Independent technical audit

agentsphere.run

Overall AI readiness score

A combined result across all audit signals.

Average

AI readiness audit: 7/21/2026Public technical data

Overall AI readiness assessment

How ready agentsphere.run is for AI systems

58/100

LLMs.txt for AgentSphere was independently audited by llmsmap. agentsphere.run currently scores 58/100 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 2,263 tokens. An expanded llms-full.txt is also available with 27,369 tokens, giving agents more direct context. No separate ai.txt policy was detected; it is optional, but can clarify training, retrieval, and attribution preferences.

robots.txt is available. 6 of 11 tracked AI bots are not blocked, while 5 receive a prohibition. Declared sitemaps: 0. No Schema.org type was detected on the homepage. 0 OpenGraph tags were found and markup completeness is 0%, leaving more entity interpretation to crawlers.

The mobile Lighthouse profile adds Performance 83/100, Accessibility 95/100, Best Practices 92/100, 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
Strong Google agentic signals

Priority improvements

1Review the 5 explicit AI-bot blocks and keep only intentional restrictions.
2Declare the current sitemap.xml in robots.txt.
3Add JSON-LD for the organisation, website, and core entities.
4Complete OpenGraph and canonical homepage metadata.

llms.txt tokens2,263

llms-full.txt tokens27,369

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

Performance

Accessibility

Best Practices

100

Technical SEO

100

Agentic Browsing

What these results mean

Mobile performance is 83/100, with the largest visible content block appearing in 3.5 s and the browser main thread blocked for 200 ms. Layout shift was 0. 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 95/100, Best Practices 92/100, 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.

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.

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.

Reduce network delay

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

FCP2.5 s

First content

LCP3.5 s

Main content

CLS0

Layout stability

TBT200 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.

7/21/2026Lighthouse 13.4.0Mobile profile

AI readiness checks

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

llms.txt

File found and accessible

https://www.agentsphere.run/llms.txt

llms-full.txt

Full version is available

https://www.agentsphere.run/llms-full.txt

ai.txt

ai.txt file was not found

robots.txt

File found

https://agentsphere.run/robots.txt

Sitemap in robots.txt

Sitemap is not declared in robots.txt

Schema.org (JSON-LD)

Schema.org markup was not found on the homepage

OpenGraph0%

OpenGraph tags were not found on the homepage

AI bot access

Based on robots.txt analysis

GPTBotBlocked

OAI-SearchBotNot mentioned

ChatGPT-UserNot mentioned

Google-ExtendedBlocked

ClaudeBotBlocked

Claude-SearchBotNot mentioned

Claude-UserNot mentioned

BytespiderBlocked

CCBotBlocked

PerplexityBotNot mentioned

Perplexity-UserNot mentioned

# LLMs.txt for AgentSphere
# Specification: https://llmstxt.org
# Contact: contact@agentsphere.run
# Website: https://www.agentsphere.run

> AgentSphere is an agent-native cloud sandbox for secure code execution, sandbox environments, and developer workflows. It helps teams rapidly prototype, test, and run applications with integrated AI/LLM support.

## Overview
- [AgentSphere Home](https://www.agentsphere.run): The main homepage for AgentSphere, providing an overview of the platform, key features, and use cases for developers and AI engineers.

## Product Features
- [Gallery](https://www.agentsphere.run/gallery): A showcase of community-built projects and applications. Fork existing projects, find inspiration, and share your own creations.
- [Playground](https://www.agentsphere.run/playground): An interactive, browser-based environment to instantly test AgentSphere's capabilities without any local setup or API keys.
- [Sign Up](https://www.agentsphere.run/signup): The registration page for creating a new AgentSphere account.
- [Budget Management](https://www.agentsphere.run/budget): Manage your team's spending on sandbox usage. Set budgets, receive alerts, and control costs for your AI applications.
- [Templates](https://www.agentsphere.run/template): A library of pre-configured sandbox environments (e.g., Node.js, Python with Playwright) to accelerate your development workflow.
- [Usage Tracking](https://www.agentsphere.run/usage): Monitor your real-time and historical sandbox usage, including vCPU hours, RAM hours, and overall costs.
- [API Key Management](https://www.agentsphere.run/apikey): Generate, manage, and revoke your API keys for securely authenticating with the AgentSphere platform.
- [Sandbox Management](https://www.agentsphere.run/sandbox): The main dashboard to view, manage, and interact with your active sandbox instances.
- [Billing](https://www.agentsphere.run/billing): View your current plan, manage payment methods, and access your invoice history.
- [Team Management](https://www.agentsphere.run/team): Invite and manage team members, set roles, and collaborate on projects within your organization.
- [User Account](https://www.agentsphere.run/user): Manage your personal account settings, profile information, and preferences.

## Support & Documentation
- [Pricing](https://www.agentsphere.run/pricing): Detailed information about AgentSphere's pricing plans, including free and pro tiers, based on usage.
- [Documentation](https://www.agentsphere.run/docs): The official platform documentation, including quick starts, SDK guides, tutorials, and API references.
- [Quick Start](https://www.agentsphere.run/docs/quick-start): Get started with AgentSphere by running your first secure cloud sandbox.
- [Sandbox Lifecycle](https://www.agentsphere.run/docs/sandbox/lifecycle): Understand and manage the lifecycle of your AgentSphere sandboxes. 
- [Sandbox Metadata](https://www.agentsphere.run/docs/sandbox/metadata): Learn how to use metadata to attach custom key-value data to your AgentSphere sandboxes.
- [Sandbox Environment Variables](https://www.agentsphere.run/docs/sandbox/environment-variables): A guide to setting and using environment variables within an AgentSphere sandbox.
- [List Sandbox](https://www.agentsphere.run/docs/sandbox/list): Discover how to list and filter your active AgentSphere sandboxes.
- [Connect Sandbox](https://www.agentsphere.run/docs/sandbox/connect-sandbox): Learn how to reconnect to and reuse an active AgentSphere sandbox instance. 
- [Pause/Resume Sandbox](https://www.agentsphere.run/docs/sandbox/resume-pause): Learn how to pause and resume an AgentSphere Sandbox to persist its complete memory and filesystem state, including running processes and variables.
- [Internet Access](https://www.agentsphere.run/docs/sandbox/internet-access): Learn how sandboxes have full internet access and can be exposed via a public URL.
- [Sandbox Commands](https://www.agentsphere.run/docs/sandbox/commands): This guide covers how to run commands, stream stdout and stderr in real-time, and manage long-running background processes using the SDK. 
- [Connect to Bucket](https://www.agentsphere.run/docs/sandbox/connect-bucket): Learn how to mount and interact with external object storage buckets (e.g., AWS S3) from inside a sandbox.
- [Rate Limits](https://www.agentsphere.run/docs/sandbox/rate-limits): Understand the API rate limits for sandbox creation, command execution, and file operations.
- [Sandbox Metrics](https://www.agentsphere.run/docs/sandbox/metrics): Learn how to collect runtime metrics (CPU, memory, network) from active sandboxes for monitoring and debugging.
- [Customize Template](https://www.agentsphere.run/docs/template/customize-template): A guide to creating and extending your own templates to accelerate sandbox setup.
- [Customize CPU and RAM](https://www.agentsphere.run/docs/template/customize-cpu-ram): Learn how to configure custom CPU and memory resources for your sandboxes.
- [Start Command](https://www.agentsphere.run/docs/template/start-cmd): Define the startup command for your sandbox so it automatically runs the right process when launched.
- [Ready Command](https://www.agentsphere.run/docs/template/ready-cmd): Configure a ready-check command to determine when a sandbox has fully started and is ready to accept traffic.
- [Get File/Directory Information](https://www.agentsphere.run/docs/filesystem/info): Learn how to use AgentSphere Sandbox files.getInfo() / files.get_info() methods to retrieve detailed information about files and directories, including name, type, path, permissions, size, and more.
- [Read/Write Files](https://www.agentsphere.run/docs/filesystem/read-write): Learn how to perform file I/O operations in an AgentSphere sandbox using the Python and JavaScript/TypeScript SDKs.
- [Watch Directory](https://www.agentsphere.run/docs/filesystem/watch): Discover how to monitor a directory for filesystem events within an AgentSphere sandbox.
- [Upload Files](https://www.agentsphere.run/docs/filesystem/upload): Learn to use the SDK for direct uploads and how to generate secure, pre-signed URLs to authorize uploads from a browser.
- [Download Files](https://www.agentsphere.run/docs/filesystem/download): Learn to use the SDK for direct downloads and how to generate secure, pre-signed URLs to authorize downloads from a browser.
- [MCP Server](https://www.agentsphere.run/docs/mcp-server): Explore AgentSphere's official Model Context Protocol (MCP) server, enabling frontier LLMs to safely interact with external tools and data. Learn how to configure AgentSphere as an MCP server for clients like Cursor, Claude Code, and Raycast, and discover examples like generating live data charts within a secure sandbox environment.
- [Desktop](https://www.agentsphere.run/docs/desktop): Discover AgentSphere Desktop, a secure virtual desktop designed for AI agents performing 'Computer Use' tasks. This guide shows you how to programmatically control a complete, isolated desktop environment to launch GUI applications, all via our Python and JavaScript SDKs.
- [Release Notes](https://www.agentsphere.run/docs/release-notes): Stay updated with the latest features and improvements in AgentSphere.
- [CLI Setup](https://www.agentsphere.run/docs/cli/cli-setup): Learn how to install and configure the AgentSphere Command-Line Interface (CLI).
- [CLI Operations](https://www.agentsphere.run/docs/cli/cli-operations): A complete guide to managing your AgentSphere cloud sandboxes via the command line. Learn the CLI commands to list, filter, and destroy sandboxes.
- [Common Issues](https://www.agentsphere.run/docs/troubleshooting/common-error): A troubleshooting guide to address frequently encountered errors when using AgentSphere, including authentication failures, network issues, and sandbox access errors.  
- [Startup Issues](https://www.agentsphere.run/docs/troubleshooting/startup-issue): Learn how to diagnose and resolve problems when initializing or starting an AgentSphere sandbox, such as timeout errors, missing dependencies, or misconfigured runtime environments.  
- [Template-related Issues](https://www.agentsphere.run/docs/troubleshooting/template-error): Understand common issues when creating or customizing sandbox templates, including reserved ports, conflicting services, and invalid configuration files.  
- [Glossary](https://www.agentsphere.run/docs/glossary): A comprehensive glossary of AgentSphere terminology, covering core concepts like sandboxes, templates, MCP, environment variables, and lifecycle management.  

## Company & Legal
- [Terms of Service](https://www.agentsphere.run/terms): The platform's terms of service and other legal agreements.
- [Contact](https://www.agentsphere.run/contact): The primary page for getting in touch with the AgentSphere support and sales teams.

## Blog
- [AgentSphere Blog](https://www.agentsphere.run/blog): The company's official blog, featuring technical guides, product updates, and insights for developers and AI engineers.

Share or continue the analysis

Share this audit

Discuss with AI

Added 7/19/2026