LaunchRepoBefore you buy
Git, Python 3.10+ on Windows, macOS or Linux, Chrome, Node.js for Chrome DevTools MCP and an agent with local-file and MCP browser access. Toolkit documentation is English. Check your browser integration on a harmless public page. This establishes basic access; it cannot certify every directory workflow.
Check your agent before you buy
LaunchRepo needs an agent that can read local files and work with Chrome. Already using an AI editor does not necessarily mean its browser connection is set up. You can check the basics without buying LaunchRepo. In a folder containing a harmless text file you created for this check, ask your agent:
Read the text file I created for this check and summarize its contents. Then use Chrome DevTools MCP to open https://example.com in Chrome. Tell me the page title and its main heading. Do not sign in, fill forms, send data or change any settings. If you cannot perform either action, tell me which capability is missing.
- Both actions worked
- Your agent has the basic file and browser access this workflow needs. Directory logins, verification and individual platform rules still vary.
- Only the file action worked
- Configure your agent’s Chrome integration before purchasing. The toolkit’s browser guide documents connection options, but buying a directory toolkit does not add a browser capability to your editor.
- Neither action worked
- Set up local-file access and browser access first. You can still read the public directory sample.
This is a basic capability check, not a guarantee of every submission or a measured setup-time promise. It does not use your inbox or log in to an account. Your provider’s normal usage terms apply.
Read the public browser connection instructions →Read the public directory sample →
The five steps
Everything below happens on your machine, with your accounts. Nothing runs in the background while your agent is stopped.
Step 1: Give it the facts.
Your agent helps collect your description, screenshots, pricing and allowed claims. Agree on the browser, verification-email and publication permissions for this product.
Step 2: Plan your run.
Start with a target of 10 new confirmed submissions and at most 2 in parallel. The local planner recommends 1 when resources or browser isolation are insufficient. Choose platforms by fit, current rules and effort.
Step 3: Start a goal, then work through the run.
Copy the saved run prompt to your agent. Use /goal if your agent supports it; otherwise paste the same instructions as a normal message. The agent works through suitable free platforms within your permissions and records each result before continuing.
Step 4: Record the actual result.
Only new confirmed submissions count toward the target: pending review, queued, scheduled or live, once per platform. Drafts, existing listings and blocked attempts do not count. After recording evidence, the agent closes that submission’s assigned window.
Step 5: Pick up where you left off.
Resume the saved run for its remaining submissions. Provider limits or human steps can interrupt a session; a goal is not a guarantee of uninterrupted execution. Add your next product with its own information and permissions.
Setup in practice
The technical side of the first session is documented in three short guides:
What still needs you
LaunchRepo is deliberately not a background service. These moments are handed to you and recorded as human handoffs instead of being “solved” by the agent:
- CAPTCHAs and bot checks
- The agent stops, records prepared_needs_human and the dashboard lists the platform under “needs you”. You solve it in your own browser.
- 2FA and verification codes
- Codes arrive in your mailbox in the connected browser. Forwarding a code by hand is a supported fallback and is recorded as a human handoff, never as automated access.
- Paid routes
- If the only usable route costs money, the platform gets deferred_paid. No purchase is ever made; you decide later, with the note in front of you.
- Your public representation
- Before a maker bio, launch intro or “why I built this” reaches a listing, PR-BRIEFING.md shows you concrete examples to correct. Approved wording is kept in representation.md.
- Website badges
- Some directories require a badge on your site. The agent asks once per product whether it may add, commit and deploy one; a “no” is recorded and does not block the rest.
- Confirming “live”
- A thank-you screen is not a listing. Marking a platform live requires a public URL and your attestation that you reviewed it.
What the tracker states mean
record.py accepts exactly these states, and the dashboard shows the same ones. Each is tied to a minimum observation so a “done” never gets inflated:
| State | Minimum observation |
|---|---|
draft | Work prepared; the final submission is not confirmed. |
prepared_needs_human | A precise owner action or challenge (CAPTCHA, 2FA, unclear account) blocks prepared work. |
submitted_pending_review | The platform explicitly received the submission and moderation is still pending. |
queued | The platform confirms a queue position or waiting-list state. |
scheduled | The platform confirms a launch date on or after your earliest launch date; any outstanding approval stays in the note. |
live | Public listing verified with no pending label; requires the public URL and your confirmation. |
already_listed | An existing public listing was found and verified; same URL and attestation requirement as live. |
blocked | Eligibility, account capacity or a mandatory missing fact prevents progress. |
deferred_paid | The currently usable route requires payment; no purchase was made. |
not_a_fit | The product does not meet the audience or listing criteria. |
unavailable | The route or platform cannot currently be used; the observed problem is noted. |
Each platform’s result stays independent: a partner-distribution checkbox on one site does not count as a second submission, and “scheduled” can still take several weeks to actually post on free-tier directories.
The founder explains it in under three minutes
Aleks walks through what LaunchRepo does, who it is for and what it deliberately leaves to you. English audio.
Questions about the flow
Does it submit automatically while I sleep?
No. Your agent runs in your session, in a browser you can see, and the repository runs nothing in the background. CAPTCHAs and 2FA pause that platform for you. The agent can continue eligible independent work; paid routes are skipped. The saved target lets a later session resume the remaining work.
Which agents can run it?
Any agent that can read local files and use Chrome DevTools MCP with a browser you are signed in to. We name Claude Code, Codex and Cursor because they meet those two requirements when their browser integration is set up; we publish no benchmark and certify no configuration. The capability check above tells you whether yours is ready.
How long until a listing is live?
From minutes to several weeks. Free-tier directories queue submissions for review, and “scheduled” is not “live”. Your earliest launch date sets a floor; the tracker records queued, scheduled and pending review separately so you always know what has actually posted.
What if a directory only offers a paid route?
The agent records deferred_paid with a note and moves on. The default workflow pauses before paid actions and never authorises a purchase; whether a featured spot is worth it stays your decision.
Do I have to work in the terminal?
No. python3 scripts/dashboard.py starts a local dashboard on 127.0.0.1 with products, states, handoffs, follow-ups, the catalog and the prompts to hand back to your agent. Its forms write the same files the agent reads; --demo shows a sample workspace before you set up your own.
One payment. A process you can use again.
The reference price is €119.00, one-time, and it does not rise. The pricing page shows the live price, the requirements and everything that is included.