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
  • Privacy
  • Terms

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.

Visit counting is on.

AI agentsAppsMCP serversTemplatesWantedCommunityOur library
Sign inSell
Catalogue/Agents/Agency Os

Agency Os

dvg-os · Agent

Adds a marketing operating system to Claude Code, with named agents arranged in eight departments and a strict lead pipeline numbered 0 to 5 where no stage is skipped. Its commands enrich a lead, write outreach, send it through Brevo, monitor replies and launch Meta ad campaigns. It runs on your machine with no backend of its own, uses your own keys for HubSpot and Brevo, and suits an agency that already works in Claude Code. It is in active engineering, with internal validation still to come.

Written by ooruby from the README of @dvg-os/agency-os 0.1.5.

Not claimed by its maker. Is this yours? Prove it and answer the findings

Why it's useful

Lead research, outreach and ad launches run from your own Claude Code with your own keys and data, and nothing sends mail or spends money until you allow it.

What you could do with it

  1. 1Run the enrich command on a HubSpot lead to get a company analysis, a brand match and decision-maker details.
  2. 2Have the agents draft four outreach versions in your brand voice, then send through Brevo once you enable sending.
  3. 3Create a Meta ad campaign that starts paused, so you decide when to switch it on.

Written from its documentation: what it says it can do, not what our checks found.

AOagentSales & CRM

Maintenance

Not measured

No release date is on record for this package yet. The nightly publisher check records one as it reaches each npm package, about once every ten nights.

Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured

Not yet tested
Command execution is bounded
inventory
node child_process (bin/agency-os.js:27)
An inventory of where the code starts another program, not a verdict on this row: whether each one runs a fixed program or whatever it is handed takes a reading by hand.

Published because it was found. A finding is information about where the limits are, not a verdict that the software is unsafe.

What this does not cover

  • ·Everything. Treat it as you would software from anywhere else.

Receipt history: every signed receipt for every version of this listing, and what changed between them.

In its maker's words

AI marketing operating system distributed as a Claude Code plugin. BYOK multi-tenant architecture with 37 named agents, 8 departments, strict 0→5 lead pipeline, Cerberus + Hemingway quality gates, Minerva-backed RAG.

Compare with

  • Cargo AI CLIside by side
  • Peoplebladeside by side
  • Marketing Mindsetside by side
Compare all 4

How far this has been checked

Static scanned

What it establishes
Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
What it does not
How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
Exactly what was read
Version 0.1.5, the file with digest sha512-BtIDtr9Sp4AtJ6AThB5InK/riYTieZRKAvUveSkaaSPcmHFxhppY1YiSU+EmAzlLGYMQzLnqWhhY3DiFOcVagg==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
Authentication
Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
How the rungs work

Adding it

Run it with:

npx -y -p @dvg-os/agency-os@0.1.5 agency-os

Pinned to 0.1.5, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.

Where this came from

Registry
npm
Package
@dvg-os/agency-os
Version read
0.1.5
Resolved
2026-10-10
Open the source(opens in a new tab)

No build provenance published. The repository above is the one the publisher declared, and nothing links it to the package you would install. That is not a mark against this listing, since most packages are published this way, but it is a check nobody can run.

The badge, if this is your listing

It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.

[![ooruby: static scanned](https://ooruby.com/api/badge/dvg-os-agency-os)](https://ooruby.com/market/dvg-os-agency-os)

About this listing

Kind
Agent
Category
Sales & CRM
Pricing
Free
Sandbox
No
Hosted
No
Updated
2026-10-09
Price
Free
Get it freeVisit maker
Rating
no reviews yet
0 want this so far
Sign in to vote

Sign in to watch this listing and hear when its version, rung or findings change.

Similar agents

All agents
CAagentSales & CRM
1 findingStatic scanned
Commands cover workflows, storage, connectors, billing, segments, AI agents and hosting, and every command prints JSON. A separate set of seventeen skills teaches AI coding agents to use it.

Cargo AI CLI

cargo-ai
Free

Builds lead lists, enriches contacts and runs plays in a Cargo workspace from your terminal.

18.7k installs/moUNLICENSED
PEagentSales & CRM
Clean scanStatic scanned
A personal CRM with no app to open: your agent runs its commands against a private database. Free command line for macOS and Linux that runs on Bun, with no account needed.

Peopleblade

hraness
Free

Builds one private contact book on your computer from your apps and exports, for your agent to search.

5.1k installs/moMIT
MMagentSales & CRM
Clean scanStatic scanned
Comes as an installable agent skill and a command line. Commands print a marketing engineer job description, judge whether it is time to write a playbook, tag links with UTM parameters and price a readable test.

Marketing Mindset

axelfreeman
Free

Gives your agent a marketer's rules for tests: sample-size floors, kill rules and verdicts on results.

3.8k installs/moMIT

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.