ADR: Agentic AI Detection & Response Framework

Building or securing AI agents in enterprise environments?

ADR (Agentic AI Detection and Response) is an open-source security framework from Uber designed to monitor, evaluate, and detect security risks in AI agents used by developers and organizations.

Key highlights: • AI agent observability & telemetry collection • Benchmark suite with 300+ security tasks • Detection of risky AI agent behavior • Support for 133 MCP servers • Security evaluation for coding assistants & enterprise agents • Cross-platform support for macOS, Linux & Windows • Reproducible benchmarking & research workflows • Based on the MLSys 2026 research paper

A valuable resource for AI security researchers, security engineers, platform teams, and AI developers working on secure agentic AI systems.

https://github.com/uber/ADR

#GitHub #OpenSource #AISecurity #AgenticAI #LLM #CyberSecurity #MachineLearning #SecurityResearch #MCP #InfoSec

uber/ADR

Source: https://github.com/uber/ADR

ADR: Agentic AI Detection and Response

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.

ADR is deployed in production at Uber, and the accompanying paper was accepted to MLSys 2026: Paper PDF · Slides PDF

How ADR secures enterprise AI agents

ADR secures enterprise AI agents through four complementary capabilities: observing agent activity, evaluating defenses, detecting threats, and preventing unsafe actions.

1. ADR Observability: Understand what AI agents are doing and why. In production, ADR captures agent intent, tool use, and execution traces across 7+ AI coding tools on macOS, Linux, and Windows, as well as internal automation and customer-facing support agents.
2. ADR Benchmark: Test agent security under realistic enterprise conditions. ADR-Bench includes 300+ tasks, 133 MCP servers, and coverage of all 17 agent attack techniques.
3. ADR Detection: Detect risky agent behavior efficiently. Its two-tier architecture combines high-recall triage with deeper agentic reasoning for suspicious sessions.
4. ADR Prevention: Stop unsafe actions before they cause harm. This component is not included in the current open-source release. Stay tuned.

Repository layout

This repository contains the open-source ADR Sensor, ADR-Bench, and ADR Detector described in the paper. The offline ADR Explorer engine, which hardens ADR Detection through pre-deployment red teaming, is not included here.

Quick start: ADR Detection

git clone https://github.com/uber/ADR
cd ADR/Detection
uv sync
export ANTHROPIC_API_KEY="..." OPENAI_API_KEY="..."

Default detector is adr (ADR dual-agent). For keyless smoke tests, use --detector llamafirewall (see Detection/README.md).

See docs/REPRODUCIBILITY.md for the full evaluation workflow (inflate packed benchmark → run detectors → plot figures).

Component documentation:

• Sensor/README.md: telemetry collection and unified schema
• Detection/README.md: ADR-Bench, detector baselines, MCP infrastructure

Citation

@inproceedings{li2026adr,
  title={ADR: An Agentic Detection System for Enterprise Agentic AI Security},
  author={Li, Chenning and Hu, Pan and Xu, Justin and Ozbas, Baris and Liu, Olivia and Van, Caroline and Li, Manxue and Zhou, Wei and Alizadeh, Mohammad and Zhang, Pengyu and Sriramadhesikan, KK and Zhang, Ming},
  booktitle={Proceedings of the Ninth Conference on Machine Learning and Systems},
  year={2026}
}

Or use CITATION.cff.

License

Apache License 2.0. See LICENSE. Detection/benchmark/agentdojo/ is vendored third-party code under its own LICENSE (MIT).

Data notice

Detection/ includes synthetic benchmark fixtures (fake credentials, emulated environments, prompt-injection scenarios) for defensive security research only. Details: docs/OPEN_SOURCE_REVIEW.md.