Harden - A security layer for AI coding agents
by•
Harden AIF is a free, local security tool for AI coding agents. Its post-trained model checks tool calls before they run, using your request and session context. It beat frontier models on key agent-security benchmarks, while keeping your repo and tool output on your machine.
Replies
congrats on the launch!! 👍 funny timing, i backed out of a third-party agent skill yesterday, bacause it runs npx in my repo and who knows what it touches.
local check-before-it-runs is exactly the thing! does it cover the install step, or just runtime?
@seenew Great timing 😄 and yes, that’s exactly the kind of thing Harden is meant for.
It can cover the install step too, as long as that action goes through the agent/tool flow Harden is monitoring. So something like an agent trying to run npx in your repo can be checked before it executes, not just after the package is already installed.
And thanks a ton for supporting the launch, Shinyoo 🙌
can finally run my coding agent in YOLO mode and walk away. AIF checks what it is doing and stops things that could go wrong, so I don't have to babysit it.
@anurag_arora6 Exactly. The goal is simple: we just want people to say that I trust my agent.
@rukhsar_amjad Yes, definitely do try it. It is completely free, installs in seconds, and watches your agents 24/7 so that you don't have to.
So I am having similar issues, But I have my own rule sets in Molt Code, Do you have some Client Server model rather than invasive one ?
@junaid1460 As of now, no. But we do plan to ship a feature like that. Do let use know if you want something more!
Companies have always had risk and compliance as separate functions from product and business development because their incentives are at odds. Risk team looks at risk adjusted long term reward, but biz-dev indexes on shorter term rewards. In a similar way, the same system can't both be the coding agent, and the security agent. That's why Harden is needed
@pushpendre_rastogi That separation is really at the heart of Harden, letting the coding agent focus on getting the job done while Harden independently handles the security boundaries. Great analogy, Pushpendre
We built Harden after seeing how difficult it is to control what AI agents can access and do. As users ourselves, we wanted a simpler way to set policies, monitor activity, and deploy agents confidently.
@ankitatproducthunt Exactly why we built Harden. Excited to see it finally in users’ hands
@priyankamandal Oh for sure! DevOps is still one of the most cubersome of areas which can benefit the most from a secure autonomous agent.
Congratulations 🎉
this is actually really great.
Congratulations on the launch. Very cool. This is very timely. Would be curious to understand the common gotchas and security holes it catches. Exciting