Hello community, for future consideration when developing hosting-related features/improvements for a0, what are the most popular cloud providers you normally use? I am in the process of choosing a provider to build my new lab for cloud experiments and I would like to align with what is in use for the majority of our users. Just write your favorites in the comments. Best, Rafael

This is what I run in Claude Code. Goal is to have A0 manage as the overall Orchestrator of Orchestrators, if you will, via Terminals or subagents? We discussed a bit in weekly meet. Maybe this helps someone. Just takes small amount of customization to fit your needs! https://github.com/bybren-llc/wtfb-safe-agentic-workflow What This Is A production-tested Claude Code harness for teams that want structured AI workflows. Built on SAFe methodology (Scaled Agile Framework), adapted for AI agent teams. Works for any team with repeatable processes: Software, Marketing, Research, Legal, Operations. Includes: - 17 Model-Invoked Skills - Domain expertise Claude loads automatically - 23 Slash Commands - Workflow automation for common tasks - 11 SAFe Agent Profiles - Specialized roles with clear boundaries - Three-Layer Architecture - Hooks → Commands → Skills

I can't get the Browser-agent to work, I get information like like " "Task reached step limit without completion. Last page: about:blank. The browser agent may need clearer instructions on when to finish" any ideas ??? Thanks

and I want to say the research agent is most defintely the most capable when it it comes to handling multi step reasoning and thinking smart. I usually reference the reasoning loop from that agent when creating new ones as a starting point if I need some super smart thinking. whoever did that research agent prompt....you rock on that one

I want to start a discussion about our new subordinate agents. These agents are now a way to fully enhance the A0 system as they can have their own tools and system extensions. In other words, agents can now be used as plugins for the A0 system. This allows us to create a repository of custom agents inside our community platform https://agent-zero.ai/?community that would be maintained by independent developers as well as our team and could be pulled into an existing A0 instance at runtime. Technically, the agent folder containing the prompts, tools and extensions would be hosted on the creator's GitHub and linked to our community platform. This would allow users to browse agents on the platform, sponsor/tip creators in A0T tokens directly and A0 itself would be able to clone these git repos and include these subagents into itself. What are your options? Should we make an improvement proposal for it already? Thanks!