What did Hlido score UXLoom?

UXLoom scored 71/100 (STEADY) in Hlido's independent, hands-on review.

How much does UXLoom cost?

Hlido recorded the pricing model as: Open source. Derived from evidence Hlido holds, not vendor-supplied; verify current prices on the vendor's pricing page.

Does any vendor pay Hlido for placement?

No. Hlido takes no money from the agents it rates — scoring weights stay private and the evidence behind every verdict is public.

UXLoom

Name: UXLoom review
Item: UXLoom
Rating: 71
Author: Hlido Editor

Frameworks & Eval · tested 2026-08-10 · re-test due 2026-11-10 · by the Hlido desk, not the vendor

In short: A design-time critic for AI-generated UI that checks state coverage deterministically — unusually honest about being a linter, not a generator.

6 PASS · 0 FAIL of 6 public-surface claims

Visit UXLoom → scorecard.json

Quick answer

UXLoom scores 71/100 (STEADY) on Hlido’s independent, hands-on test (reviewed 2026-08-10). STEADY (71) because the value proposition is specific and independently checkable, the checks described are deterministic rather than model-judgement, and the access path is completely open — MIT, npm, MCP registry, docs Pricing: Open source (free entry point documented).

Hlido Editor · 2026-08-10

UXLoom occupies a genuinely under-served slot: everyone is shipping UI generators, almost nobody is shipping the thing that audits their output. It takes a journey definition (an open format the project calls JourneyGraph) plus the screens a generator produced, models the flow as a state machine, and reports what is missing — unreachable screens, dead-end transitions, absent loading/empty/error/offline states, WCAG contrast failures, sub-44px touch targets, and label overflow under localization growth. The public surface is precise about what that means: five named checks, a worked coverage matrix showing 21/30 required states on a sample checkout flow, and an explicit framing of the findings as deterministic — same input, same report, diffable in CI. That framing is the strongest signal here. A tool that says 'zero opinions, all evidence' and then shows you the matrix is making a claim you can falsify, which is rarer in this category than it should be. The distribution posture is equally clean for agent use: MIT, on npm, listed in the official MCP registry, no sign-up and no mailing list gate on the docs. What we cannot assess from the public surface is the part that decides whether it works — how well the journey definition survives contact with a real generator's output, and whether the required-state model is right for flows more complex than checkout. The site shows the sample, not the corpus. At v0.14 the honest read is a well-specified early tool with a real thesis, not a proven one.

Why STEADY

STEADY (71) because the value proposition is specific and independently checkable, the checks described are deterministic rather than model-judgement, and the access path is completely open — MIT, npm, MCP registry, docs with no login. It is not VITAL because the evidence on the public surface is a single illustrative flow rather than results across real projects, the version (v0.14) is pre-1.0 with the API surface still moving, and nothing public establishes how the journey definition holds up on flows the authors did not design the example around.

Public-surface checklist

PASS Homepage loads (required)
PASS Primary value prop (required) — 'Your generator gave you 6 screens. UXLoom proves you're missing 9 states.'
PASS Cta present (required) — 'Star the repo' / 'uxloom on npm'
PASS Pricing or access (required) — Open source, MIT, no sign-up
PASS Evidence or demo (required) — Worked coverage matrix + sample CLI output on homepage
PASS Docs public — Docs linked in top nav, no login

What we saw

4 screenshots captured by the Hlido engine during the reviewed run (run-00d0c25444aa946d-uxloom-dev). Our own captures — not vendor marketing material.

UXLoom — run screenshot 1 (home.png) — home.png

UXLoom — run screenshot 2 (page__main.png) — page__main.png

UXLoom — run screenshot 3 (page__.png) — page__.png

UXLoom — run screenshot 4 (page_docs_html.png) — page_docs_html.png

What it does well

Names a real, specific gap — generators emit the happy path, nothing audits the missing states
Checks are deterministic and diffable, so findings are reviewable in CI rather than advisory
Publishes a worked coverage matrix (21/30 states) instead of only asserting the capability
Fully open access path: MIT, npm, official MCP registry, docs without sign-up
Explicitly positions as a critic layer over any generator rather than replacing one

What it fails at

Evidence is one illustrative checkout flow — no results across real or third-party projects
v0.14 pre-1.0: the JourneyGraph format and CLI surface are not stability-committed
Requires the user to author a journey definition; the cost of that step is not shown
No pricing or commercial-support story published (fine for OSS, unclear for adoption)
The required-state model is asserted, not justified — why these states, for which flows, is undocumented on the surface

Best for

Teams shipping UI from v0, Lovable, Figma Make or Claude who need a gate before implementation
Design-system owners wanting state coverage enforced mechanically rather than by review
CI pipelines that can consume a deterministic report and fail a build on it
Agent workflows that generate UI and need a machine-checkable critic in the loop

Not recommended for

Teams wanting UI generated rather than audited — this deliberately does not generate
Projects with no journey definition and no appetite to author one
Anyone needing production-stability guarantees today (pre-1.0, v0.14)
Accessibility programmes needing full WCAG audit coverage — this checks contrast and target size, not the standard

Pricing & access

ModelOpen source
Free entry pointYes — a free tier or open-source edition is documented
Pricing findable on the public surfacePASS Open source, MIT, no sign-up (tested 2026-08-10)

Derived from Hlido-held evidence only (engine checklist + editorial text); quotes are verbatim from the scorecard; not vendor-supplied; re-derived daily. Verify current prices on the vendor's pricing page. Last verified 2026-08-10.

Related agents

Agent relevance

CLI MCP Behavioral-testable

Agentic-Commerce Readiness 69/100 · INTEGRABLE

Independent readiness for agent delegation & transaction. How it’s scored · check live

CLI (npx uxloom check ./design) plus an MCP server listed in the official registry, so an agent can run the check and consume a structured report directly. The deterministic output is the property that makes it usable in an agent loop — a generating agent can call it, read the missing-state list, and iterate without a human arbitrating.

Agent-friendly score: 8/10

Evidence

Checks journey completeness, state coverage, WCAG contrast, touch targets and text expansion — source (2026-08-10) verified
Published on npm and the official MCP registry — source (2026-08-10) verified
MIT licensed, no sign-up and no mailing list required — source (2026-08-10) verified
Sample coverage matrix reports 21/30 required states (70%) — source (2026-08-10) verified
Version v0.14 (pre-1.0) — source (2026-08-10) verified

scorecard.json · transparency passport · registry · methodology

More: compare agents · best of · developer tools · incident registry

Verdict by Hlido Editor, our automated editorial system · Method: public-surface-tier-1+editorial-narrative-v2 · Methodology version 2026.05 · Next review due 2026-11-10

How this page was produced. The scores, claim verdicts and evidence come from automated hands-on testing of the product’s public surface. The written analysis is drafted by an AI system, and pages publish without a person reviewing each one. Hlido publishes this record and answers for it — tell us if anything here is wrong and we will correct it.

Embed this trust badge

Live, always-current independent score — free to embed on your site or README. No vendor pays for placement.

Markdown

[![Hlido trust score](https://hlido.eu/badge/uxloom-dev-uxloom.svg)](https://hlido.eu/check/?agent=uxloom-dev-uxloom)

HTML

<a href="https://hlido.eu/check/?agent=uxloom-dev-uxloom"><img src="https://hlido.eu/badge/uxloom-dev-uxloom.svg" alt="Hlido trust score"></a>