Uber open-sources ADR: enterprise AI agent security and threat detection framework
uber · github · 2026-08-04
Uber has open-sourced ADR, its internally deployed AI agent security project. The framework targets enterprise AI agents, providing observability, security benchmarking, and threat detection. It specifically defends against LLM security risks like prompt injection and is compatible with mainstream models and protocols like Claude, Codex, Cursor, and MCP.
Related event: Uber Open-Sources ADR Framework for AI Agent Security(3 posts)→
More from coding & agent
- Don't Be Fooled by Agent Parallelism: Core Business Problems Still Need Deep Focus — yacineMTB · 2026-08-04
- Vibe Coding a Social Listening Tool with 2 Prompts: $10/mo vs $100/mo SaaS — ayushtweetshere · 2026-08-04
- The Illusion of Productivity: Why Parallel Agents Can't Solve Core Business Problems — aryanXmahajan · 2026-08-04
- OpenWiki: The Self-Maintaining Context Layer for AI Agents — blaizedsouza · 2026-08-04
- LokalBot: A Fully Local macOS AI Work Assistant — stevyhacker · 2026-08-04
- 13 Lessons from Building Enterprise AI Agents: Self-built ETL Cuts Costs 20x — redouanea · 2026-08-04