An open-source Semrush alternative for teams that ship from a repo
Semrush is a suite you log in to and operate. Tin is a set of open-source SEO workflows your coding agent runs: audit, keyword research, a content plan, drafts, and fixes that arrive as pull requests.
codex mcp add tin --url https://app.tin.computer/mcpWhat Tin does in place of Semrush
Semrush is a broad SEO and marketing suite built around large keyword and backlink databases, with dashboards for research, tracking and reporting. If you need that breadth, it is hard to beat.
| the job | how Tin does it | workflow |
|---|---|---|
| Site audit | Audits up to 100 pages for technical SEO and AI visibility, with evidence. | organic.audit → |
| Keyword and competitor research | Researches buyer searches, competitor keywords and live results inside a cost cap. | organic.keyword_plan → |
| Content planning | Turns the audit and keywords into an editable roadmap. | content.plan → |
| Fixing what the audit finds | Proposes verified pull requests for missing titles and descriptions. | organic.technical_fix → |
What Tin does not replace
Tin is not a clone. Here is where each one fits.
Semrush still does this better
- A keyword and backlink database you browse by hand. Tin fetches the data a job needs and does not host an index.
- Backlink analysis and link monitoring.
- Daily rank tracking across thousands of keywords.
Choose Tin when
You are a founder or small team, your site lives in a repository, and you want the work done and reviewed, not another dashboard to check.
Stay with Semrush when
You are an SEO professional or agency that lives in keyword and backlink data every day.
What every workflow here comes 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
Tin connects to Claude Code, Codex or Cursor over MCP. That agent has your repository open and knows your product, customers and voice, so it fills the inputs and reviews the output. You never brief a new tool from zero.
All workflows →The workflows behind this page
Each one is a folder in the repo. Open a page for its steps, inputs and output.
Questions
Is Tin a free Semrush alternative?
Tin is open source under Apache 2.0 and you can self-host it. You pay your own model and data providers, and keyword research runs inside a cost ceiling you set. The hosted app uses credits.
Does Tin have a keyword database like Semrush?
No. It fetches the keyword and search result data a run needs and saves the researched inventory to your project.
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.