Edit: RPA is an acronym for Robotic Process Automation - things like triggering mouse clicks and key strokes to perform tasks programmatically. Sorry if this wasn't clear!

We were working on non-RPA integrations when a customer promised to sign a deal in 2 days if we could unblock a sale of theirs that involved integrating with a clinic’s Windows based medical record system. We didn’t know it at the time but it turns out that building desktop RPAs at scale is extremely difficult because scripting is hard (learning the system, defining the automation, UIs changing constantly), orchestration is hard (is the VM up? queuing, parallelizing) and debugging is hard (zero observability, false positives, cascading failures). 30%+ failure rates are not uncommon. At scale we’ve seen cases of failed RPAs leading to thousands of support tickets a month.

To solve the problems we were facing, we built an MCP that Claude Code/Codex can use to navigate a virtual machine running desktop software with Python to create RPA workflows. The RPA workflows run as Python scripts for speed, cost, and determinism. These workflows can be triggered by API following any input/output schema specified, with video replays and logs stored with each run. The MCP can debug RPAs and make changes to the underlying code, all of which are version controlled. We also built tools for cloning VMs for parallelizing RPAs, and handling 2FA/OTP challenges. Plus since workflows are code based: we were also able to add triggers for Slack notifications, human-in-the-loop steps, or call an LLM to verify the state of a VM by passing a screenshot.

Would love to hear your feedback and if you have any RPA horror stories! (:

I was trying to deploy Ghost on a DigitalOcean droplet and found that DO and many different VPS services have started to block the default SMTP ports to try to combat the various types of abuse they get. To actually configure my app, I had to hack together a Postfix relay.

In another project, I had a static site which had a contact form, but my free Formspree account was occasionally hitting usage limits and I desperately wanted some of the anti-spam features they had gated behind their paid accounts so I put together a caddy module to catch HTTP POSTs and bounce them to my provider.

I kept bumping into these same email issues. Many of the services I wanted to host (Gitea, Mastodon, Umami, Comentario) ran into the same limitations. This felt like a really common issue that had no good solution.

Posthorn is what I built to solve this. It's a small Go binary (or 10 MB docker image) that sits between your self hosted apps and your transactional email provider of choice (shipping with support for Postmark, Resend, Mailgun, Amazon SES or an outbound SMTP relay). It also accepts POSTs from HTML forms to support static site needs while adding security layers such as honeypot fields, origin checks and IP rate limiting. There's also a JSON HTTP API that supports Bearer auth for backend scripts or cron jobs that just want a /send endpoint.

I now use this personally in multiple scenarios and I've spent a lot of time beating this up and testing against what I can validate. I'd love to hear how this might be useful for you, what breaks and any feedback you might have. It's open source under Apache 2.0 and I'd love contributions. I'm planning to support and grow this for the long haul.

Code: https://github.com/craigmccaskill/posthorn

Docs: https://posthorn.dev/

Longer write up: https://craigmccaskill.com/introducing-posthorn/

Previous HN discussion on the exact issue I'm trying to solve: https://news.ycombinator.com/item?id=43620318

https://twitter.com/drewhouston/status/2059275240065425474?s...