Skip to content
Good for Bots

AI Sandbox Hunt

aisandboxhunt.com

Independent directory rating and comparing 103 AI agent sandboxes, dev boxes and CI runners

Click badge to copy

Changed your site? Run a new scan.

Claim to rescan

Claiming is free. Verify ownership to request a rescan after deploying your changes.

Unclaimed listings are checked automatically every 90 days.

Good for Bots report

AI Sandbox Hunt scores 86 of 100: the whole readable base, 36 of the 50 agent-layer points, no penalties.

Earned

The whole readable base above the line, 36 of the 50 agent-layer points below it.

86

3 prompts away

Copy them below ↓

14
Penalties0
How scoring works · current methodology →

Through a bot’s eyes

“AI Sandbox Hunt is an independent directory that rates and compares 103 AI agent sandboxes, dev boxes, browser and GPU sandboxes and CI runners, with sourced prices and a published method.”

Simulated from the response GoodForBotsBot received on , not a live answer from any AI assistant.

What it can read, and what stays hidden →

What a bot can read

The homepage text covers agent sandboxes and related categories, the site's published method, monthly prices for a reference workload, the top provider in each category, a comparison of per-vCPU-hour prices, and short answers to four questions about agent sandboxes, dev boxes, scoring and vendor listing. Prices, free-tier notes and isolation labels for the top providers appear as text, and the guides and tools are present as links. No Markdown version of the homepage was provided. The llms.txt file adds a site summary, a list of guides and tools, and one-line entries for the leading agent sandboxes with monthly list prices and check dates, plus links to a machine-readable API and a full Markdown file of provider facts. Its provider list is cut off partway through. The JSON-LD blocks describe the WebSite, the Organization, the four FAQ answers and a Dataset covering the directory's prices and update date.

What stays hidden

The homepage text does not list all 103 providers, so a model reading only this input cannot name most of them or compare them. The scoring criteria are only named, not explained, and the method page was not read. Monthly prices appear for only a few providers, and per-vCPU prices for twelve of the 64 providers that publish one. User reviews are not present as text. The llms.txt input stops in the middle of its provider list. Nothing here shows which provider suits a given workload.

What is AI Sandbox Hunt?

AI Sandbox Hunt is a directory that rates and compares 103 agent sandboxes, dev boxes, browser sandboxes, GPU sandboxes and CI runners in 6 categories. It is aimed at people choosing an environment for AI agents and at developers.

Read more →

The site lists monthly and per-unit prices, with each price linked to the vendor page it came from, and offers tools including a cost calculator, a provider explorer, a workload picker, a price-change log and public benchmarks. The homepage states that facts were checked on 2026-11-20, that vendors do not pay to be listed, and that user reviews are shown next to each provider without changing its rank.

3 prompts, 14 points

For Claude Code, Cursor or Codex. The score moves after the next scan.

+10score from 86 to 96

Serve Markdown when asked for it

None of the 4 pages read pass. Asking the homepage for markdown still returns text/html.

Read prompt

+2.5score from 96 to 99

Declare AI usage preferences

No usage declaration found in robots.txt or the final successful homepage response header.

Read prompt

Pro

11 more prompts in Pro

Pro shows a prompt for every fix and drafts your llms.txt and robots.txt. It never changes the score.

$9 once, per listingSee Pro

Deployed your fixes? Rescan to update your score →

Select a check to see what we found and how it is graded.

Readable base

50 / 50

Passes.

3.3 of 3.3 points.

robots.txt is valid, with 2 user-agent groups.

Passes.

8.3 of 8.3 points.

Sitemap declared in robots.txt, listing at least 200 URLs.

Passes.

8.3 of 8.3 points.

3 of 4 pages read pass. The page at /categories publishes no structured data at all: no JSON-LD, no microdata, no RDFa.

Passes.

10 of 10 points.

All 4 pages read pass. The homepage marks its content root, its heading outline and its landmarks.

Passes.

8.3 of 8.3 points.

12 of 12 assessed homepage navigation links expose usable destinations.

Passes.

4.2 of 4.2 points.

190 of 190 assessed homepage links and buttons have a nonempty accessible name.

Passes.

2.5 of 2.5 points.

19 of 19 assessed homepage form fields meet the static naming and field-semantics checks.

Passes.

2.5 of 2.5 points.

228 of 228 assessed homepage controls and role declarations meet the static role, state and relationship checks.

Passes.

1.7 of 1.7 points.

All 4 pages read pass. The homepage declares itself as its canonical URL.

Agent layer

36.3 / 50

Passes.

11.3 of 11.3 points.

/llms.txt is well formed: 201 links across 10 sections.

Passes.

7.5 of 7.5 points.

/llms.txt is descriptive: a summary plus descriptions on 100% of links.

Passes.

12.5 of 12.5 points.

/llms-full.txt serves the site's content as markdown (at least 64 KB).

Fails.

0 of 10 points.

None of the 4 pages read pass. Asking the homepage for markdown still returns text/html.

Passes.

5 of 5 points.

States a position on 13 AI crawlers, across 3 purposes (search, user-fetch, training).

Fails.

0 of 2.5 points.

No usage declaration found in robots.txt or the final successful homepage response header.

Penalties

− 0

Passes.

Penalty: 0 of 15 points.

Our crawler reaches the page without being challenged.

Passes.

Penalty: 0 of 20 points.

Nothing on the homepage tells a crawler to skip it or to withhold its snippet.

Passes.

Penalty: 0 of 25 points.

The captured homepage HTML contains 1077 content words; completeness is not assessed.

Passes.

Penalty: 0 of 25 points.

robots.txt allows every known search and user-fetch crawler to reach the homepage.

Passes.

Penalty: 0 of 10 points.

The homepage is served over HTTPS and returns HTTP 200.

Passes.

Penalty: 0 of 3 points.

The homepage provides both a non-empty title and meta description.

Passes.

Penalty: 0 of 3 points.

The homepage is reached in 0 redirects.

Passes.

Penalty: 0 of 3 points.

The homepage reached a plain crawler in 237 ms.

Agent capabilities

0 of 11 · no points

Each one found adds +1 to the badge.

Not applicable.

Adds +1 to the badge when found.

No API catalog published.

Not applicable.

Adds +1 to the badge when found.

No /auth.md published.

Not applicable.

Adds +1 to the badge when found.

No AI Catalog published, so no MCP server card can be discovered.

Not applicable.

Adds +1 to the badge when found.

No A2A Agent Card at /.well-known/agent-card.json, and none listed in an AI Catalog.

Not applicable.

Adds +1 to the badge when found.

No usable Agent Skills index was found at either well-known path or in the AI Catalog.

Not applicable.

Adds +1 to the badge when found.

No WebMCP declarations were found in the collected HTML or inline scripts. External scripts were not inspected.

Not applicable.

Adds +1 to the badge when found.

No Web Bot Auth key directory at /.well-known/http-message-signatures-directory.

Not applicable.

Adds +1 to the badge when found.

No HTTP 402 payment challenge on the homepage or robots.txt, and no manifest at /.well-known/x402.

Not applicable.

Adds +1 to the badge when found.

No ACP discovery declaration established at /.well-known/acp.json.

Not applicable.

Adds +1 to the badge when found.

No UCP discovery declaration established at /.well-known/ucp.

Not applicable.

Adds +1 to the badge when found.

No public AMP discovery declaration established. Private or hidden agents may not advertise one to our crawler.

Access & usage policy

Who can read this page, and for what purpose?

GoodForBotsBot received HTTP 200 via a direct request. No indexing restriction was observed in the supported homepage directives.

Sampled URL: https://aisandboxhunt.com/

Measured, our crawler
HTTP 200
GoodForBotsBot received HTTP 200 via a direct request.
Search and user-fetch crawlers refused
0 of 20
robots.txt refuses none of them.
Training crawlers refused
0
Refusing training would not change the score.

Crawlers and what robots.txt declares for them

Rules for the sampled URL, read the way RFC 9309 reads them. These are declarations, not access tests.

Crawlers and what robots.txt declares for them on the sampled URL
CrawlerPurposeDeclared accessScore effectRule that applies
Our crawler, measured
GoodForBotsBotGood for BotsSite diagnosticsFetchedHTTP 200, directNot scoredrobots.txt admitted our crawler
Search and AI answers
OAI-SearchBotOpenAIAI searchAllowedNoneUser-agent: oai-searchbot User-agent: chatgpt-user User-agent: gptbot User-agent: perplexitybot User-agent: perplexity-user User-agent: claudebot User-agent: claude-searchbot User-agent: claude-user User-agent: google-extended User-agent: applebot-extended User-agent: bingbot User-agent: duckassistbot User-agent: mistralai-user User-agent: meta-externalagent Allow: /
Claude-SearchBotAnthropicAI searchAllowedNoneUser-agent: oai-searchbot User-agent: chatgpt-user User-agent: gptbot User-agent: perplexitybot User-agent: perplexity-user User-agent: claudebot User-agent: claude-searchbot User-agent: claude-user User-agent: google-extended User-agent: applebot-extended User-agent: bingbot User-agent: duckassistbot User-agent: mistralai-user User-agent: meta-externalagent Allow: /
PerplexityBotPerplexityAI searchAllowedNoneUser-agent: oai-searchbot User-agent: chatgpt-user User-agent: gptbot User-agent: perplexitybot User-agent: perplexity-user User-agent: claudebot User-agent: claude-searchbot User-agent: claude-user User-agent: google-extended User-agent: applebot-extended User-agent: bingbot User-agent: duckassistbot User-agent: mistralai-user User-agent: meta-externalagent Allow: /
DuckAssistBotDuckDuckGoAI searchAllowedNoneUser-agent: oai-searchbot User-agent: chatgpt-user User-agent: gptbot User-agent: perplexitybot User-agent: perplexity-user User-agent: claudebot User-agent: claude-searchbot User-agent: claude-user User-agent: google-extended User-agent: applebot-extended User-agent: bingbot User-agent: duckassistbot User-agent: mistralai-user User-agent: meta-externalagent Allow: /
GooglebotGoogleSearchAllowedNot scoredNot named; User-agent: * applies
BingbotMicrosoftSearchAllowedNot scoredUser-agent: oai-searchbot User-agent: chatgpt-user User-agent: gptbot User-agent: perplexitybot User-agent: perplexity-user User-agent: claudebot User-agent: claude-searchbot User-agent: claude-user User-agent: google-extended User-agent: applebot-extended User-agent: bingbot User-agent: duckassistbot User-agent: mistralai-user User-agent: meta-externalagent Allow: /
, all allowed
Fetches a person asked for
ChatGPT-UserOpenAIUser fetchAllowedNoneUser-agent: oai-searchbot User-agent: chatgpt-user User-agent: gptbot User-agent: perplexitybot User-agent: perplexity-user User-agent: claudebot User-agent: claude-searchbot User-agent: claude-user User-agent: google-extended User-agent: applebot-extended User-agent: bingbot User-agent: duckassistbot User-agent: mistralai-user User-agent: meta-externalagent Allow: /
Claude-UserAnthropicUser fetchAllowedNoneUser-agent: oai-searchbot User-agent: chatgpt-user User-agent: gptbot User-agent: perplexitybot User-agent: perplexity-user User-agent: claudebot User-agent: claude-searchbot User-agent: claude-user User-agent: google-extended User-agent: applebot-extended User-agent: bingbot User-agent: duckassistbot User-agent: mistralai-user User-agent: meta-externalagent Allow: /
Perplexity-UserPerplexityUser fetchAllowedNoneUser-agent: oai-searchbot User-agent: chatgpt-user User-agent: gptbot User-agent: perplexitybot User-agent: perplexity-user User-agent: claudebot User-agent: claude-searchbot User-agent: claude-user User-agent: google-extended User-agent: applebot-extended User-agent: bingbot User-agent: duckassistbot User-agent: mistralai-user User-agent: meta-externalagent Allow: /
MistralAI-UserMistralUser fetchAllowedNoneUser-agent: oai-searchbot User-agent: chatgpt-user User-agent: gptbot User-agent: perplexitybot User-agent: perplexity-user User-agent: claudebot User-agent: claude-searchbot User-agent: claude-user User-agent: google-extended User-agent: applebot-extended User-agent: bingbot User-agent: duckassistbot User-agent: mistralai-user User-agent: meta-externalagent Allow: /
, all allowed
Model training, never scored
GPTBotOpenAIAI trainingAllowedNoneUser-agent: oai-searchbot User-agent: chatgpt-user User-agent: gptbot User-agent: perplexitybot User-agent: perplexity-user User-agent: claudebot User-agent: claude-searchbot User-agent: claude-user User-agent: google-extended User-agent: applebot-extended User-agent: bingbot User-agent: duckassistbot User-agent: mistralai-user User-agent: meta-externalagent Allow: /
ClaudeBotAnthropicAI trainingAllowedNoneUser-agent: oai-searchbot User-agent: chatgpt-user User-agent: gptbot User-agent: perplexitybot User-agent: perplexity-user User-agent: claudebot User-agent: claude-searchbot User-agent: claude-user User-agent: google-extended User-agent: applebot-extended User-agent: bingbot User-agent: duckassistbot User-agent: mistralai-user User-agent: meta-externalagent Allow: /
Applebot-ExtendedAppleAI trainingAllowedNoneUser-agent: oai-searchbot User-agent: chatgpt-user User-agent: gptbot User-agent: perplexitybot User-agent: perplexity-user User-agent: claudebot User-agent: claude-searchbot User-agent: claude-user User-agent: google-extended User-agent: applebot-extended User-agent: bingbot User-agent: duckassistbot User-agent: mistralai-user User-agent: meta-externalagent Allow: /
Google-ExtendedGoogleAI training, GroundingAllowedNoneUser-agent: oai-searchbot User-agent: chatgpt-user User-agent: gptbot User-agent: perplexitybot User-agent: perplexity-user User-agent: claudebot User-agent: claude-searchbot User-agent: claude-user User-agent: google-extended User-agent: applebot-extended User-agent: bingbot User-agent: duckassistbot User-agent: mistralai-user User-agent: meta-externalagent Allow: /
Meta-ExternalAgentMetaAI training, Product improvementAllowedNoneUser-agent: oai-searchbot User-agent: chatgpt-user User-agent: gptbot User-agent: perplexitybot User-agent: perplexity-user User-agent: claudebot User-agent: claude-searchbot User-agent: claude-user User-agent: google-extended User-agent: applebot-extended User-agent: bingbot User-agent: duckassistbot User-agent: mistralai-user User-agent: meta-externalagent Allow: /
, all allowed
Agents, extraction and others
, all allowed

The robots.txt groups behind this table

User-agent: oai-searchbot
User-agent: chatgpt-user
User-agent: gptbot
User-agent: perplexitybot
User-agent: perplexity-user
User-agent: claudebot
User-agent: claude-searchbot
User-agent: claude-user
User-agent: google-extended
User-agent: applebot-extended
User-agent: bingbot
User-agent: duckassistbot
User-agent: mistralai-user
User-agent: meta-externalagent
Allow: /

User-agent: *
Allow: /

https://aisandboxhunt.com/robots.txt

How to read this table

Each row says what robots.txt asks of that crawler. It does not show whether the crawler obeys, or how a firewall treats it. We measured only our own request.

Refusing search or user-fetch crawlers costs points under AI crawler access. Refusing training crawlers costs nothing.

Indexing directives, Content-Signal and AIPREF preferences are in the tabs below.

Observed access

GoodForBotsBot received HTTP 200 via a direct request.

Sources and scope: observed access
  • Declared allow · Scan admission

    • GoodForBotsBot/1.0 (+https://goodforbots.com/bot)

    The recorded robots admission decision allowed our crawler to proceed.

    GoodForBotsBot admission along the homepage request chain

    https://aisandboxhunt.com/

    robots.txt is present and valid

  • Observed · Direct request

    • GoodForBotsBot/1.0 (+https://goodforbots.com/bot)

    Our request received HTTP 200. A status alone does not identify a WAF.

    Our recorded direct transport attempt; intermediate attempt URLs are not retained

    https://aisandboxhunt.com

    HTTP 200

    Serves the homepage over HTTPS with HTTP 200

  • Observed · Final homepage response

    • GoodForBotsBot/1.0 (+https://goodforbots.com/bot)

    GoodForBotsBot received HTTP 200 via a direct request.

    homepage response

    https://aisandboxhunt.com/

    HTTP 200
    Transport: direct

    Serves the homepage over HTTPS with HTTP 200Serves our crawler without a challenge

Coverage and interpretation
  • Crawler coverage includes the registered identities and up to 50 user-agent entries from robots.txt. Source excerpts and detail groups are bounded; omissions are labelled.
  • Observed access describes GoodForBotsBot only. Other crawler entries describe declared rules, not tests of those operators' access.
  • Coverage is the sampled homepage response and collected robots.txt files. No indexing or citation is guaranteed. Usage preferences are declarations, not a legal determination of permission.
  • This explanation adds no points or penalties. Any score effects belong to the linked checks.
  • AIPREF and Content Signals keep their own definitions. AIPREF search can include processing used exclusively for search; training preferences are not a blanket ruling on every search process.

In its category

7th of 51 in Directories & Aggregators

  1. 1Brivoybrivoy.com
  2. 2IndieLaunchindielaunch.dev
  3. 7AI Sandbox Hunt · this reportaisandboxhunt.com

The prompts above would take AI Sandbox Hunt to 100, first in its category.

To the prompts ↑

Category average 63. The percentile appears once the catalogue holds a few hundred sites.

Scanned

Site profile

Login
Not established
API
Not established
Commerce
Not established

It decides which conditional checks apply. “Not established” means no proof in what we read, not proof of absence.

Scan details

Every scan is kept. Pro draws the history as a chart →

Scanned
20 Nov 2026
Rubric
0.9.0
Requests
23
Fetched
501.2 KB
Took
13.7 s
Homepage
237 ms · direct
Pages read
4
robots.txt
allowed
Which pages the scan read

The homepage and up to three pages from the sitemap and homepage links. Structured data, page structure, Markdown negotiation and typed links check each page read and take the median page; other checks read the homepage.

  • Homepagealways read
  • /aws-agentcore-code-interpreterarticle · linked from the homepage · from the sitemap · read
  • /agent37/pricingpricing · linked from the homepage · from the sitemap · read
  • /categoriescollection · linked from the homepage · from the sitemap · read

More like AI Sandbox Hunt:Directories & AggregatorsAI & Machine LearningCloud & HostingDevelopers

Same category

saascubes.com

Curated SaaS directory offering permanent do-follow backlinks for modern software products

Same category

brivoy.com

Community site where makers launch new products and early adopters discover them

Same category

submityourstartup.now

Free weekly launch directory where early-stage founders list startups and are ranked by votes

Also AI & Machine Learning

dolaai.pro

AI agent that edits Unreal Engine 5.7 Blueprints, C++ and levels in the open editor

Also Cloud & Hosting

volanea.com

Transactional email, campaigns, and automation API with AI agent support

Also AI & Machine Learning

contentspilot.com

AI co-pilot that plans, drafts and schedules Instagram carousels and posts in brand style