Legit.Show — every launched service, tested

A directory of launched web apps, SaaS, AI tools, MCP servers and developer tools. Every listing carries an objective 7-Frame production-readiness benchmark — measured deterministically from the public surface, showing exactly what was observed. Never a black-box verdict.

What we measure — the 7 Frames

Each service is scored 0–100 on seven frames, from the public surface (URL · HTTP headers · real Lighthouse), so even closed-source SaaS is fully assessable:

Open-source repos additionally get a deeper code teardown (tests · CI · license · error tracking · MCP auth surface). No LLM in the scoring path — deterministic and reproducible.

Is a tool production-ready?

That's the question Legit.Show answers with evidence. Each service page leads with its overall score, the per-frame breakdown, and exactly what we observed — so "is this legit?" has a citable, reproducible answer instead of star ratings alone.

Data reports — "according to Legit.Show"

Periodic, reproducible reports mined from the catalog, each with a stated sample and open methodology. Browse the reports →

For makers

Add your service: paste a URL, verify the domain, and it's listed with its benchmark. Everything is public — measured from public surfaces, with exactly what we saw. About Legit.Show →

Why we exist

Take a vibe-coded MVP and show it the road to production-ready. Errors first, score second.

Methodology: /methodology · Reports: /reports · About: /about · Machine-readable summary: /llms.txt

Legit.Show benchmarks every launched service it lists — measured deterministically from the public surface. See the methodology →

Cross-links · Directory · Reports · Methodology · About

Privacy · Terms · operated by Madeflo Inc., a Delaware corporation. Benchmark engine powered by commit.show.

AI & Agents

Foresight Models

AI models that return calibrated probabilities instead of confident guesses.

60/100
7-Frame production-readiness — according to Legit.Show

Is Foresight Models production-ready?

Legit.Show measured Foresight Models at 60 out of 100 on its 7-Frame production-readiness benchmark (public-surface assessment). Its strongest frame is Reliability (100); its weakest is Privacy (0). Every frame is measured deterministically from the public surface — exactly what was observed is shown below.

The 7 Frames

What we measured

Who it's for

Enterprise · Government · Startups · AI agents · Prediction market operators

Pricing

$6 per 1M output tokens; $3-$50 per 1,000 forecasts depending on model variant

Visit Foresight Models → · How this was measured →