News for hackers. Stuff that matters.
Re:Building a Multi-Agent System from Scratch: Architecture ... by brkomir on Thursday November 05, 2026 @02:47PM (#50383531)
I usually run 4-5 claude sessions in parallel on the same branch, each with its own working plan or work item. They coordinate almost in real time, leaving messages in a shared queue and picking them up every 30 seconds. What keeps them from stepping over each other's work is a commit script that allows only staged changes from one session to be committed at a time.

Where it actually pays off to have separate sessions is the code review. Every code change that affects how the app behaves is checked by a session that didn't write the change. Some numbers: 4,454 verdicts on 4,471 commits since September. About four in five first reviews found something, and about half asked for changes.

Re:Building a Multi-Agent System from Scratch: Architecture ... by cgio on Thursday November 05, 2026 @04:19PM (#50384598)
They always find something. I am at the level where in a review I allow the reviewer to give me the most important item only and explain its impact.
Re:Building a Multi-Agent System from Scratch: Architecture ... by UncleOxidant on Thursday November 05, 2026 @07:43PM (#50386701)
Interesting. I'd like to have something where I'm primarily running a local model - Qwen3.8-Flash-Next - and then have it consult with a frontier model as an "advisor" - like how you can setup an advisor model in Claude code.
Re:Building a Multi-Agent System from Scratch: Architecture ... by leobg on Friday November 06, 2026 @01:15PM (#50396095)
> They coordinate almost in real time, leaving messages in a shared queue and picking them up every 30 seconds. What keeps them from stepping over each other's work is a commit script that allows only staged changes from one session to be committed at a time.

You wrote that as a skill or hook or something? I do notice that sessions have knowledge of other sessions, but what you’re describing sounds more formalized and enforced.

Re:Building a Multi-Agent System from Scratch: Architecture ... by brkomir on Sunday November 08, 2026 @01:58PM (#50415956)
A hook plus a background script. The hook tells the session to arm the background script (mail-listener) that check every 30 seconds for anything addressed to it or the entire fleet, using Calude Code’s Monitor tool.

The mailbox is a file-based message queue I’ve been using since June. It can broadcast to every session at once, it holds mail for up to 72 hours, and the messages stay on disk as a record. Claude Code added its own cross-session messaging in the meantime, but I still use my own because of the differences.

For example, the most heavy daily use is for code reviews. Session A writes the code -> dedicated review session reviews it -> Session A fixes the findings or challenges some -> the reviewer runs another round. The loop is closed once every finding is fixed or tracked in todo/backlog (as long as it’s not high or critical severity).

The commit part is a script that refuses any staged file that isn't the committing session's own.

It’s my own design and it's open source if you want to look and play around. I'd appreciate your feedback! https://github.com/brkomir/anja