Arcjet is the runtime security platform that ships in your AI code. Detect prompt injection, authorize agent tool calls, redact sensitive data, and block bots and abuse. Real-time security building blocks you call inside your app, before an action happens.
Launch Team
Floot MCPBuild and ship web and mobile apps inside Claude or ChatGPT
Promoted
any volume increase in security breach attempts you've seen recently and how are you solving them? how do you see runtime security platforms keeping pace?
congrats on the launch! been following you guys for a while love what you're doing
@samsmallmind The biggest challenge I'm hearing from security leaders is how quickly agents are being deployed, and without any visibility from security teams. Going from 30 to 3000 agents within a month is one example - at that volume, there's no way for security teams to keep up unless "security" can be built into agent code from the beginning. That's why I think Arcjet has an interesting advantage because of our native SDKs and AI agent framework integrations.
We split the responsibility so engineers provide the inputs and wrap their agent flows with Arcjet's SDK. Then the security team can independently manage the policies. That prevents one team becoming the bottleneck and allows security teams to work with engineering, rather than blocking them.
@samsmallmind thanks for your continuous support, Sam!
I am curious how much more secure this actually makes an AI agent in practice
@noureldin_ehab Arcjet gives you the tools to set up your own policies so you can set up the right level of protections for each agent.
Is there potential for users to accidentally submit PII, like in a support form and medical context? Arcjet can help detect and block.
Does the agent accept user prompts or read from third party sources that could inject attacks? Indirect prompt injection through GitHub issue bodies or website content can be detected through Arcjet's prompt injection protection.
And if the agent calls any tools, the inputs are decided by the agent at runtime. Tool guards add constraints to tools and APIs so they're only called with the expected values.
It really depends on what the agent is doing and where it gets its inputs.
@noureldin_ehab thanks for the support! curious how did you handle security at @Stakpak?
This is an amazing product, and we are extremely happy customers at @Creem !
Congrats on the launch guys, any plans to also expand the product towards image and video output moderation?
Thanks@sudoferraz - it's been great working with you and the @Creem team! We're working on own fine-tuned internal models for content moderation and other security analysis, which will include multi-modal video and image content moderation, so hope to have something to share with you soon!
@sudoferraz wow! please add your review here, that would mean the world: https://www.producthunt.com/products/arcjet/reviews
Hey Product Hunt, Cassie here from @Arcjet!
When AI was just a chatbot, the worst thing it could do was be wrong. That's no longer where the risk sits. Agents now read and write to databases, resolve support tickets and move money, and they are set off by an inbox, a text message or a code commit rather than someone typing into a chat box.
Today, we're announcing Agent Runtime Security. It gives engineering teams enforcement at the moment an agent acts, and it gives security teams the evidence to prove afterwards what happened and why. It's available now with a 15-day free trial: https://arcjet.com/
Over to you! Ask us anything, challenge us, tell us what you think about security in this AI era. We're here all day.
S/O for the great work, Cassie!
@Arcjet is securing production workflows at companies like @Creem - what do they really enjoy about the product from your perspective?
@fmerian Working with @Creem has been great. They're growing quickly and focused on their core product, so we take on the security side of things. You can definitely build some basic prompt injection detection using open source models, but keeping them up to date with new techniques and models requires a lot of time and effort. Security isn't a one-time thing because techniques and attacks are always changing. That's what Arcjet does.
@fmerian @davidmytton We are super happy with Arcjet!
It completely removes the effort needed from our side to keep improving our moderation product, Arcjet simply does it all for us!
@davidmytton @sudoferraz framing this!
So happy to see this go live, and delighted to be part of the launch. The team have put in a serious body of work over the last few months to get here.
Governing agents at the code level is something most companies still aren't doing, and it's exactly where the real risk sits.
As David put it: "The code is where the context is, so you can make security decisions at machine speed."
Let's go!
@gtmnerd S/O for this launch! Keep up the great work, and keep launching
Thanks @gtmnerd ! Security has moved into the action boundary because agent behavior can change throughout the flow. We see Arcjet being called to evaluate actions multiple times during the agent workflow: before and after LLM calls, before and after API/database calls, and to guard risky actions. That's quite a different security model than inspecting network packets at the gateway.
Congrats on your PH launch! I personally faced some security issues, and this seems to be a perfect solution.
Thanks!
Thanks@kunalukey ! What kind of security issues have you seen?
@kunalukey thanks for the support! security isn't an afterthought anymore.
start for free with this prompt or follow the quickstart:
enjoy!
This looks really interesting! Congrats on the launch. I'm excited to try this out and see how it works.
@rahilpirani amazing Rahil! looking forward to your feedback, make sure to add your review here: https://www.producthunt.com/products/arcjet/reviews
@rahilpirani anything in particular you'd expect from your first-time experience using @Arcjet?
@rahilpirani Let me know how you get on!