How readable is a site to AI agents? Source: https://agentreadable.site/check/ Checker The checker reads a site's `/llms.txt` and the pages it lists, the way an agent would, and scores it from 0 to 100. Try these ## Sites that publish an llms.txt Scores are live and cached for up to a day. Listed as examples only. - [llmstxt.org ![Readable score for llmstxt.org](https://agentreadable.site/b/llmstxt.org.svg)](https://agentreadable.site/check/?url=llmstxt.org) - [developers.cloudflare.com ![Readable score for developers.cloudflare.com](https://agentreadable.site/b/developers.cloudflare.com.svg)](https://agentreadable.site/check/?url=developers.cloudflare.com) - [docs.stripe.com ![Readable score for docs.stripe.com](https://agentreadable.site/b/docs.stripe.com.svg)](https://agentreadable.site/check/?url=docs.stripe.com) - [svelte.dev ![Readable score for svelte.dev](https://agentreadable.site/b/svelte.dev.svg)](https://agentreadable.site/check/?url=svelte.dev) How the score works Five checks, 100 points. The same code runs here, in the badge and in the CLI. Only the first 10 links in an llms.txt are checked, so big files are scored on a sample. | Check | Points | | --- | --- | | /llms.txt exists, valid H1 title, ≥1 section | 20 | | Summary blockquote under the title | 15 | | Markdown copies of listed pages (the link is markdown, or the page has a markdown version) | 25, proportional | | Listed pages show text without JavaScript | 20, proportional | | Links in llms.txt resolve (2xx) | 20, proportional | # Show your agent-readability score. Source: https://agentreadable.site/badge/ Badge kit A small SVG badge with your live score. It refreshes at most once a day, so it costs nothing to embed. Details - URL: `/b/.svg`, with `?theme=light` for light backgrounds. The domain is the site's host name, like `docs.example.com`. - Colors follow the score: green from 80 (AGENT-READABLE), orange from 50 (NEEDS WORK), red below (NOT READABLE). - Cached for 24 hours. After you upload new files, the badge can lag by up to a day. # Know when your site stops being readable. Source: https://agentreadable.site/monitor/ Monitor Readable re-checks watched sites every day and alerts you by Telegram or webhook. No account: you get a private link to change or stop the watch. Alerts when - SCORE The score drops below 80 - LINK A link in your llms.txt breaks - PAGE A new page is missing from your llms.txt History keeps your last 30 daily scores. Capacity is limited on the free plan, so the number of watched sites is capped. Watch a site Website Send alerts to Telegram Webhook Telegram chat ID Message the Readable bot on Telegram; it replies with your chat ID. # Which Pons token sites can AI agents read? Source: https://agentreadable.site/pons/ Pons Readability Index A weekly ranking of the websites of tokens that graduated on Pons, by agent-readability score. Read this first - **Not investment advice.** A high score says nothing about a token's value or prospects. - **Not a safety check.** Readable does not audit contracts, teams or liquidity. A readable website can belong to a scam. - **Not affiliated with Pons or Robinhood.** This index is independent and uses only public data: launch records on Robinhood Chain and the public pages of each website. Loading the latest index… | Rank | Token | Site | llms.txt | 7-day change | Score | | --- | --- | --- | --- | --- | --- | | Loading… | | | | | | Scores come from the same checks as the [checker](https://agentreadable.site/check/), with up to 5 links per site. Token names link to the Robinhood Chain explorer; scores open the full check. How tokens are picked and when the index updates: [methodology](https://agentreadable.site/docs/#pons). # How Readable works Source: https://agentreadable.site/docs/ Docs Everything Readable does, what it doesn't, and how to undo it. ## What Readable does You give Readable a website address. It reads up to 30 public pages of that site, removes navigation, scripts, cookie banners and hidden elements, converts what is left to markdown, and writes three things: - **`llms.txt`**: the site's name, a one-line summary, and links to every page, grouped into _About_, _Tokenomics_, _Docs_ and _Optional_. - **`llms-full.txt`**: the markdown of every page in one file. - **`pages/*.md`**: one markdown file per page. You download them as a zip and upload them to your own site. Readable never hosts them for you, and never needs a login, a wallet or access to your hosting. The same input always gives the same output, byte for byte: no timestamps, no random order. ## What llms.txt is llms.txt is a [community proposal](https://llmstxt.org/): a markdown file at the root of a website (or of a folder) that tells language models and AI agents what the site is and where its important pages are, ideally as plain markdown. It is **not an official standard**, and no AI product is required to read it. Version 2 of the proposal (August 2026) also describes where a page's markdown version lives: at the page URL with `.md` appended (`page.html.md`) or with the extension replaced (`page.md`), or wherever the page points with ``. The checker accepts all of these. Readable writes its copies to `pages/.md` and links them from llms.txt. ## Upload your files Upload everything to your site's **web root**, so these addresses work: ``` https://your-site.com/llms.txt https://your-site.com/llms-full.txt https://your-site.com/pages/.md ``` | Your site runs on | Put the files in | | --- | --- | | Next.js, Vite, Astro, SvelteKit, most frameworks | `public/` (in Next.js, **not** the `pages/` folder) | | WordPress | the folder that contains `wp-config.php` | | GitHub Pages, Netlify, Cloudflare Pages, static hosts | the folder you publish | | Webflow, Wix, Squarespace, Framer | usually not possible: these builders don't allow it | Then run the [checker](https://agentreadable.site/check/) to confirm your score. ### Scanning a folder Enter a folder address ending in `/` (for example a GitHub Pages project site, `https://you.github.io/project/`) and Readable scans only that folder. The files are then meant for that folder: `https://you.github.io/project/llms.txt` and `…/project/pages/*.md`. Version 2 of the proposal says an llms.txt covers the pages under its folder. Enter the homepage to scan the whole site. ### Optional: point pages to their copies The result page also gives you snippets that let agents go straight from a page to its markdown copy, as version 2 of the proposal describes: - a `` tag for every page, - a `` tag per page, - or the same as `Link:` headers, in the `_headers` format of Netlify and Cloudflare Pages. In Next.js, set `alternates.types['text/markdown']` in a page's metadata. All of this is optional: agents that read llms.txt find the copies anyway. Readable keeps every copy in one `pages/` folder on purpose. The proposal also allows copies next to each page (`/about/index.md`), but that creates real folders like `/about/`, and on WordPress and many PHP or Nginx setups a real folder takes priority over the page with the same address, which can break it. ## The score The checker fetches `/llms.txt` and the pages it lists, the way an agent would. It checks at most 10 links per site. For a URL in a folder (like a GitHub Pages project site), it uses the most specific llms.txt it finds, as version 2 of the proposal describes. | Check | Points | | --- | --- | | `/llms.txt` exists, has an H1 title (`# Name`) and at least one section (`## Section`) | 20 | | A summary blockquote (`> …`) under the title | 15 | | Markdown copies of listed pages: the link is itself markdown, or the page has a markdown version | 25, proportional | | Listed pages show at least 200 characters of text without running JavaScript | 20, proportional | | Links in llms.txt answer with 2xx | 20, proportional | 80 and up is **AGENT-READABLE**, 50 to 79 **NEEDS WORK**, below 50 **NOT READABLE**. Results are cached for 10 minutes. ## Pages that need JavaScript Readable does not run JavaScript and has no headless browser. If a page shows almost no text until scripts run (a typical single-page app), Readable flags it and leaves it out. To fix it, render the page on the server (static generation or server-side rendering), or write its markdown copy by hand. ## Badge ``` https://agentreadable.site/b/your-site.com.svg https://agentreadable.site/b/your-site.com.svg?theme=light ``` The badge shows your live score and is cached for 24 hours. Make one on the [badge page](https://agentreadable.site/badge/). ## Command line The same scan and checker run in your terminal with Node.js 20 or later. Nothing goes through agentreadable.site: ```sh npx agentreadable scan your-site.com --out public npx agentreadable check your-site.com --min 80 ``` - `scan` writes `llms.txt`, `llms-full.txt` and `pages/*.md` into `--out` (default `readable/`) and prints the score the site will get once they are uploaded. - `check` prints the five checks and the score. With `--min`, it exits with code 1 when the score is lower, so a CI build can fail when agents can no longer read your site. `--json` prints the result as JSON. - `--allow-private` lets it fetch a development server on `localhost`. In GitHub Actions: ```yaml - uses: actions/setup-node@v4 with: node-version: 22 - run: npx --yes agentreadable@0.1 check https://your-site.com --min 80 ``` ## The crawler Readable fetches pages with this user agent: ``` Readable/0.1 (+https://agentreadable.site/docs#crawler) ``` - It only fetches pages when someone asks for it: a scan, a check, or a badge view. The only scheduled fetches are the daily re-check of sites someone chose to monitor and the weekly [Pons Readability Index](https://agentreadable.site/docs/#pons). - It reads `robots.txt` before anything else and obeys it for the `Readable` user agent and for `*`, in scans, checks, badges, the monitor and the index, `llms.txt` included. If `robots.txt` can't be fetched because of a server error, it fetches nothing. Links in your llms.txt that `robots.txt` blocks are skipped, not counted as broken. - It never visits login, sign-up, admin, account or dashboard paths, and never sends cookies. - At most 30 pages per scan, 2 MB per page, 3 redirects per request, and only public `http`/`https` addresses: private networks are blocked. To keep Readable off your site: ``` User-agent: Readable Disallow: / ``` ## Monitor The [monitor](https://agentreadable.site/monitor/) re-checks a site about once a day and alerts you on Telegram or by webhook when: - the score drops below 80 (while it stays low, you get a reminder at most once a week), - a link in your llms.txt stops working, - a page linked from the watched page is missing from your llms.txt. Pages already there at the first check count as the baseline. Each check reads your llms.txt, up to 3 of the links it lists, and the watched page. The last 30 scores are kept. **Telegram:** message the Readable bot; it replies with your chat ID. **Webhook:** an `https` address on the public internet. Redirects are not followed. Readable sends a `POST` with a JSON body like: ```json { "type": "readable.alert", "url": "https://your-site.com/", "score": 55, "label": "NEEDS WORK", "reasons": ["The score is 55/100 (NEEDS WORK)."], "brokenLinks": [], "newPages": ["/staking"] } ``` There is no account. When you start watching, you get a private link to see the history or stop the watch; we only store a hash of its secret, so keep the link safe. Capacity is limited to keep the service free (250 sites). ## Pons Readability Index The [index](https://agentreadable.site/pons/) ranks the websites of tokens launched on Pons, the token launchpad on Robinhood Chain, by the same score as the [checker](https://agentreadable.site/check/). - **Which tokens:** tokens that graduated from their bonding curve (most launches never do) and whose creator entered a website. Links to X, Telegram, Discord, Linktree, GitHub, chart sites and the like are not websites and are left out. The index holds the 150 most recent of them. - **Where the data comes from:** the public launch records of the Pons V2 factory on Robinhood Chain (chain ID 4663), read through the chain's public RPC: graduation events, and each token's name, symbol and website as stored in its contract. Nothing is signed and no wallet is involved. - **How it updates:** sites are checked through the week, each once, with up to 5 links from its llms.txt. Every Monday (UTC) the finished week is published. The 7-day change compares a token's score with last week's index; "new" means the token was not in it. - **Launched this week** means the token launched in the same week it is listed for. - A site whose `robots.txt` blocks Readable is left out. So is, for that week, a site that needs too many requests to check (long redirect chains). The index says nothing about a token's value, team or safety. It is not investment advice, and it is not affiliated with Pons or Robinhood. To keep your site off the list, block Readable in `robots.txt`; it drops out within two weekly updates. ## Privacy - No accounts, no cookies, no tracking scripts. - A scan runs in your browser. Our server only fetches the pages for you and does not store them. The result stays in your browser tab. - If you click **Publish result page**, we store your llms.txt and the scores for 60 days at a public link. - If you start watching a site, we store its address, your Telegram chat ID or webhook URL, and the last 30 scores until you stop the watch. - We don't keep request logs. Cloudflare runs our servers and processes requests to deliver them. Fonts load from Google Fonts. ## Limits - 30 pages per scan, closest pages first; 2 MB per page. - Scans, checks and publishing are rate-limited per network to keep the service free. - The checker scores at most 10 links of an llms.txt. - Published result pages expire after 60 days. ## Not guaranteed today - AI products are not required to read llms.txt. Some agents and developer tools fetch it when they find it; many don't. - llms.txt is a proposal, and its format can still change. - It is not an SEO tool. Don't expect search ranking changes. ## What this is not - Not a security audit, and not a safety check for any token. - Not investment advice. - Not hosting, and not a browser: no JavaScript is run.