Microsoft releases RAMPART and Clarity as open source to improve AI agent safety engineering. RAMPART turns red-team findings into repeatable AI safety tests for CI pipelines. Clarity helps developers ...

Microsoft on Tuesday took the wraps off Adaptive Spec-driven Scoring for Evaluation and Regression Testing, an open-source framework for spinning up AI evaluations.

Evaluate the effectiveness of Microsoft’s Python Risk Identification Toolkit (PyRIT) for agentic AI red teaming. Address evolving autonomous AI system threats.

Just two months ago, researchers at the Data Intelligence Lab at the University of Hong Kong introduced CLI-Anything, a new state-of-the-art tool that analyzes any repo’s source code and generates a ...

Lehigh University researchers have built the first "AI for Science" software tool designed to support the entire project workflow for research scientists. Dr. Claw is an open-source, full-stack AI ...

NVIDIA introduced Agent Toolkit, an open source package for building and running enterprise AI agents, including a new runtime called OpenShell that the company says adds policy-based security, ...

Nvidia's reported platform will allow companies to dispatch AI agents to perform tasks for their own employees. The platform is expected to include security and privacy tools. The report comes as ...

Microsoft has open-sourced two new tools aimed at bringing AI safety checks much earlier into the agent development lifecycle. The tools, called Rampart and Clarity, were announced this week as part ...

Microsoft open-sources RAMPART and Clarity to improve AI agent safety engineering. RAMPART turns red-team findings into repeatable AI safety tests for CI pipelines. Clarity helps developers validate ...