Show HN: Wispbit - Linter for AI coding agents

(wispbit.com)

29 points | by dearilos 16 hours ago

3 comments

  • tptacek 15 hours ago
    SOC2 is definitely not the highest industry standard for security (also: save yourself some money: nobody cares if you have availability attested).
    • winstonp 15 hours ago
      when I did startups, we had multiple companies who would not sign deals until our SOC2 was complete
      • tptacek 14 hours ago
        I don't want to do a whole thread about SOC2 here, just wanted to snipe at a bit of marketing messaging. :)

        For their market maybe that line works fine. It just trips a security cool kid tripwire.

    • dearilos 15 hours ago
      Love it :) Thank you!
  • handfuloflight 15 hours ago
    Pricing?
    • dearilos 15 hours ago
      We do a two week trial and then it's $0.2 per file reviewed. Buying in bulk + optimizing rules gives a significant discount.
      • CuriouslyC 14 hours ago
        Does this produce actual lint rules, or are you templating out lint-like replies from a LLM using a response format?

        If you're doing inference, just give me a cli that's userless and free. I'm happy to use left over codex plan tokens or gemini free tokens for this, and while the idea seems interesting and I might be upsellable to more features down the line, the price/offering is a non starter.

        • dearilos 14 hours ago
          We combine determinism + LLMs to catch things a human would normally have to. If the LLM finds a violation, it generates a comment.

          Big agree on the CLI being open and letting you bring your own inference provider. We’re holding off on it until we get more feedback from some of our hardcore users.

          • hdjrudni 9 hours ago
            What are you using for "determinism"? Sounds to me like you might just be running eslint + et al and then charging a fee for it.
            • dearilos 9 hours ago
              We use ast-grep for the determinism part. I should have clarified - we don’t charge for fully deterministic runs. Only ones where the LLM is involved as a judge.
          • codyswann 10 hours ago
            Is that a "yes" on lint rules? AI needs determinism to block commits because once the slop hits code review, it's already a gigantic waste of time. AI needs self-correcting loops.
            • dearilos 9 hours ago
              It supports fully deterministic rules, which we use LLMs to help you write.

              Agreed on all of this too. This is why we built the CLI tool - to shift left the work.

  • vmesel 14 hours ago
    congrats on the work Ilya and Nikita! It was nice talking to you, all success to you guys!