My team fully abandoned our attempts to make OpenClaw or Claw-like agents work for us. We invested a sizable chunk of our R&D budget to setting various Claws up to help our software and QA teams. It took about a week after launch for the team to fully sour on the idea of using these systems.

The biggest feedback we collected was that any tasks they assigned to the Claw systems would turn into tangled messes often requiring significant time investment to understand, and mostly ending in the team scraping the code changes over quality concerns. The team really struggled to find anything these Claw systems could be tasked with that wouldnt end in poor results, So we ended up scraping the idea entirely. I think it will be quite a few more years until these types of systems are appropriate for the enterprise.

We also tried to use OpenClaw for teams but unfortunately OpenClaw gateway is not designed as multi-tenant. Peter also confirms it: https://x.com/steipete/status/2026820269050855757

That's why we built https://lobu.ai which is a multi-tenant implementation for proactive agents like OpenClaw. It has entity based memory for building the org context layer and every channel/user gets its isolated container.

I don't know about other people, but the name "OpenClaw" immediately signals jank and wrecklesness to me. Like, as a consumer, I will pretty much immediately write it off.

I've never run it, but isn't OpenClaw kind of useless if you sandbox it? I thought the entire point is that it has access to do everything. The danger with OpenClaw IMO isn't so much that your local machine gets hacked (although it's certainly a real danger), the danger is giving sensitive data to something horribly unreliable that can leak it or take actions on your behalf that are very dumb. I can understand (although very much disagree) with individuals running it, but trying to do it in the "enterprise" feels like playing with fire in a bad way.

With agentjail (github.com/LuD1161/agentjail), I've tried to contain coding agents in os-native sandboxes (sbpl for macos and similarly for linux) + policy guardrails evaluated by Open Policy Agent (OPA), policies written in rego.

Protocol aware network proxy coming soon Then you can match a DSL and block particular network requests.

This ensures you no longer fear --dangerously-skip-permissions and stop babysitting agents

What else would you want to see in this project? Please star the repo, if you like the idea :)

Truthfully, this sounds like you're showing folks the magic code to get inside various arcade claw machine games.

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 get. Nope. Nopedy nopedy nope.

Anything made in a couple of days or even hours is abandoned easily. This is how I felt when I saw the onslaught of OpenClaw tutorials months ago. I wonder how many of those influencers who felt they were so far ahead of the game are still using it and if they still feel the GAME has been SHOCKINGLY CHANGED.

I wouldn't want OpenClaw anywhere near a business I was running, even if I was all aboard the LLM hype train. That codebase is a nightmare. Just take a look at the hundred-plus pages of bugs on the Github repo.