News for hackers. Stuff that matters.

har-ki

Re:Ask HN: Has anyone built a leaderless multi-agent system? on Saturday September 26, 2026 @08:36AM (#49855929)
Multiple agents working on long lived records. Agents could be owned by the same or different parties.

Ask HN: Has anyone built a leaderless multi-agent system?

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:...

( Read More... | 3 comments | on HN )
Its an experiment worth trying - swap out Claude Code for OpenCode and run the benchmark. I'll try it out.
Re:Running Claude Code Offline on an M3 Pro with Qwen3.6 on Thursday June 11, 2026 @04:05PM (#48495718)
I am using qwen3.6:35b-a3b-coding-nvfp4, active 3b. Easier on my hardware - Mac M3 Pro.
Re:Running Claude Code Offline on an M3 Pro with Qwen3.6 on Thursday June 11, 2026 @02:00PM (#48494027)
Yes!! And your LiteLLM-proxy-to-internal-models setup is a cleaner setup than mine.
Re:Running Claude Code Offline on an M3 Pro with Qwen3.6 on Thursday June 11, 2026 @01:57PM (#48493987)
Fair question. I haven’t benchmarked it against other harnesses, so I can’t say it’s better.

My reason for using claude code is continuity - I use it for dev (it’s also the tool of choice for most people I work with), and it already has the context. And it supports both frontier and OSS models.