Launching today
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.
Mastra
absolute fan of @davidmytton's work with @Console and @Arcjet.
Their new agent runtime security platform is a must-have for engineering teams to enforce policy the moment an AI agent acts, and keep the evidence to prove what happened and why. Detect prompt injection, authorize agent tool calls, block bots and abuse. It's available now.
Start for free with this prompt or follow the quickstart to protect your first agent tool and LLM calls:
Curious to know what the community thinks about security these days.
Congrats on the launch! How out-of-the-box is the implementation and later use?
Arcjet
Arcjet
@denis_prodan You can implement Arcjet manually - we have language SDKs e.g. JS, Python, Go, as well as direct integrations to AI agent frameworks like Eve, Mastra, LangChain, Google ADK, Claude Managed Agents. But most of our users just install the skill with `npx skills add arcjet/skills` and have their agent implement it!
Is that focused on end users abusing the agent or on agents themselves getting tricked into abusive loops?
Arcjet
Arcjet
@simonclark55 Arcjet can protect both sides - bot detection for web requests like chat UIs, and then tool guards, PII leak detection, and indirect prompt injection detection within the agent workflow (where there is often no web request).
Does it add much latency when you check for prompt injection before every action?
Mastra
@manonbriffaut good question. it adds approximately 100 ms of latency to requests, according to their docs.
Arcjet
@manonbriffaut It depends on the policies you have configured. We run our own models for prompt injection detection so that can take around 100ms to complete the analysis, but for PII detection the p50 is 6ms, and for tool guards it's less than 1ms.
nenspace
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
Arcjet
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.
Mastra
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?
Arcjet
@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.
The GTM Co-Founder
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!
Mastra
@gtmnerd S/O for this launch! Keep up the great work, and keep launching
Arcjet
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.