agi-jev-containment

A HackSpain 2026 hackathon project that monitors sandboxed LLM agents for malicious behavior by classifying whole chains of actions rather than single tool calls, combining Jev with a rules engine for chain-level detection, an escalate-only five-level containment response, Neo4j-backed forensics, and a live dashboard — deliberately built so no automated system can pull the plug itself.

unverified — sourced from awesomejev.com; description independently written by AionEdge from the repo’s own GitHub metadata and README, not GitHub-API relevance-checked