12 comments

  • tonyarkles 22 hours ago
    As a more general idea, I’ve had pretty great success using LLMs to write “doctor” scripts. Similar idea to what’s going on here, instead of repeatedly giving LLMs raw data files from hardware and having it find the same issues over and over, I’ve started being careful to drive the lessons learned into automated test scripts and just instinctively running them against telemetry files every time someone sends me one, whether or not there’s something wrong (or they’re just looking for some data analysis). It’s the kind of thing I’ve always wanted to do, but under time pressure would always just knock out 20 lines of numpy code, do whatever analysis or debugging, and then move onto the next fire.
    • __padding 11 hours ago
      This was kind of the idea I had behind pcapsql[1]

      We end up having to do a bunch of pcap analysis at work, and rather than having to write a bunch of one off python scripts, a colleague had expressed that if we could just use sql, we could more easily add/share various checks analysis etc, and we’ve built up a little library of easily shareable SQL statements That, and adding the ability to join with other data sources via DuckDB has been a fun project.

      Thing is - LLMs are really very good now, and there is always the temptation to just throw it the pcap file and say “find the problem” (as long as tokens are cheap).

      [1] https://github.com/mtottenh/pcapsql

    • subscribed 20 hours ago
      Same here. Another upside is that I have a common "library" of the solved problems (ie: tools), my sessions / project reuse. It dramatically improves the perceived results and quality (I get to what I need in a fraction of the time it took me on the beginning)
  • amanverasia 14 hours ago
    I created something similar, incase anyone wants to check it out. No login page.

    https://github.com/amanverasia/estudely-packet-explorer

  • tuckerpo 22 hours ago
    Neat! My team and I at CableLabs did something very similar, but with more of a PNM and reactive self-fix angle. [1] [2]

    We demoed it to the CEOs and CTOs of the world's largest broadband companies and unfortunately it never caught traction.

    [1] https://www.cablelabs.com/wp-content/uploads/2025/03/62200_P...

    [2] https://www.cablelabs.com/blog/netllm-handy-automated-networ...

    • dolmen 13 hours ago
      AI on the gateway?

      What about malware impersonating the user and installing a persistent backdoor or spy on the network?

  • rkagerer 18 hours ago
    I'm confused what is divulged if you use the AI feature. Does it perform bidirectional redaction of sensitive portions of captures (IP's, MAC's, data, etc)?
  • hallucinate 19 hours ago
    Another tool that solves that issue that I found: https://packetsnitch.com/
  • SilentM68 18 hours ago
    Can an uv environment be used in a similar way to install and use the app if docker is not chosen?
  • TZubiri 21 hours ago
    Unclear what problem this solves
    • ba1afd89f34cb23 20 hours ago
      I guess it is if you haven’t worked with this sort of thing before

      pcap is a file format for packer captures. You can use tools to capture copies of all packets traversing a network interface, both on clients and servers running operating systems like Linux and Windows, and on network switches and routers that support this (at a minimum, with enterprise gear you can at least send a copy of all traffic from specific source and destination interfaces in both receive and transmit directions to other interfaces you connect a “sniffer” to that you then run a pcap capture on, or you can often even encapsulate the copied traffic in GRE tunnel payloads and send them directly to a remote sniffer).

      This is a local web app that uses Python libraries to analyze these capture files and look for common tell tale signs of specific issues, such as a TCP connection being opened and being immediately reset, which is an excellent way to find firewalls in the path that are denying connections. You can also, providing an API key, send the capture and analysis result to an LLM to discuss things further.

      A sufficiently talented network engineer can do this by hand, but can save time with this tool. End users that aren’t capable of interpreting the capture due to lack of knowledge of underlying network protocols can also get results this way without escalation.

      • Hikikomori 12 hours ago
        Firewalls generally dont sent a rst when blocking syn, they just silently drop it.
        • ba1afd89f34cb23 11 hours ago
          Disagree. This is configuration dependent, and generally enterprise firewalls send a reset to quickly close the connection and letting the client know about that instead of retrying assumed lost SYNs.

          Palo Alto and Cisco firewalls reset by default (you can, of course, change that). Linux will if you REJECT instead of DROP.

          You may be configuring to silently drop, but many people don’t.

          Either way, the point wasn’t that you can find all firewalls that way, but that this tool purports to be able to tell you quickly when this behavior does occur.

          • cenamus 10 hours ago
            Anecdotal, but I had the same experience debugging some incorrect firewall configs at work.
          • Hikikomori 10 hours ago
            You can, but why would you. It's a DoS vector as it takes more resources to respond.
            • yardstick 7 hours ago
              In cases I’ve seen, normally Internet-origin traffic is silently dropped, but blocked traffic from the local network will get a tcp reset or ICMP unreachable.

              A local client trying to DoS the local firewall has a lot better options than trying to overload it sending rejects.

      • TZubiri 19 hours ago
        >pcap is a file format for packer

        I've worked with pcap through tcpdump and wireshark before.

        >This is a local web app that uses Python libraries to analyze these capture files and look for common tell tale signs of specific issues

        The problem is that your 'problem' is that it's an app to find problems. So you are just kicking the can down the road of defining your problem. You present a specific example though:

        >such as a TCP connection being opened and being immediately reset, which is an excellent way to find firewalls in the path that are denying connections

        So the customer has a specific problem they are trying to debug and that's when they use your tool? It's not like a proactive scan of issues?

        I guess I see it, but I don't get why someone's AI Agent wouldn't just run 'apt install tcpdump' or 'winget install wireshark-cli' and run the commands themselves and interpret it.

        Consider evaluating an MCP or a Skill file, the UX is like a plugin in the user's existing trusted LLM software, instead of downloading a separate tool to find the problem. I'm just having trouble imagining how someone ends up downloading this otherwise.

        • ba1afd89f34cb23 11 hours ago
          It’s not my tool. I have nothing to do with its development and have never used it. You posted a statement of not understanding what this is for, with no indication of your knowledge level around the problem, so I tried to help.

          This is a local tool so you don’t ship full payloads to an LLM that, depending on the license level of your key, will be used for training. These payloads will contain what at least some companies will consider sensitive information just in packet headers, let alone potential clear text.

          • TZubiri 3 hours ago
            tinhoil hat off, tcpdump will capture headers, content will be encrypted, assume headers are public because they are. it’s not a secret, Kerchoff it

            second, both tools use LLMs apparently, one uses LLMs better or in a safer manner? see above, it’s already safe

  • Agataproximadev 1 hour ago
    [flagged]
  • sebaandrada 6 hours ago
    [flagged]
  • emer_sec 14 hours ago
    [flagged]
  • ironmagma 12 hours ago
    Who needs a problem detector when you've got a wife?