ADR: Agentic AI Detection and Response
github.com/uber/adr- Category
- Cybersecurity
- Pricing
- Open Source
- Platform
- cli
- Type
- TOOL
- GitHub
- 1.2k stars
- Added
- Aug 6, 2026
About
ADR is an open-source enterprise security system for AI agents that combines telemetry collection (Sensor), a 300+ task benchmark covering 133 MCP servers and 17 attack techniques (ADR-Bench), and a two-tier dual-agent threat detector. It is deployed in production at Uber to monitor and secure both employee-facing coding agents (Cursor, Claude Code, Codex) and customer-facing support agents, with an accompanying paper accepted to MLSys 2026.
Why it made the leaderboard
Agent security is mostly still policy documents; this is a production-proven detection and response layer for the coding agents engineers are already running inside the company.
Tags
ai-agent-securitythreat-detectionmcpprompt-injectionllm-securitybenchmarkuberobservability
Comments (0)
No comments yet
Indexed by a proprietary survey. Corrections welcome.