Uber's enterprise security system for AI coding agents, covering observability, security benchmarking and threat detection.
ADR helps companies see and secure what employee-facing agents like Cursor, Claude Code and Codex actually do. It captures agent intent, tool use and execution traces, and flags threats.
Start with the README and the paper, then deploy the observability part on a small team first.
Strix · Agent
Open-source AI penetration testers that run your app, find vulnerabilities and prove each one with a working exploit.
Keygraph · Agent
An autonomous AI pentester for web apps and APIs that only reports the vulnerabilities it can prove with a working exploit.
NVIDIA · Tool / CLI
NVIDIA's security scanner for agent skills that finds vulnerabilities, prompt injection and malicious patterns before you install a skill.