Live data from Hacker News

Viewing profile — simple10

simple10

HN member
Joined
Thu, Dec 23, 2010, 12:04 AM UTC
HN karma
1,266
Public activity
463 items

About simple10

https://github.com/simple10

https://twitter.com/joejohnston

Recent public activity

  1. comment
    Comment #48714151

    I use an observability tool with claude code [1] that shows me usage including prompt and session cost. Even though I use a max subscription, it's interesting to see what it would …

  2. comment
    Comment #48210013

    The Ryzen AI Max 395 128gb is super cool, but not fast for inference. Order of magnitude slower than dedicated GPU but at half the cost. You can run larger models on it but it's sl…

  3. comment
    Comment #47975935

    The website has a broken github link. Repo is here https://github.com/DO-SAY-GO/ghostbox-releases but it's only a README.md with binary releases. No public source code?

  4. comment
    Comment #47759476

    I got kinda obsessed with observability a month ago and wired together a full stack for personal use. https://github.com/simple10/agent-super-spy - llm proxy + http MiTM proxy + LL…

  5. comment
    Comment #47747538

    This is useful if you want to keep an eye on what claude's actually doing behind the scenes: https://github.com/simple10/agents-observe

  6. comment
    Comment #47678103

    They kinda buried the code deep in their docs: https://github.com/GoogleCloudPlatform/scion

  7. comment
    Comment #47657287

    Really cool. I've been building a mission control system (multi agent orchestration) that follows very similar patterns of spec driven development, steering, and task management. H…

  8. comment
    Comment #47606278

    Yep. I finally realized what "green" accounts are for on HN. Recently created accounts.

  9. comment
    Comment #47605038

    Right on. Good luck! You might also want to play around with https://github.com/simple10/agent-super-spy if you want to see the raw prompts claude is sending. It was really helpful…

  10. comment
    Comment #47604270

    Sub-agent trees are fully tracked by the dashboard. When an agent is spawned, it always has a parent agent id - claude is sending this in the hooks payload. When you mouse over an …

  11. comment
    Comment #47604172

    Sort of. It wasn't really noticeable until I did an intentional audit of performance, then noticed the speed improvements. Node has a 30-50ms cold start overhead. Then there's over…

  12. comment
    Comment #47604013

    I hit a lot of limits on Pro plan. Upgraded to Max $200/mo plan and haven't hit limits for awhile. It's super important to check your plugins or use a proxy to inspect raw prompts.…

  13. comment
    Comment #47603928

    I'm not actually reading the jsonl files. Agents Observe just uses hooks and sends all hook data the server (running as a docker container by default). Basic flow: 1. Plugin regist…

  14. comment
    Comment #47603695

    This tool is useful if you want to see all the internal commands claude agents are making in real-time: https://github.com/simple10/agents-observe

  15. comment
    Comment #47603176

    Thanks! This was step one in my daily driver stack - better observability. I also bundled up a bunch of other observability services in https://github.com/simple10/agent-super-spy …

  16. story
    Show HN: Real-time dashboard for Claude Code agent teams

    This project (Agents Observe) started as an exploration into building automation harnesses around claude code. I needed a way to see exactly what teams of agents were doing in real…

  17. comment
    Comment #47445753

    Yes, this. They need as much lock-in as possible before IPO. Most likely less about cash flow and more about IPO story telling. We'll know for sure when they add full OpenClaw-like…

  18. comment
    Comment #47435566

    It's on my claw list to write a blog post. I just keep taking down my claws to make modifications. lol Here's the full (unedited) details including many of the claude code debuggin…

  19. comment
    Comment #47435066

    NemoClaw is mostly a trojan horse of sorts to get corporate OpenClaw users quickly ported over to Nvidia's inference cloud. It's a neat piece of architecture - the OpenShell piece …

  20. comment
    Comment #47435038

    Yeah, it's wild. I spent several weeks nearly full time on a deep dive of claw architecture & security. The short of it - OpenClaw sandboxes are useful for controlling what sub-age…

  21. story
  22. story
  23. comment
    Comment #47343337

    Klaus looks great! It's definitely looks like a step up from the one-click VPS deploys that are terribly insecure. I spent the past month hacking on openclaw to play nice in a dock…

  24. comment
    Comment #47066793

    Yeah, claude seemed genuinely shocked when it analyzed the logs. lol

  25. comment
    Comment #47059921

    Just sharing the most surreal 3-hour claude assisted debugging session I've ever had. This was intended for my team notes but thought I'd share it. It's a treasure trove of how Ope…