#llmsmap.me

Independent technical audit

agentsandboxes.fyi

agentsandboxes.fyi

Overall AI readiness score

A combined result across all audit signals.

99of 100Excellent
AI readiness audit: 10/28/2026Public technical data

About the site

AgentSandboxes is a neutral index of cloud sandboxes for AI agents, covering 25 providers with facts drawn from each vendor's own documentation. The site groups providers by categories such as code execution, dev environments, open source, browser sessions and evals, and offers comparison tools, a cost estimator and guides.

Category:
Developer tools
Platform:
Next.js

Written by AI from the site’s llms.txt and homepage.

Overall AI readiness assessment

How ready agentsandboxes.fyi is for AI systems

99/100

AgentSandboxes was independently audited by llmsmap. agentsandboxes.fyi currently scores 99/100 for AI readiness. The result combines AI-specific files, crawler policy, sitemap discovery, structured homepage data, and—when available—the mobile Google Lighthouse technical profile.

Audit context

llms.txt is accessible and contains 1,193 tokens. An expanded llms-full.txt is also available with 2,806 tokens, giving agents more direct context. A separate ai.txt policy is published.

robots.txt is available. 11 of 11 tracked AI bots are not blocked. Declared sitemaps: 1. The homepage exposes Schema.org types Organization, WebPage, WebSite, Dataset, Service and others; 10 OpenGraph tags were found and markup completeness is 100%.

The mobile Lighthouse profile adds Performance 71/100, Accessibility 100/100, Best Practices 100/100, SEO 100/100, and experimental Agentic Browsing 100/100. These signals have a limited weight: they complement rather than replace llms.txt, robots.txt, and structured-data checks.

Confirmed strengths

  • Accessible llms.txt
  • Expanded llms-full.txt
  • Published AI policy
  • 1 sitemap declaration
  • Schema.org: Organization, WebPage
  • Complete social metadata

Priority improvements

  1. 1Reduce mobile rendering delay and main-thread work.
llms.txt tokens1,193
llms-full.txt tokens2,806
ai.txt
sitemap.xml

Google Lighthouse technical profile

A mobile Lighthouse measurement. Google’s experimental Agentic Browsing category is explained separately and does not replace the broader llmsmap AI-readiness score.

Mobile · Lighthouse
71

Performance

100

Accessibility

100

Best Practices

100

Technical SEO

100

Agentic Browsing

What these results mean

Mobile performance is 71/100, with the largest visible content block appearing in 7.8 s and the browser main thread blocked for 0 ms. Layout shift was 0.007. The main thread is where the browser runs JavaScript, calculates layout, and paints the page; long work there delays both user input and browser-agent actions.

Accessibility scored 100/100, Best Practices 100/100, and technical SEO 100/100. The experimental Agentic Browsing category scored 100/100. It measures signals Google currently tests for software agents and is shown separately from the llmsmap AI-readiness score.

1

Free the main thread and accelerate the first view

Split long JavaScript tasks, defer non-critical scripts and styles, and shorten blocking request chains. This helps the primary content appear sooner and makes controls usable earlier.

2

Reduce code that loads without helping the page

Remove unused CSS and JavaScript, load heavy widgets on demand, and limit third-party scripts. Less code means less parsing and background work on the device.

3

Reduce network delay

Improve server response time, remove unnecessary redirects and repeat downloads, and use compression, caching, and selective preconnect hints.

FCP2.6 s

First content

LCP7.8 s

Main content

CLS0.007

Layout stability

TBT0 ms

Blocking time

SI3.6 s

Visual speed

Metric glossary
FCP · First content
When the first text or image appeared on screen.
LCP · Main content
When the largest visible element in the first viewport rendered.
CLS · Layout stability
How much content shifted unexpectedly while loading; lower is better.
TBT · Blocking time
How long the browser main thread could not respond quickly to input.
SI · Visual speed
How quickly the visible viewport filled with content.
10/28/2026Lighthouse 13.5.0Mobile profile

AI readiness checks

Machine-readable files, crawler policy, discovery, and homepage markup.

llms.txt

File found and accessible

https://agentsandboxes.fyi/llms.txt
llms-full.txt

Full version is available

https://agentsandboxes.fyi/llms-full.txt
ai.txt

AI rules are defined

https://agentsandboxes.fyi/ai.txt
robots.txt

File found

https://agentsandboxes.fyi/robots.txt
Sitemap in robots.txt1

1 sitemap found

Schema.org (JSON-LD)

Types: Organization, WebPage, WebSite, Dataset, Service, FAQPage

OpenGraph100%

10 OG tags found

AI bot access

Based on robots.txt analysis

GPTBotAllowed
OAI-SearchBotAllowed
ChatGPT-UserAllowed
Google-ExtendedAllowed
ClaudeBotAllowed
Claude-SearchBotAllowed
Claude-UserAllowed
BytespiderAllowed
CCBotAllowed
PerplexityBotAllowed
Perplexity-UserAllowed

Sitemaps

Declared discovery routes for crawlers and agents.

https://agentsandboxes.fyi/sitemap.xml

OpenGraph tags

Social preview metadata found on the homepage.

Markup completeness: 100%
og:titleCloud sandboxes for AI agents: a neutral index | AgentSandboxes
og:descriptionCompare 25 sandbox providers by isolation, cold start, persistence, GPU support, pricing model and free tier.
og:urlhttps://agentsandboxes.fyi
og:site_nameAgentSandboxes
og:localeen
og:imagehttps://agentsandboxes.fyi/og
og:image:width1200
og:image:height630
og:image:altCloud sandboxes for AI agents: a neutral index | AgentSandboxes
og:typewebsite

Schema.org markup

Structured entities and properties exposed on the homepage.

Types found: 6 · Properties: 9
OrganizationWebPageWebSiteDatasetServiceFAQPage
nameAgentSandboxes
urlhttps://agentsandboxes.fyi/
logohttps://agentsandboxes.fyi/brand/logo.svg
descriptionCompare 25 sandbox providers by isolation, cold start, persistence, GPU support, pricing model and free tier.
inLanguageen
author{"@id":"https://agentsandboxes.fyi/#organization"}
publisher{"@id":"https://agentsandboxes.fyi/#organization"}
potentialAction{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://agentsandboxes.fyi/search?q={search_term_s
dateModified2026-10-21T15:19:57.993Z
# AgentSandboxes

> A neutral index of cloud sandboxes for AI agents.

> **Check before you choose.** Vendor specs and prices change. Follow the cited source on each listing before you pick a provider.

AgentSandboxes lists 25 sandbox providers. Updated 2026-10-21. Every page has a markdown copy: add `.md` to its URL, or send `Accept: text/markdown`. The home page copy is [index.md](https://agentsandboxes.fyi/index.md).

## Regions

- [Global](https://agentsandboxes.fyi/global.md): 25 sandbox providers

## Sandbox providers by city

- [Online, Global](https://agentsandboxes.fyi/global/online.md): 25 sandbox providers

## Categories

- [Code execution](https://agentsandboxes.fyi/category/code-execution.md): 19 sandbox providers
- [Dev environments](https://agentsandboxes.fyi/category/dev-environments.md): 8 sandbox providers
- [Open source](https://agentsandboxes.fyi/category/open-source.md): 8 sandbox providers
- [Browser sessions](https://agentsandboxes.fyi/category/browser.md): 3 sandbox providers
- [Computer use](https://agentsandboxes.fyi/category/computer-use.md): 2 sandbox providers
- [Evals and RL](https://agentsandboxes.fyi/category/evals-rl.md): 2 sandbox providers

## Free tools

- [Sandbox cost estimator](https://agentsandboxes.fyi/tools/sandbox-cost-estimator.md): Estimate a monthly sandbox compute bill from runs, seconds, vCPU, GiB and the provider's published rates.
- [Compare sandboxes](https://agentsandboxes.fyi/tools/compare-sandboxes.md): Compare two or three sandbox providers side by side: isolation, cold start, persistence and price.

## Guides

- [Common mistakes and questions about sandbox providers](https://agentsandboxes.fyi/guides/common-mistakes-and-questions.md): Six mistakes that teams make when picking a cloud sandbox provider and the questions to ask before you commit, based on specs recorded in this index.
- [How to compare sandbox providers](https://agentsandboxes.fyi/guides/how-to-compare-sandbox-providers.md): Compare sandbox providers by isolation, cold start, persistence, GPU support, pricing model and free tier using a standard checklist and the compare tool on this site.
- [What a sandbox provider listing shows](https://agentsandboxes.fyi/guides/how-to-read-a-listing.md): Every listing on this site records the specs a provider publishes on its own docs or pricing page: isolation, cold start, persistence, GPU, pricing and more. Each row links the cited source.
- [Sandbox providers for global agent teams](https://agentsandboxes.fyi/guides/sandbox-providers-for-global-agent-teams.md): Every provider in this index serves the Online or Global scope. This guide covers what that means for latency, data residency, team access and compliance.

## About this site

- [About AgentSandboxes](https://agentsandboxes.fyi/about.md): What AgentSandboxes is, where its data comes from, and how a listing is checked.
- [Contact AgentSandboxes](https://agentsandboxes.fyi/contact.md): How to reach AgentSandboxes: our email address, how fast we reply, and how to add or fix a listing.
- [Link exchange with AgentSandboxes](https://agentsandboxes.fyi/link-exchange.md): Swap links with AgentSandboxes for free. You link to us. We check the link. An approved site gets a partners page link, a guide mention, or a blog mention.
- [The sandbox newsletter](https://agentsandboxes.fyi/newsletter): A short email now and again: a new provider, a pricing change that matters, and one source note. No noise.

## Data sources

- [Vendor documentation and pricing pages, as described on our About page](https://agentsandboxes.fyi/about): license Fact-level data (prices, limits, isolation classes); open-licensed doc sets include Cloudflare docs (CC BY-4.0) and Fly.io docs (Apache-2.0), refreshed monthly

## API

- [OpenAPI 3.1 description](https://agentsandboxes.fyi/api/v1/openapi.json): the read API as JSON
- [API guide](https://agentsandboxes.fyi/developers): endpoints, examples, rate limits and how to credit the data
- [MCP server card](https://agentsandboxes.fyi/.well-known/mcp/server-card.json): the MCP server at https://agentsandboxes.fyi/mcp and its tools
- [Agent card](https://agentsandboxes.fyi/.well-known/agent-card.json): the A2A agent at https://agentsandboxes.fyi/a2a and its skills
- [Agent skills](https://agentsandboxes.fyi/.well-known/agent-skills/index.json): a skill that explains the API and the MCP server
- [API catalog](https://agentsandboxes.fyi/.well-known/api-catalog): the API description and the guide as an RFC 9727 linkset
- [WebMCP manifest](https://agentsandboxes.fyi/webmcp): the tools as a manifest

## Optional

- [Every sandbox provider with its facts](https://agentsandboxes.fyi/llms-full.txt)
- [Sitemap](https://agentsandboxes.fyi/sitemap.xml): every indexable page
Share or continue the analysis
Share this audit
Discuss with AI
Added 10/28/2026

Similar sites in the directory

Sites with a close AI-readiness score — compare how they set up llms.txt and markup.

agentsandboxes.fyi - AI readiness audit | llmsmap.me