agi-jev-containment
AGI JEV Detection — local AI agent monitor: chain-level malicious-agent detection (TypeSafe Jev + Sentinel), escalate-only L1–L5 containment, Neo4j forensics, AngryRobot dashboard. HackSpain 2026.
How it uses Jev
Also searchable as: agent security monitor , LLM agent kill-switch , Jev / Sentinel / SafetyDrift pipeline , sandbox containment ladder (L1–L5) . GitHub repo today: hack-spain-2026 . Proposed rename: agi-jev-detection .
- Languages
- Python 79% · TypeScript 13% · HTML 4% · CSS 2%
- Last activity
- Sep 2026
- Added
- 2026-09-21
- Stars at snapshot
- 4
- Status
- Community listing
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.