Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Orchestrate teams of Claude Code sessions

code.claude.com

Post reply on HN
Print view View original

111–120 of 238 posts

Re: Orchestrate teams of Claude Code sessions

#111

Post by shafyy »

digdugdirk wrote: post #105
doctoboggan wrote: post #99

Earlier quoted context omitted.

It _does_ use up tokens incredibly fast, which is probably why Anthropic is developing this feature. This is mostly for corporations using the API, not individuals on a plan.

I'd love to see a breakdown of the token consumption of inaccurate/errored/unused task branches for claude code and codex. It seems like a great revenue source for the model providers.

Yeah, that's what I was thinking. They do have an incentive to not get everything right on the first try, as long as they don't over do it... I also feel like that they try to get more token usage by asking unnecesary follow up questions that the user may say yes to etc.

Re: Orchestrate teams of Claude Code sessions

#112

Post by andyferris »

tclancy wrote: post #95
nickstinemates wrote: post #92

Earlier quoted context omitted.

You write a generic architecture document on how you want your code base to be organized, when to use pattern x vs pattern y, examples of what that looks like in your code base, and you encode this as a skill. Then, in your prompt you tell it the task you want, then you say, supervise the implementation with a sub agent that follows the architecture skill. Evaluate any proposed changes. There are people who maximize…

How does this not use up tokens incredibly fast though? I have a Pro subscription and bang up against the limits pretty regularly.

It does use tokens faster, yes.

Re: Orchestrate teams of Claude Code sessions

#113

Post by nickorlow »

greenfish6 wrote: post #14
nickorlow wrote: post #10

Earlier quoted context omitted.

yeah, seems like a much simpler design though (i.e. only seems like one 'special/leader' agent, and the rest are all workers vs gastown having something like 8 different roles mayor, polecat, witnesses, etc). Wonder how they compare?

i would have to imagine the gastown design isn't optimal though? why 8, and why does there need to multiple hops of agent communications before two arbitrary agents communicate with each other as opposed to single shared filespace?

yegge's article does come off as complicated design for the sake of complication

Re: Orchestrate teams of Claude Code sessions

#114

Post by bcrosby95 »

ttoinou wrote: post #79
bonesss wrote: post #70

Earlier quoted context omitted.

Compare both approaches to mature actor frameworks and they don’t seem to be breaking much ice. These kinds of supervisor trees and hierarchies aren’t new for actor based systems and they’re obvious applications of LLM agents working in concert. The fact that Anthropic and OpenAI have been going on this long without such orchestration, considering the unavoidable issues of context windows and unreliable self-validati…

If it was so obvious and easy, why didn't we have this a year ago ? Models were mature enough back then to make this work

The high level idea is obvious but doing it is not easy. "Maybe agents should work in teams like humans with different roles and responsibilities and be optimized for those" isn't exactly mind bending. I experimented with it too when LLM coding became a thing.

As usual, the hard part is the actual doing and producing a usable product.

Re: Orchestrate teams of Claude Code sessions

#115

Post by eaf7e281 »

nkmnz wrote: post #17

I’m looking for something like this, with opus in the driver seat, but the subagents should be using different LLMs, such as Gemini or Codex. Anyone know if such a tool? just-every/code almost does this, but the lead/orchestrator is always codex, which feels too slow compared to opus or Gemini.

These two basically do what you want, let Claude be the manager and Codex/Gemini be the worker. Many say that Coder-Codex-Gemini is easier to understand than CCG-Workflow, which has too many commands to start with.

https://github.com/FredericMN/Coder-Codex-Gemini https://github.com/fengshao1227/ccg-workflow

This one also seems promising, but I haven't tried it yet.

https://github.com/bfly123/claude_code_bridge

All of them are made by Chinese dev. I know some people are hesitant when they see Chinese products, so I'll address that first. But I have tried all of them, and they have all been great.

Re: Orchestrate teams of Claude Code sessions

#116

Post by khaliqgant »

nkmnz wrote: post #17

I’m looking for something like this, with opus in the driver seat, but the subagents should be using different LLMs, such as Gemini or Codex. Anyone know if such a tool? just-every/code almost does this, but the lead/orchestrator is always codex, which feels too slow compared to opus or Gemini.

You can accomplish this with https://github.com/AgentWorkforce/relay and make the Lead/Orchestrator any harness you want. At the core agent-relay is agent to agent communication but it unlocks quite a few multi agent orchestration paradigms. I wrote about some learnings here as well https://x.com/khaliqgant/status/2019124627860050109?s=46

Re: Orchestrate teams of Claude Code sessions

#117

Post by khaliqgant »

Been waiting for this to drop and excited to test it out. We've been building something in this space - https://github.com/AgentWorkforce/relay, a real-time messaging layer that lets AI coding agents talk to each other across any CLI.

Assign roles to different models and have them coordinate: Claude as the lead, Codex on backend, Gemini on frontend, etc.

I wrote about my experiences with multi-agent orchestration here: https://x.com/khaliqgant/status/2019124627860050109?s=46

Re: Orchestrate teams of Claude Code sessions

#119

Post by frde_me »

satellite2 wrote: post #94
nickstinemates wrote: post #92

Earlier quoted context omitted.

You write a generic architecture document on how you want your code base to be organized, when to use pattern x vs pattern y, examples of what that looks like in your code base, and you encode this as a skill. Then, in your prompt you tell it the task you want, then you say, supervise the implementation with a sub agent that follows the architecture skill. Evaluate any proposed changes. There are people who maximize…

Aren't you just moving the problem a little bit further? If you can't trust it will implement carefully specified features, why would you believe it would properly review those?

It's hard to explain, but I've found LLMs to be significantly better in the "review" stage than the implementation stage.

So the LLM will do something and not catch at all that it did it badly. But the same LLM asked to review against the same starting requirement will catch the problem almost always

The missing thing in these tools is that automatic feedback loop between the two LLMs: one in review mode, one in implementation mode.

Re: Orchestrate teams of Claude Code sessions

#120

Post by Spoom »

woah wrote: post #86
nprz wrote: post #49

Earlier quoted context omitted.

There is research[0] currently being done on how to divide tasks and combine the answers to LLMs. This approach allows LLMs reach outcomes (solving a problem that requires 1 million steps) which would be impossible otherwise. [0] https://arxiv.org/abs/2511.09030

All they did was prompt an LLM over and over again to execute one iteration of a towers of hanoi algorithm. Literally just using it as a glorified scripting language: ``` Rules: - Only one disk can be moved at a time. - Only the top disk from any stack can be moved. - A larger disk may not be placed on top of a smaller disk. For all moves, follow the standard Tower of Hanoi procedure: If the previous move did not mov…

Good lord, I can only imagine the wasted electricity.
Post reply on HN