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
DocsAlot
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
Premarket Bell
I’m curious how much context Harden looks at before making a security decision. Does it consider the whole session or mainly the current request?
Harden
@daniel_henry4 Hi Daniel, thank you for the question. Harden AIF looks beyond just the current request. It evaluates the pending tool call against the developer's intent and the relevant session history, especially earlier events that can change what the action really means. Hope that answers your question. I'm happy to answer any other question as well.
Harden
@hamza_afzal_butt Great question, but it totally depends on the device that you are on, for example on an M5 Pro, The p50 latency is about 2 seconds and p95 latency is about 3.4 seconds. However, this is one thing which we are working on actively right now to push the latency below 500ms.
Really cool approach to agent security. Love that the checks happen locally while still being powerful enough to catch risky tool calls.
Harden
@harsh_rathore10 Thanks, Harsh. Really glad you like the approach and that it resonated with you. Also, really good DP :)
Security usually gets added after something goes wrong. Building it directly around agent actions feels like a much better approach.
Harden
@subhash_kanagamani Very much indeed Subhash! I hope you try our product out!
Harden
@subhash_kanagamani Totally agreed with you, Subhash, and that is exactly why we built Harden.
This is such an interesting problem to solve. We’re giving agents more autonomy every month, so the security layer has to catch up too
Harden
@prakhar_gupta44 Yeah, exactly. As agents get more dominance, the security has to speed up, but now Harden has got your back, and it is free for individual developers. You can just set it up in a single command. If you hit any issue while setting up, just book a call with us. Our team would be more than happy to help you out
Paste
"Babysitting caps how much work you can hand off" is such a clean way to put it. I also like that it all stays local, a tool that reads every command is exactly the thing you don't want phoning home. Does the model learn anything from what you approve or reject over time?
Harden
@protsenkoalexandra As of now the model doesn't learn locally but this is a feature that we are working on - based on your long term approve / reject pattern, AIF will be able to actively adapt itself to ensure it runs in the way you expect it to.
Paste
@rishav99 cool :)
Does the protection and noticeable delay before tool calls or can developers use it smoothly during fast coding sessions?
Harden
@haolin Thanks for the question, Hao. Harden runs the security checks locally on your system, so it’s designed to work smoothly even during fast coding sessions without relying on a second remote model for every action. Hope this answers your question and we are happy to answer any other questions you might have.
Harden
@iamhetpatel Thanks, Het. Great question. That number matters a lot for something that sits on every tool call. We specifically train and evaluate Harden model to keep false positives low. For example, our SLEIGHT evaluation reports TPR at a ≤1% false-positive rate, and LinuxArena is also measured at a 1% step-wise FPR target.
I would love to hear how it behaves in your daily sessions and how many tool calls it ends up blocking for you. You can also refer to this article for more details on the benchmarks and evaluation setup: https://harden.run/blog/aif-research-and-evidence
And of course, happy to answer any other questions you might have.