Agent readiness tools, compared
“Agent ready” gets used for three different questions. Can an AI agent use your SDK or service? Can it read your website? Can it work inside your code repository? The tools below each answer one of them.
| Tool | What it checks | Cost |
|---|---|---|
| agentic-usability (Nutrient) | How well AI coding agents use your SDK: it writes programming challenges from your SDK’s source, has agents (Claude Code, Codex, Gemini CLI or your own) solve them in isolated sandboxes using only your public docs, and has an AI judge score the results | Open source |
| AX benchmark (Tech Stackups) | Gives a coding agent (Claude Code) the task of integrating a service from scratch, and scores discoverability, sign-up, onboarding, API design and SDKs from 1 to 4 | Free to read |
| metaend Grade | Scans a URL and grades its “agent readiness” from A to F: discovery files, content negotiation, A2A, ERC-8004 and payments, with a fix for each failure | Free |
| agent-ready | Scores how ready a code repository is for AI coding agents (Claude Code, Cursor, Copilot, Codex) | Open source |
| agent-readiness | Benchmarks how agent-ready a code repository is for AI coding agents | Open source |
Checked October 31, 2026 from each tool’s own page.
Can agents use your SDK or service?
agentic-usability (Nutrient)
- Checks
- How well AI coding agents use your SDK: it writes programming challenges from your SDK’s source, has agents (Claude Code, Codex, Gemini CLI or your own) solve them in isolated sandboxes using only your public docs, and has an AI judge score the results
- Cost
- Open source (Apache 2.0); published June 9, 2026
The closest to testing whether agents can integrate your product, but aimed at SDKs rather than a script tag or hosted service.
Source: www.nutrient.io/blog/agentic-usability-open-source-ai-sdk-testing/, checked October 31, 2026.
AX benchmark (Tech Stackups)
- Checks
- Gives a coding agent (Claude Code) the task of integrating a service from scratch, and scores discoverability, sign-up, onboarding, API design and SDKs from 1 to 4
- Cost
- A published benchmark of chosen services (email services first), not a tool you run; announced January 26, 2026
Useful as a scoring model even if your product isn’t in it.
Source: techstackups.com/guides/introducing-ax-benchmark-agent-experience/, checked October 31, 2026.
Can agents read your website?
metaend Grade
- Checks
- Scans a URL and grades its “agent readiness” from A to F: discovery files, content negotiation, A2A, ERC-8004 and payments, with a fix for each failure
- Cost
- Free to scan
Checks your website as agents read it, not whether an agent can install your product.
Source: www.producthunt.com/products/metaend-grade-agent-readiness-checker/reviews, checked October 31, 2026.
Can agents work in your repo?
agent-ready
- Checks
- Scores how ready a code repository is for AI coding agents (Claude Code, Cursor, Copilot, Codex)
- Cost
- Open source (MIT); version 0.1.0, June 4, 2026
About agents working inside your own repo, not installing your product into someone else’s.
Source: pypi.org/project/agent-ready-cli/, checked October 31, 2026.
agent-readiness
- Checks
- Benchmarks how agent-ready a code repository is for AI coding agents
- Cost
- Open source (MIT); version 4.1.0, June 1, 2026
Like agent-ready, it looks at your own repo.
Source: pypi.org/project/agent-readiness/, checked October 31, 2026.
What’s missing
None of these runs your actual install prompt in the AI builders people use (Lovable, v0, Cursor) and checks the result in a browser. Today that’s done by hand: see how to test it yourself.