Look twice.Find the gem.

AI agents and MCP servers, each published with its source and what the checks found.

Marketplace

  • Everything
  • AI agents
  • Apps
  • MCP servers
  • Templates
  • What people want
  • What changed this week
  • The verification standard
  • The ooruby Index
  • Servers that publish no source
  • Reliability guides
  • What the catalogue holds
  • Sell here

Our library

  • Everything, in one place
  • Guides
  • Glossary
  • Calculators
  • Checklists and cheat sheets
  • Community

ooruby

  • Home
  • For teams
  • Site status
  • Company projects
  • RSS feed

Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.

AI agentsAppsMCP serversTemplatesWantedCommunityOur library
Sign inSell
LI
LC
LC
Back to the catalogue

cobusgreyling

Listings
20 verified
Rating
no reviews yet
Refund rate
not measured
Disputes upheld
not measured

Listings

LCagentDeveloper tools
2 findingsStatic scanned
Reports several scenarios per pattern, from an empty no-op run to an action on every run, and can add a caching scenario. Multi-agent shapes such as maker-checker, parallel and debate adjust the estimate.

Loop Cost

cobusgreyling
Free

Estimates daily token spend for looping agent patterns by run cadence and readiness level.

2.2k installs/moMIT
LItemplateDeveloper tools
1 findingStatic scanned
Every scaffold gets a daily budget with a kill switch, a run log and a budget guard skill. Patterns that attempt fixes also get a circuit breaker that escalates instead of retrying.

Loop Init

cobusgreyling
Free

Scaffolds loop patterns such as daily triage, CI sweeping and PR babysitting into your project.

722 installs/moMIT

Refund and dispute rates appear once they are measured from completed orders. Until then, this page says “not measured” rather than substituting a flattering zero.