guilds.run
Create multi-agent workflows that you can trust
392 followers
Create multi-agent workflows that you can trust
392 followers
Open-source AI agent teams you can actually inspect. Debug every prompt, tool call, memory change, and agent interaction. Control permissions, edit context, and choose the model for each agent. Self-host for free. Stop guessing what your agents are doing.
Free
Launch Team / Built With
Framer AI AgentsDesign and publish professional sites with AI
Promoted
Hi there! I’m not technical at all, yet within a few hours, I set up automated prospecting on LinkedIn. It searches for and invites prospects, sends personalized messages, and follows up.
@vincent_cigale can we test it as a template?
Love the idea of being able to see what AI agents are actually doing. The debugging and permissions features look really useful. Congrats on the launch 🚀🙏🏻
@zeynepsahin Thanks for the support Zeynep
@zeynepsahin That's exactly it :) Thanks for the support.
We should thank @Jev for their great product too. If you have a typesafe key, then guilds.run use it for smart group chat message routing and context compression.
3rd maker here! I have a PhD in cognitive science, and now I’m trying to understand what’s going on inside agent “brains.” 😅
Hope you like what we’re building!
@dadadel this guy, never miss an opportunity to show off his PHD 😝
@m4nuc My agent brain has a permission setting for PhD mentions. Default: always on 😅
Get started with:
@m4nuc So easy even a non-PhD can run it 😜
@m4nuc @dadadel 😅
Being able to trace how a mistake propagates from one agent to the next is the part I find most interesting. When you debug a failed run, does the trace show the exact message one agent passed to the next, or only each agent’s own steps?
@neerajnathany Yea, you can crawl back the call tree and see what agent was the cause and why, then fix that until you get the perfectly oiled workflow
That's exactly the answer I was hoping for, thank you! Being able to walk back the call tree and see which agent caused the problem turns a frustrating mystery into something you can actually fix. I'm going to try it on a workflow this week :)
Seeing where an assumption went wrong as it passes between agents sounds useful. Being able to follow that trail would help with figuring out what to fix. Congrats on the launch, Emmanuel and Vincent!
@oleksii_sekundant exactly. Thanks for the kind words Olek