Doesn't codex already do this when it decides whether to use subagents, and what prompt to give each subagent?
Yes, but as far as I'm aware, subagents can't spawn their own subagents, so the root agent tends to grow its context linearly
Cord: Coordinating Trees of AI Agents
41–50 of 93 posts
Re: Cord: Coordinating Trees of AI Agents
#42[flagged]
>40% of total tokens go to coordination rather than actual task completion once you get past 3-4 agents
Remarkably similar to humans.
Re: Cord: Coordinating Trees of AI Agents
#43This is a vibeslop project with a vibeslop write-up.
Trees? Trees aren't expressive enough to capture all dependency structures. You either need directed acyclical graphs or general directed graphs (for iterative problems).
Based on the terminology you use, it seems you've conflated the graphs used in task scheduling with trees used in OS process management. The only reason process trees are trees are for OS-specific reasons (need for a single initializing root process, need to propagate process properties safely) . But here you're just solving a generic problem, trees are the wrong data structure.
- You have no metrics for what this can do - No reason given for why you use trees (the text just jumps from graph to trees at one point) - None of the concepts are explained, but it's clearly just the UNIX process model applied to task management (and you call this 60 year old idea "genuinely new"!)
Re: Cord: Coordinating Trees of AI Agents
#44[dead]
Re: Cord: Coordinating Trees of AI Agents
#45Re: Cord: Coordinating Trees of AI Agents
#46We built something like this by hand without much difficulty for a product concept. We'd initially used LangGraph but we ditched it and built our own out of revenge for LangGraph wasting our time with what could've simply been an ordinary python function. Never again committing to any "framework", especially when something like Claude Code can write one for you from scratch exactly for what you want. We have code on…
This is one of the worst takes I've ever heard.
There's a reason industries have standards. If you replace established libraries with vibecoded alternatives you will have:
- less documentation
- less tested code
- no guarantees it's doing the right thing
- a dice roll for whether it works this time on this project
- a bad time in general
Re: Cord: Coordinating Trees of AI Agents
#47Why can’t you just give access to all tools to all subagents? That’s more general than what you’ve done. Surely it can figure out how to backtrack or keep context?
But I do like you approach and I feel this is the next step.
Re: Cord: Coordinating Trees of AI Agents
#48I love this. I always imagined more capable agent systems that have graph-like qualities.
Re: Cord: Coordinating Trees of AI Agents
#49[dead]
Re: Cord: Coordinating Trees of AI Agents
#50[dead]