Anyone running multiple agents concurrently in production? And has anyone tried going leaderless? There's LangGraph, CrewAI, etc. But I keep coming back to whether you need an orchestrator at all. No supervisor. Just…
Anyone running multiple agents concurrently in production? And has anyone tried going leaderless?
There's LangGraph, CrewAI, etc.
But I keep coming back to whether you need an orchestrator at all.
No supervisor. Just agents, each reacting to their own inputs, coordinating only through shared state. A true leaderless architecture.
The way some distributed systems have been for decades.
Context: previously, I wrote about running Claude Code as an AI SRE handling an incident end to end. I've been rebuilding it as four, all working on the same incident: detect, diagnose, remediate, communicate.
3 comments
spidey22about 2 months ago
Have you tried Kiro Crew?
arachabout 2 months ago
what kind of workloads are we talking about?
har-kiabout 2 months ago
Multiple agents working on long lived records. Agents could be owned by the same or different parties.
Read the full thread on Hacker News →
Related stories
- DEV Community · 52 points · 2 months ago
- Hacker News · 1 points · about 2 months ago
- Multi-Agentdevelopers.openai.comHacker News · 2 points · about 2 months ago
- Hacker News · 5 points · 2 months ago
- Hacker News · 1 points · 2 months ago
- Hacker News · 9 points · about 2 months ago