Tag

llm-security

Oldest Newest URL A-Z URL Z-A Title A-Z Title Z-A Random
Agent-Safe Pipeline
https://github.com/decionis/agent-safe-pipeline

Reference architecture for AI agents that propose actions but cannot authorize them — immutable intent capture, an independent Decionis policy verdict (ALLOW/ESCALATE/BLOCK), verified human approval, and a SafeExecutor that consumes a single-use intent-bound grant.

 
ai-agent apache2-licensed llm-security open-source security
Added 1 month ago
ADR: Agentic AI Detection and Response
https://github.com/uber/ADR

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

ADR (Agentic AI Detection and Response) is an enterprise security system for AI agents. It helps organizations secure employee-facing agents such as Cursor, Claude Code, and Codex, as well as customer-facing agents such as AI support agents.

 
agent-firewall ai ai-security apache2-licensed firewall foss llm-security open-source security
Added 1 month ago