Show HN: OpenClawMachines – Extending OpenClaw to the Enterprise

31–32 of 32 posts

Re: Show HN: OpenClawMachines – Extending OpenClaw to the Enterprise

#31

Post by neya » Tue, Jul 14, 2026, 11:01 AM UTC

mathaix wrote: post #17

neya wrote: post #4

I was a basic user who happened to just TRY OpenClaw. Thankfully it was brief and thankfully I ended my session after being underwhelmed because the very next day, they were on the news for the wrong reasons. There is no way on earth I am trusting this or anything even remotely similar in an enterprise setting. In a way, it was course correction for me - I was super optimistic about AI until I saw how ugly it could g…

Do you use Claude or Codex, how different is it really?

I tried Claude, it was half decent. The real issue is these are pretty much ways for these AI companies to burn your tokens faster. Claude is notorious for this and I honestly can't get any real work done without ensuring it isn't randomly erroring out due to token limits. I don't use Codex so can't really comment. What really worked well for me is - using Codex/any other coding tool to write your own API integrations to work with (Eg. Google Calendar) and run a local server of your choice with MCP in it and use openrouter + some cheap model to get the actual work done. This is overblown, but only because the APIs I consume are non-standard.

Re: Show HN: OpenClawMachines – Extending OpenClaw to the Enterprise

#32

Post by jillesvangurp » Tue, Jul 14, 2026, 12:42 PM UTC

luplex wrote: post #29

jillesvangurp wrote: post #10

Earlier quoted context omitted.

We gave it a few months try. My conclusion was that it did interesting things but is designed completely wrong from the ground up which means it's got a lot of moving parts that are part of the code base that can break for all sorts of reasons. As a learning exercise it was pretty nice. But since then the plugin/connector ecosystem for things like Claude Code/Cowork and ChatGpt/Codex has first come into existence and…

I have a quite specific use case. I work for a government agency and we run our AI assistant with models from Azure, which works fine! (Although the models aren't always released with EU data residency) Our most interesting data and documents are classified (VS-NfD), and I don't know of any good certified AI solutions for that yet. I would love to experiment more with deeper system integration, but we can't do that w…

You'd pretty much have to self host on premise or in a fully certified environment for classified stuff like that. That will limit your options of course. But some of the OSS models might still be OK for this.

Post reply on HN