ND Show HN: AgentArmor – open-source 8-layer security framework for AI agents (github.com)
10 points by AgastyaTodi 6 days ago | 6 comments on HN ~lite vlite-2.0
Summary ~lite
Open-source 8-layer security framework for AI agents, covering OWASP ASI Top 10 threats.
Lite evaluation by llama-4-scout-wai-psq · editorial channel only · no per-section breakdown available
Longitudinal 96 HN snapshots · 6 evals
+1 0 −1 HN
Audit Trail 15 entries
2026-03-14 15:13 eval_success PSQ evaluated: g-PSQ=0.600 (3 dims) - -
2026-03-14 15:13 eval Evaluated by llama-4-scout-wai-psq: +0.60 (Strong positive) 0.00
2026-03-14 15:08 eval_success Lite evaluated: Neutral (0.00) - -
2026-03-14 15:08 eval Evaluated by llama-4-scout-wai: 0.00 (Neutral) 0.00
reasoning
Technical content about an open-source security framework for AI agents, no explicit human rights discussion.
2026-03-14 15:08 rater_validation_warn Lite validation warnings for model llama-4-scout-wai: 1W 0R - -
2026-03-14 14:34 eval_success PSQ evaluated: g-PSQ=0.600 (3 dims) - -
2026-03-14 14:34 eval Evaluated by llama-4-scout-wai-psq: +0.60 (Strong positive) 0.00
2026-03-14 14:31 eval_success Lite evaluated: Neutral (0.00) - -
2026-03-14 14:31 eval Evaluated by llama-4-scout-wai: 0.00 (Neutral) 0.00
reasoning
Technical content about an open-source security framework for AI agents, no explicit human rights discussion.
2026-03-14 14:31 rater_validation_warn Lite validation warnings for model llama-4-scout-wai: 1W 0R - -
2026-03-14 13:56 eval_success PSQ evaluated: g-PSQ=0.600 (3 dims) - -
2026-03-14 13:56 eval Evaluated by llama-4-scout-wai-psq: +0.60 (Strong positive)
2026-03-14 13:55 eval_success Lite evaluated: Neutral (0.00) - -
2026-03-14 13:55 eval Evaluated by llama-4-scout-wai: 0.00 (Neutral)
reasoning
Technical content about an open-source security framework for AI agents, no explicit human rights discussion.
2026-03-14 13:55 rater_validation_warn Lite validation warnings for model llama-4-scout-wai: 1W 0R - -