HOL Guard is the firewall for AI agents. It sits between agents and your systems, blocking high-risk actions before they happen like deleting production data to exposing secrets. Built by HOL, it’s free, open source, and already has 400K+ downloads.
I’m Michael Kantor, President of HOL. We’re an open standards consortium for AI agents, with 20+ specifications contributed through LF Decentralized Trust and more than 37M transactions powered by our work.
For the past two years, we’ve been thinking about what happens when billions of autonomous agents are transacting, installing tools, accessing systems, and exchanging information. As we used AI more deeply inside HOL, we saw agents attempt to bypass safeguards, access secrets, and send data they should never have been able to reach.
We originally built HOL Guard to protect our own systems. Once we realized how widespread the problem was, we open-sourced it and started building it for everyone.
HOL Guard uses open standards and hundreds of security heuristics to protect agents from malicious packages, prompt injection, secret exfiltration, and catastrophic actions such as deleting a production database or filesystem. GPT-5.6 was also a valuable partner in building adversarial tests and hardening the product.
We’d love for you to try it, break it, and tell us what we should improve. Thank you for supporting open-source AI security.
firewall for agents is exactly whats missing rn 🔒 congrats on the launch!
We've been using HOL standards for quite some time, especially HCS. With this new exciting release we downloaded immediately. This proves to be invaluable tool for any AI agent in your backend/on-chain flow.
@kantorcodes congrats on the launch - keen to give this a crack with our team as we push more agents into our workflows. The balanced policy approach looks to be exactly what we need to avoid approval fatigue.
We’re excited about where AI agents are headed but as they become more autonomous, we think developers need better ways to stay in control without sacrificing speed. Our goal with HOL Guard is simple: make it easy to let AI do more while ensuring sensitive actions are reviewed or blocked when they should be.
We’re always building and would genuinely love your feedback. If you’re working with AI agents, what kinds of actions would you want an AI firewall to monitor, pause, or automatically block? We’d love to hear your thoughts!
Incredible work, I'll be setting this up in my environment today. My security concerns have been growing as I start relying on autonomous workflows more and more, so this feels like a solid step.
I like that this sits before the agent acts, not after logs are reviewed. The thing I would want to debug quickly is a blocked action: exact tool call, matched rule, risky input/output, and whether it was policy or model uncertainty. Is that visible in the product?
Many of security heuristics is a lot of surface area to keep accurate over time, and heuristic based detection tends to have a specific failure mode, it either misses a genuinely dangerous action that just does not match a known pattern, or it gets so cautious that agents start getting blocked on legitimate work. With something as high stakes as approving or blocking a database delete, which side do you tune toward when a new kind of action does not clearly match anything in the existing heuristic set.
Also curious how GPT-5.6 fits into it beyond building adversarial tests during development. Is there any live model reasoning happening at the moment an action gets evaluated, or is the actual runtime blocking purely heuristic and rule based once it ships, with the model only having been used to help design and harden those rules beforehand.
heuristics cutting both ways is my worry here. a firewall that's too strict on false positives trains developers to just approve everything without reading the prompt, which is worse than not having it at all. do you have real numbers yet on false positive rate at 400k downloads, or is that still mostly theoretical since it just launched
About HOL Guard on Product Hunt
“The 1st Firewall for AI Agents”
HOL Guard launched on Product Hunt on July 23rd, 2026 and earned 106 upvotes and 18 comments, placing #18 on the daily leaderboard. HOL Guard is the firewall for AI agents. It sits between agents and your systems, blocking high-risk actions before they happen like deleting production data to exposing secrets. Built by HOL, it’s free, open source, and already has 400K+ downloads.
HOL Guard was featured in Developer Tools (516.3k followers), Artificial Intelligence (474.3k followers), GitHub (41.3k followers), Security (2.8k followers) and OpenAI Day (9 followers) on Product Hunt. Together, these topics include over 217.1k products, making this a competitive space to launch in.
Who hunted HOL Guard?
HOL Guard was hunted by Michael Kantor. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how HOL Guard stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Michael Kantor
Hi Product Hunt
I’m Michael Kantor, President of HOL. We’re an open standards consortium for AI agents, with 20+ specifications contributed through LF Decentralized Trust and more than 37M transactions powered by our work.
For the past two years, we’ve been thinking about what happens when billions of autonomous agents are transacting, installing tools, accessing systems, and exchanging information. As we used AI more deeply inside HOL, we saw agents attempt to bypass safeguards, access secrets, and send data they should never have been able to reach.
We originally built HOL Guard to protect our own systems. Once we realized how widespread the problem was, we open-sourced it and started building it for everyone.
HOL Guard uses open standards and hundreds of security heuristics to protect agents from malicious packages, prompt injection, secret exfiltration, and catastrophic actions such as deleting a production database or filesystem. GPT-5.6 was also a valuable partner in building adversarial tests and hardening the product.
We’d love for you to try it, break it, and tell us what we should improve. Thank you for supporting open-source AI security.