For a while, I had active subscriptions to Codex, Cursor, Grok, Devin, Antigravity, Kimi, and StepFun, running them across the cloud and five local machines. My main requirement was to keep each model running inside its official harness to get the best performance while staying compliant with their Terms of Service. Under the hood, they can all be invoked via CLI, but they often have to run in headless mode to work reliably. Because of that, I can't see the logs for sub-conversations or child threads, nor can I track the file changes they make or the reasoning behind them. So I wanted a unified setup that connects these harnesses over the ACP protocol, letting models in different environments communicate while a central orchestrator routes tasks to the right model. I tried (Tailscale +) Devin and Cursor over SSH Remote, tmux, herdr, and luvus before settling on Lody. It handles cross-harness control on a single machine as well as across all my devices. Having a UI is also more comfortable than working purely in the terminal, and I don't need to memorize another set of keyboard shortcuts. The project is open-source, and the maintainers were quick to respond when I opened a few issues. Unlocking the full feature set requires a subscription, which I think is worth it and makes for a sustainable business model. Orca, Paseo, and T3 Code are also positioned in a similar space, though I haven't tested them extensively. All of them are worth a try.

The developers contributing to Lody have given us an incredible amount of energy. Our team has embraced open source since @loro_dev . It’s hard to explain the appeal—but building something with like-minded people and solving shared problems together feels genuinely amazing.

Your agents never stop. Now they fit in your pocket. Lody for iOS: · Live Activity for every running session · Replies stream in live, diffs down to the word · Steer mid-turn from anywhere · New: your Mac's Simulator, streamed to your iPhone TestFlight:

✨ I think I've been coding almost solely on my VPS with Claude Code for almost a year now All I can say it's just fantastic: - no need to keep laptop open ever - no laptop battery drain - can switch to phone or any other device you like whenever you want to continue (like when you're outside) - it just keeps going all night while you sleep (esp with /goal) - you can start hacky projects from scratch and go live in seconds because you're already on the server which is great to ship things and get it used by people fast (not stuck on your local laptop webserver) - it just feels like living in the future I used to code on my laptop, test locally, then push to GitHub, then it auto pulled and deploy to production, that'd take me ~1 minute to get a new feature out But then when I bought a new Mac Book Pro a few years ago I was too lazy to install a local Nginx environment, so I just started pushing to prod and everything went fine, and I sped up deploying to about 3 seconds from laptop to server, which people called me crazy for too But now with Claude Code on my VPS in the last year, it just live edits on my production server, which sounds like it should go wrong but it just doesn't, it's very careful and only twice in 12 months messed up which meant my site didn't load for 10 seconds which is OK If I wasn't working solo, like at a big company, I' think I'd recommend the same workflow but with a staging server, so it wouldn't touch production, for safety and regulatory reasons etc. but for me it's fine I agree with @theo completely, it's clear to me this is where it's going, also seeing @karpathy with Claude moving to the cloud (via Slack etc), I think AI "agents" and AI coding will operate on servers / from the cloud first P.S. I have 3-2-1 backups, multiple on-site and off-site backups which you should also even if you wouldn't code with AI, safety first!