> ## Content Index
> Fetch the complete content index at: https://www.anup.io/llms.txt
> Use this file to discover other available public pages before exploring further.

# AI Agents Are Finally Fixing Real-World Code Security Problems
- URL: https://www.anup.io/ai-agents-are-finally-fixing-real-world-code-security-problems/
- Published: 2025-10-09T06:20:21.000Z
- Updated: 2025-10-09T06:20:21.000Z
- Author: Anup Jadhav
- Tags: #til, Gemini, CodeMender, DeepMind

I came across something genuinely interesting in code security this week: DeepMind’s **CodeMender**, an AI agent that doesn’t just flag vulnerabilities but actually fixes them and upstreams the patches to major open-source projects. Codemender leverages the "thinking" capabilities of [Gemini Deep Think models](https://blog.google/products/gemini/gemini-2-5-deep-think/?ref=anup.io) to produce *autonomous* agent that is capable of debugging and fixing complex bugs and vulnerabilities.

![](https://storage.ghost.io/c/b1/a4/b1a432f8-3f63-4839-8020-97b63b6056f7/content/images/2025/10/CleanShot-2025-10-09-at-07.17.20.png)

It’s already contributed dozens of security improvements across large codebases, reasoning about root causes and rewriting risky patterns rather than applying quick patches.

What I like about this is how agentic the setup is. CodeMender uses a coordinated multi-agent system powered by **Gemini**, combining vulnerability detection, static analysis, patch validation, and **code rewriting**. It’s not just reactive either. For example, it’s been adding **\-fbounds-safety** annotations to **libwebp** to proactively reduce entire classes of bugs. For anyone working on secure automation or agent protocols, this feels like a practical step forward.

👉🏽 [Read the full post](https://deepmind.google/discover/blog/introducing-codemender-an-ai-agent-for-code-security/?ref=anup.io)