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
CA
CX
CX
Back to the catalogue

coder

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

Listings

CXagentDeveloper tools
1 findingStatic scanned
Has its own agent loop with Plan and Exec modes, works with several model providers including Ollama and OpenRouter, and shows git divergence, costs and token use in one interface. Downloads are for macOS and Linux.

Coder Xum

coder
Free

Runs many coding agents at once in isolated local, worktree or SSH workspaces.

176.3k installs/moAGPL-3.0-only
CAagentDeveloper tools
2 findingsStatic scanned
Evals are written in Markdown or TypeScript, model traffic is captured through a shared proxy, and each run's workspace artifacts are graded offline. Agent CLIs are separate dependencies and live runs incur model-provider charges.

Coder Aegis

coder
Free

Runs repeatable A/B experiments that compare skills, prompts, models and harnesses for coding agents.

2.5k installs/moApache-2.0

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.