
you pick the next step
It decides what to do next
The Leader looks at where each language stands and hands the work to the right specialist.
Coding agents wait for your next prompt. GrowthHarness researches your market, plans topics, and writes and reviews articles in every language you sell in. It keeps going while you build. You decide what gets published.
$npm run setup -- --local && npm run dev
Then walk away. It works the night shift.
Strategist · strategy v4 done for 3 languagesStrategy v4 done
3 ready for you
Approved 3
Each one passed independent review.
The team view is the real console with sample data. The night log is illustrative.
You already have a coding agent
Ask any coding agent for ten SEO articles and you will get ten articles. Growth needs a few hundred decisions after that, spread over months, and each one starts with you typing.
write 10 seo blog posts for our pricing page keywords
Done. I created 10 posts in /content/blog. Want me to publish them, translate them, or research more keywords?
You wanted AI to take marketing off your plate. Now you manage the AI that does your marketing.
How it works
A Growth Leader runs a team of specialists: strategist, researchers, topic editor, editor-in-chief, writers and an independent reviewer. They hand work to each other and report back to the Leader. Nobody waits for you to say what is next.

you pick the next step
The Leader looks at where each language stands and hands the work to the right specialist.

you carry the context
Each task keeps its full history from start to finish. If a run is interrupted, it resumes where it stopped.

you check the work
An independent Reviewer reads every draft against your site. Data it can't find stays marked unknown.

you translate everything
Research and topics run separately for each language you sell in. Articles go live on your domain under /en/, /pt/ or /de/.
Your part is one decision.Set the goal once. After that you only see finished articles that passed review, and you choose what goes live.
Under the hood
For an agent that runs for weeks, the prompt is the easy part. The work is in everything around it, and all of it is open source.
Specialists report to the Leader, never to each other. Writers and the Reviewer work inside the Editor-in-Chief’s team.
continuous runsA task keeps its identity and conversation for its whole life. Long histories are compacted; the original is kept.
durable stepsWork runs as durable workflow steps. Interrupted tasks resume, and external jobs are never submitted twice.
self-auditThe agent decides whether to keep going or finish. Usage is recorded, and it never forces a stop to wait for you.
hard rules in codeWorkspace isolation, approvals and quality checks are enforced in code. What to research and write is left to the agents.
bring your own modelOpenRouter, OpenAI, Anthropic or a custom endpoint. Planning, writing and review can each use a different model.
workers · d1 · r2 · durable objectsThe console, the agents and your published blog all run in one Worker you deploy. Sitemap and IndexNow included.
Before you install
$ git clone https://github.com/ahamoment-101/growth-harness.git $ cd growth-harness && npm ci $ npm run setup -- --local $ npm run dev # add a model key in .dev.vars, then give the Leader a goal