AI assistants and search decision

LarryBrain - Openclaw Marketplace

A single developer can build a usable self-hosted skill index and installer in ~36 hours, but the paid product's durable value (curated & reviewed marketplace, creator ecosystem, and security review processes) is expensive to reproduce, so DIY replaces only the discovery/installation surface, not the full managed marketplace.

Visit website
You pay

$29.99/mo

$360/yr

Read off the official pricing page.

You’d pay instead

$100one-off36 h to build

$0/mo3 h/mo upkeep

On cash alone, building overtakes the subscription at 1 seat.

Open-source builds that already do this

Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All LarryBrain - Openclaw Marketplace alternatives, with the arithmetic →

What a replacement has to do

  • Provide a tiny skill marketplace that lets an agent discover available skills, fetch a skill file (SKILL.md) to the agent, and permit running skills locally after verifying a subscription key.

What it still won’t have

  • Triple-layer review (automated scanning, manual code review, runtime sandboxing).
  • GitHub-verified authors and curated publishing pipeline.
  • Creator revenue-sharing tools and referral program automation.
  • Automatic weekly additions and integrated 'always up to date' updating of skills.

What remains hard

  • Product polish and ongoing maintenance
Read the build prompt

First-year cost

Keep paying

Paying is—cheaper in year one.

On cash alone, building overtakes the subscription at 1 seat.

Paid seatsseats

Money you would actually spend

Keep paying
—

Subscription price × seats × 12

Build it
—

AI build —APIs + hosting —

Time you would spend

—

—

What you would spend

What we assumed

The verdict above measures whether you could build it. This one is only about money.

Runnable build prompt

Not run yet
Build a minimal LarryBrain-compatible skill marketplace using Node.js (Express) + Postgres + S3-compatible storage, deployed on a single DigitalOcean droplet (or equivalent). In scope: (1) an authenticated REST API that serves a searchable skill index (POSTGRES), (2) static hosting for SKILL.md files and assets (S3), (3) a CLI endpoint / installer script that downloads a SKILL.md to a local agent directory, (4) Stripe-based subscription check middleware for one paid plan, (5) a small React web UI to browse skills and generate API keys. Out of scope: automated runtime sandboxing, manual code review workflows, creator payout automation, and multi-tenant enterprise features. Deliverables must include error handling, input validation, unit and HTTP integration tests, Dockerfiles for service and Postgres, Terraform or Docker Compose for deployment, and README with install/run steps.
How we checked5 sources · 2/3 runs agreed · evidence score 63

How the score was reached

  • Partly verdict base52
  • An open-source build was found+5
  • 5 cited sources+3
  • Price verified on pricing page+3
  • Evidence score63

The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.

How scoring works →

Cited sources · 5

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

✓ Price read off the page! 2 of 3 runs agreed; the verdict is the majority✓ Citations limited to fetched pages! 1 moat recorded