Something I’ve noticed in the community is that whenever the devs explain how something works, there are always a few people who respond like, “Yeah, I know,” and then immediately follow it with, “I’d like to see this,” or, “You should build that.” If you already understand the architecture and you’re confident the solution is straightforward, why not build it yourself and show everyone? That’s the beauty of an open-source project. Prototype it. Submit a pull request. Demonstrate that it works. Feature requests are valuable, but there’s a big difference between saying, “Here’s an idea,” and speaking as if the implementation is obvious while expecting someone else to spend their time building it. The devs are already carrying the weight of the project. If you’re convinced your idea is the right one, the best way to prove it isn’t by talking about it on a community call—it’s by building it. That version gets the point across without turning into a personal attack. It challenges the “I already know” mindset and redirects it toward contributing, which is a much stronger argument in an open-source community. and with all that said im a long time user and looove agent zero. but some things just rub me a bit different. it is open sourced you are free to do what you want with it

I like it a lot , but I have like zero Linux, programming and sysadmin experience. Looking for a freelancer to setup my system correctly and provide additional support when needed.

These are two hours of demos, Q&A and new features. Thanks @Leigh Phillips for your Superordinates plugin showcase. As always we really appreciated having you, thanks everyone for dropping by! If you missed the call or want to rewatch any part of it, the full recording is now available 🎥

So lets address the elephant in the room, A0 or clawdbot - Who and why?

So I'm not a developer, but I spend about 15 hours a week over last year building with agents and have developed some expert system and effective training bots. But for me Agent Zero confabulates more than any other agent platform I've worked with. Is this happening for anyone else? It tells me there's an instance set up on the server of an application and that the testing is all fine when it isn't. It tells me it's working through a scan of selected websites and producing a report when it isn't. It often takes me a lot of prompting to get it to admit that it was simulating a web server monitoring output and it wasn't the actual output. Experimented with a wide range of llms and still getting this problem frequently (or endless loops) including with gpt 4.1, 5.2, Kimmy K2, GLM 4.6. I'm sure it's something to do with me because a lot of very expert users are doing great with Agent zero, so appreciate any tips.