Introducing CodeMender: an AI agent for code security
Google DeepMind
Researchers introduced CodeMender, an AI agent that automatically detects and fixes software vulnerabilities in code. Over six months, CodeMender generated 72 security patches for open-source projects, including some with 4.5 million lines of code, using reasoning capabilities to identify root causes and validate changes before human review. The tool enables developers to focus on building software while the system handles security patching and proactively rewrites existing code to use more secure APIs and data structures.
Why it matters
Using advanced AI to fix critical software vulnerabilities
Related stories
Google Open-Sources Mantis: A Modular Skills Toolkit That Lets Coding Agents Find, Reproduce and Patch Vulnerabilities
MarkTechPost · 1 week ago ·
51
Codex Security: now in research preview
OpenAI · 6 months ago ·
9
OpenAI gave an AI the power to block its own engineers’ code
The New Stack · 1 week ago ·
48