CodeMender preview: AI-powered code vulnerability scanning and remediation
Google Cloud is releasing CodeMender, a managed code security agent, in preview. This tool uses AI to scan for and automatically remediate software vulnerabilities, aiming to reduce security risks and speed up remediation. It is designed for security teams and developers working with various programming languages and integrates with CI/CD workflows. Availability is currently in preview, with wider access planned.
- →CodeMender agent offers AI-driven code scanning and remediation
- →Flexible model deployment for optimized scanning performance
- →Automated remediation and exploitability prioritization
- →Integration with existing security workflows and development tools
- →CodeMender integrated into AI Threat Defense
Features (5) ›
- CodeMender agent offers AI-driven code scanning and remediation
CodeMender is a new managed code security agent available in preview, designed to automatically scan software for vulnerabilities and remediate them using AI. It aims to accelerate the process of finding and fixing code flaws, reducing zero-day risks.
- Flexible model deployment for optimized scanning performance
CodeMender supports a multi-model approach, allowing users to choose from various models, including Gemini Enterprise Agent Platform, to optimize for cost, speed, and deep scanning performance. Third-party model options are expected later this year.
- Automated remediation and exploitability prioritization
The agent can automatically generate and test code fixes for verified vulnerabilities, while also prioritizing fixes based on simulated exploitability. This helps reduce manual remediation bottlenecks and focuses resources on the most critical issues.
- Integration with existing security workflows and development tools
CodeMender is built on Google DeepMind's AI research and operates within the secure Agent Platform. It can integrate with CI/CD pipelines, local development environments via a CLI client, and connect to code repositories, working with tools like VS Code.
- CodeMender integrated into AI Threat Defense
When used with AI Threat Defense, CodeMender scans code, enriches findings in the Wiz Security Graph, and triggers AI pentesting to prove exploitability. This integration streamlines the application security lifecycle and remediation process.
Notes (1) ›
- Limited availability for specific models
CodeMender with Gemini 3.5 Flash Cyber will initially be available to a select group of government and trusted partners, with plans to expand access over time. General access to CodeMender is currently in preview.
https://cloud.google.com/blog/products/identity-security/find-and-fix-software-vulnerabilities-with-codemender/
Related releases
- Google Cloud AI Infrastructure and Orchestration Updates - July 2026 Google Cloud Blog ·
- Confidential VMs Expand vCPU Support on C3D/C4D Google Cloud release notes ·
- Google Kubernetes Engine: New versions and deprecations Google Cloud release notes ·
- Datastream adds preview support for Workday replication Google Cloud release notes ·
- Google Cloud CISO Perspectives: AI Threat Defense for Boards Google Cloud Blog ·
- Data Studio Conversational Analytics GA, adds BigQuery integration Google Cloud release notes ·