AgentGuard
Shares rank 2 of 5 agent firewalls by recommenders
Open-source runtime security layer for AI agents that scans skills before they run and blocks dangerous actions. One critic calls it a no-go under the EU AI Act.
Open-source runtime security layer for AI agents that scans skills before they run and blocks dangerous actions. One critic calls it a no-go under the EU AI Act.
6 people gave an opinion
- recommend it
- 5
- criticize it
- 1
- approval share
- 83%
Recommended in 1 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 5 people recommend itNeeds 10 or more, not met.
- 5 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 1 of 13 monthsNeeds 4 or more, not met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Enforces at runtime, not just tracking
“built this because I kept hitting the same problem: classification tools assess risk once, governance dashboards track inventory, but nothing enforces compliance at runtime”
Comment from 9 Feb 2026 in “Open-source EU AI Act compliance middleware” “auto-scans skills before they run (24 detection rules), blocks dangerous runtime actions”
Comment from 5 Feb 2026 in “Show HN: AgentGuard – Open-source security layer for AI agents and skills” Fills a gap in existing tools
“built this because I kept hitting the same problem: classification tools assess risk once, governance dashboards track inventory, but nothing enforces compliance at runtime”
Comment from 9 Feb 2026 in “Open-source EU AI Act compliance middleware” “fills a real gap for agent ecosystems”
Comment from 6 Feb 2026 in “Show HN: AgentGuard – Open-source security layer for AI agents and skills”
Other agent firewalls people recommend
The four most recommended other agent firewalls, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Claw Patrol | 8 | 0 | 100% | 1 | — | — |
| AgentGuardThis page | 5 | 1 | 83% | 1 | — | — |
| FireClaw | 5 | 0 | 100% | 2 | — | — |
| AgentGate | 5 | 0 | 100% | 2 | — | — |
| AgentArmor | 5 | 0 | 100% | 2 | — | — |
What people said
All 6 comments that mention it, newest first. Each links to the original comment.
“a direct no-go under the act”
“built this because I kept hitting the same problem: classification tools assess risk once, governance dashboards track inventory, but nothing enforces compliance at runtime”
“The perfect combination of AI and security”
“treating agent security as a protocol problem, not an afterthought”
“fills a real gap for agent ecosystems”
“auto-scans skills before they run (24 detection rules), blocks dangerous runtime actions”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.