TinTinWorkflows
GitHubSign in

The whole organic loop as one open-source workflow

Tin audits your website, researches buyer searches, saves an editable content plan and drafts its next article for review. With GitHub connected, the approved article becomes an unmerged PR. Each week it drafts the next planned article and refreshes one existing page, and optionally it proposes a technical fix.

Try in browser →
codex mcp add tin --url https://app.tin.computer/mcp
Organic traffic system
organic.traffic_system
outputAudit, keyword inventory, content plan and a reviewed draft
guardrailNever merges, publishes or sends outreach.
needsA public site. GitHub is optional and only used for delivery and fixes.
required inputssite_url, market, buyer_context, start_date
optional inputsduration, keyword_max_cost_usd, technical_fix, content_delivery, expected_repository, repository_serves_site, article_weekdays, article_local_time
sourcegithub.com/tin-computer/tin →

What the workflow does.The same steps, every run.

A Tin workflow is a repeatable job: declared inputs, a bounded run and a defined output.

  1. 01Audits the site and researches keywords inside the cost ceiling you set.
  2. 02Saves an editable content plan for the duration you choose.
  3. 03Drafts the next article and waits for your review.
  4. 04Delivers the approved article as an unmerged PR, or keeps the Markdown in Tin.
  5. 05Then drafts the next planned article each week, one review at a time, and refreshes one existing page.
ask your agent

Run Tin's organic traffic system for our site. Fill the buyer context from what you know about the product.

What every workflowcomes with.

Battle tested on real products

These are the workflows we run for real companies. Claw Messenger went from about $45 to $2,105 in monthly revenue in 124 days on them. Each one has declared inputs, bounded execution and tests, and anything public waits for your review.

See the case study →

Open source: read it, fork it, self-host it

Apache 2.0. Every workflow is a folder in the repository: the steps it runs, the data it reads and what it is allowed to do. Change it, or run the whole system on your own machine.

Open the repo →

Runs on the agent that already knows your product

This is the workflow where context compounds: one agent that knows the product fills every input, reviews every output and catches what a separate SEO tool never could.

All workflows →

Using something else for this?What it replaces, and what it does not.

Semrush alternativeSEOSurfer SEO alternativeContentJasper alternativeContent

Runs well with.Workflows that feed this one, or follow it.

SEO and AI visibility auditorganic.auditKeyword planorganic.keyword_planContent plancontent.planPlanned article draftscontent.generate

Questions.

Is this an autonomous SEO agent?

It is a bounded job with review points, not an agent left alone on your site. It never merges, publishes or sends anything.

Can I run the parts separately?

Yes. The audit, keyword plan, content plan, drafting and delivery workflows all run on their own.

Is Tin really open source?

Yes. Tin is licensed under Apache 2.0 and the source is at github.com/tin-computer/tin. You can read every workflow, change it, and self-host the whole system.

Which coding agents can run Tin workflows?

Any agent that speaks MCP, including Claude Code, Codex and Cursor. There is also an API, and the same projects run in the browser at app.tin.computer.

Why run marketing from a coding agent?

Because it already knows your product. It has the repository open, so it fills workflow inputs accurately, reviews output against what the product really does, and can act on the results in the same session.

Add Tin to your coding agent.It takes one command.

Try in browser →
codex mcp add tin --url https://app.tin.computer/mcp