LaunchRepo.

Works with

Launch your SaaS on directories with a browser agent

Operator-style browser agents already do the clicking. LaunchRepo gives them what they lack: a playbook per directory, your product facts in one file and a tracker for what actually happened.

A browser agent is built to fill in forms, so the directory grind looks like its natural job. What it usually lacks is context: which fields a platform rejects, what counts as “live” there, what your product may and may not claim, and a record of what it did last time. LaunchRepo provides exactly that as files. The catch — and this page is honest about it — is that a browser agent has to be able to read those files and work in a browser where you, not the vendor, are signed in.

What a browser agent needs

Access to the repository files
The agent must read the playbook for a platform, product.json and identity.json. A coding agent with a browser tool reads them directly; a pure hosted browser agent needs you to hand it the relevant playbook and product facts per platform.
A browser you are signed in to
Submissions happen with your accounts. A browser agent that runs in its own remote browser is not signed in as you and cannot read your mailbox for verification codes; the repository’s guide assumes a Chrome you can see.
A way to record outcomes
record.py and the local dashboard are Python scripts on your machine. If the browser agent cannot run them, you record each outcome yourself in the dashboard after the run.
The runbook’s stop conditions
Duplicate search first, identity check per platform, no purchases, stop on CAPTCHA or ambiguity. These are instructions the agent must actually follow, not features it ships with.

Connecting a browser agent to your Chrome

BROWSER-SETUP.md is written for agents that attach to a Chrome you supervise. If your browser agent is a coding agent with a browser tool, the guide applies as-is: Chrome DevTools MCP with auto-connect on your everyday Chrome (144 or newer), or a dedicated Chrome profile with a local debugging port, one long-lived connection per batch.

If your browser agent brings its own browser, the guide’s smoke check still tells you whether it is usable: can it open a public directory homepage and read the heading, can it sign in to a target directory with your identity, can it reach your mailbox for the verification email? If the answer to the last two is no, plan for those steps to be yours.

In either case: close unrelated sensitive tabs, use only the product’s permitted sites, never export cookies or a browser profile, and treat a completed tool call as nothing more than a tool call — read the page back to see whether it saved.

The start prompt

The public start prompt from START.md, unchanged. It assumes an agent that can run Python in the cloned folder — a coding agent with a browser tool, typically. With a pure hosted browser agent, run the “doing it yourself” commands from START.md in your terminal instead and use the dashboard to copy per-platform prompts to the agent.

START.md — paste as-is, in English
Read AGENTS.md, then follow "Start the dashboard for the owner". Create my private
workspace if I do not have one yet, start the dashboard, and give me the link.

The playbooks and instructions are English Markdown, which is what coding agents handle best. Your product copy can be in any language a directory accepts; the agent answers you in your language.

Either way the workspace, product.json, authorizations.json and submissions.csv end up as files on your machine, and the dashboard shows what is live, pending, scheduled or waiting on you.

What a run looks like

The illustration below is the home page’s: one batch, each platform ending in the state that was actually observed. With a browser agent the states may be entered by you after the run; either way they come from the tracker, not from this page.

What still needs you

LaunchRepo is deliberately not a background service. These moments stop the run and are recorded as human handoffs; the agent never works around them:

CAPTCHAs and bot checks
Whatever the agent, the challenge is yours to solve in the intended window. The tracker records prepared_needs_human; there are no stealth or evasion steps in any playbook.
2FA and verification codes
Most directories confirm by email. If the browser agent cannot read your mailbox, the code and the confirmation click are a human handoff — recorded as such, never as automated access.
Paid upsells
Paid-only routes are recorded as deferred_paid. A browser agent must be told not to buy; the playbooks say it on every platform, and the decision stays yours.
Recording and confirming
If the agent cannot run record.py, you enter the outcome in the local dashboard. “Live” always needs a public URL and your attestation.

No benchmark, no ranking: we claim compatibility for browser agents because it meets the two requirements above, not because we measured it against other agents.

Questions

Which browser agents are compatible?

Any agent that can read the repository files and work in a browser signed in as you — the same two requirements as for coding agents. We do not test or endorse individual products and publish no benchmark.

Can a hosted browser agent do the whole run?

Usually not on its own: it is not signed in as you, cannot read your mailbox and cannot run record.py. It can fill in forms from a playbook and product facts you paste; the rest is handed to you.

Is a browser agent better than Claude Code, Codex or Cursor for this?

We make no such claim in either direction. A coding agent with a browser tool covers files, browser and scripts in one place; a browser agent may need you for the file and record steps.

Does the tracker work without an agent at all?

Yes. record.py, submissions.csv and the dashboard are useful for a fully manual run too: the same eleven states, the same follow-up dates, the same honesty about what is live.

What does the licence cover?

Unlimited products you own and operate, unlimited agents of any kind, one GitHub account for repository access. Agent usage is billed by whoever provides the agent.

One payment, every product, any agent

The launch price is €99.98, once. It rises 20 % after every 20 sales; the pricing page shows the live price, what is in the repository and the licence in short.

See pricing