Agent-to-agent pair programming(axeldelafosse.com)
72 points by axldelafosse 8 hours ago | 17 comments
divan 9 minutes ago
You can also create a skill for reviewing (which calls gemini/codex as a command line tool) and set instructions on how and when to use. Very flexible.
yesensm 2 hours ago
I’m curious whether anyone has measured this systematically. Right now most of the evidence for multi-agent setups still feels anecdotal.
stackgrid 1 hour ago
Completely with you on this! But then we need to define the cirteria for comparison. Might not be that easy unfortunately
rsafaya 59 minutes ago
I think the A2A space is wide open. Great to see this approach using App Server and Channels. I tried built something similar (at a high level) for a more B2C use case for OpenClaw https://github.com/agentlink-dev/agentlink users. Currently I think the major Agents have not fully owned the "wake the Agent" use case fully. Regardless this is a very cool approach. All the best.
cadamsdotcom 6 hours ago
The vibes are great. But there’s a need for more science on this multi agent thing.
axldelafosse 5 hours ago
I agree! Right now it is leveraging the Codex App Server, which is open-source and very well implemented, but using Claude Code Channels is probably a bit hacky.

The good thing is that it establishes a direct connection so it's already much better than having one agent spawn the other and wait for its output, or read/write to a shared .md file -- but it would be cool to make it work for all agent harnesses.

Open to ideas! The repo is open-source.

d0963319287 4 hours ago
there’s a need for more science on this multi agent thing
alienreborn 6 hours ago
I have been trying a similar setup since last week using https://rjcorwin.github.io/cook/
axldelafosse 5 hours ago
Oh, that's cool!
edf13 3 hours ago
Nice - I do something similar in a semi manual way.

I do find Codex very good at reviewing work marked as completed by Claude, especially when I get Claude to write up its work with a why,where & how doc.

It’s very rare Claude has fully completed the task successfully and Codex doesn’t find issues.

nurettin 22 minutes ago
Claude is also good at that. I made a habit of asking "are you sure?" after a complex task. It usually says it overlooked something.
axldelafosse 3 hours ago
I created the first version of loop after getting tired of doing this manually!
edf13 3 hours ago
I’m going to take a look today!
vessenes 7 hours ago
I prefer claude for generation / creativity, codex for bull-headed, accurate complaining and audit. Very rarely claude just doesn't "get it" and it makes sense to have codex direct edit. But generally I think it's happiest and best used complaining.
ph4rsikal 4 hours ago
shreyssh 2 hours ago
This is interesting for code, but I'm curious about agent-to-agent coordination for ops tasks — like one agent detecting a database anomaly and another auto-remediating it
highphive 1 hour ago
I think a lot of people/companies are integrating workflows like that, it's just separate from the point of agent pair coding.

The interesting thing here is agents working together to be better at a single task. Not agents integrated in a workflow. There's a lot of opportunity in "if this then that" scenarios that has nothing to do with two agents communicating on one single element of a problem, it's just Agent detect -> agent solve (-> Agent review? Agent deploy? Etc.)

8 hours ago
bradfox2 6 hours ago
Multi turn review of code written by cc reviewed by codex works pretty well. Been one of the only ways to be able to deliver larger scoped features without constant bugs. I've seen them do 10-15 rounds of fix and review until complete.

Also implemented this as a gh action, works well for sentry to gh to auto triage to fix pr.

_ink_ 3 hours ago
How do you do this? Are you just switching between clis? Or is there a tool that uses the models in that way?
encoderer 5 hours ago
Yes I’ve had a lot of success with this too. I found with prompt tightening I seldom do more than 5 rounds now, but it also does an explicit plan step with plan review.

Currently I’m authoring with codex and reviewing with opus.

axldelafosse 5 hours ago
Good reminder: don't forget the plan review!
jedisct1 7 hours ago
I systematically use reviewers agents in Swival: https://swival.dev/pages/reviews.html

Even with the same model (--self-review), that makes a huge difference, and immediately highlights how bad the first iterations of an LLM output can be.

AbanoubRodolf 6 hours ago
[dead]
chattermate 29 minutes ago
[dead]
hikaru_ai 2 hours ago
[dead]
kevinbaiv 2 hours ago
[dead]
elicohen1000 2 hours ago
[dead]
vacancy892 4 hours ago
[dead]