Birbla

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • I hacked this together with a small local irc server
    by iovrthoughtthis
  • I built a general version of this, with global addresses and messaging between any terminal-based agent + MCP for browser agents. OSS if you want to run your own server at https://github.com/awebai/aweb and hosted version at https://aweb.ai
    by juanre
  • This totally breaks sandbox / VM isolation if you have Remote Control enabled. This feature isn't just within sessions on a single machine, but can send commands to any session accessible by your account.

    Reading "Claude Code instructs the receiving Claude never to change permission settings" and so on in the docs makes it seem like they're using LLM classifiers to determine what commands are safe or not.

    by deviantintegral
  • I have built this with Claude as a script, but it can also message other models and get responses from them, and throughout my fleet of Linux machines via Tailscale. It's been mostly very useful, although occasionally you have to step in and interrupt if they start going the wrong way.
    by Cyuonut
  • I wish there was a clean way to compact the conversation into a prompt with all necessary context for a new fresh conversation.
    by Alifatisk
  • I was reading about the HF hack and one of the first thing the GPT swarm did was build a messaging system for themselves. This reminded me of that. (Also of how weirded out I was by Moltbook when it came out. Time flies!)

    Unrelated: when my Claude/Codex finishes cooking (or needs my attention), it pings a local HTTP endpoint that plays a frog sound on my laptop. I found this massively boosts quality of life.

    by andai
  • Like some others, I also built this myself. Overly simply, with tmux, a memory tree, and handoff files and an orchestrator. And yet for how simple it was, it was so effective at minimizing the amount of duplicate context. It's like having shared specialist subagents who source and derive important shared knowledge from separate threads. It's useful because some skills just take too much of a token penalty to invoke and a single shared persistent session just lets that issue melt away. One agent pays the cost of that large skill once, and you don't have to keep paying for it in input tokens for the rest of that conversation.
    by eigenblake
  • This is obviously cool and useful so kudos, but wow security researchers have to throw their hands up all the time.

    Now we open another attack surface where you can ask a remote agent to do things by default. There was a time when you call this a Remote Code Execution vuln. It's of course a feature here.

    by zurfer

Explore Birbla archives