Endor Labs launches free tool AURI after study finds only 10% of AI-generated code is secure

Endor Labs, the application security startup with over $208 million in venture funding, has launched AURI, a platform that incorporates real-time security intelligence directly into AI coding tools. AURI is available for free to individual developers and integrates with popular AI coding assistants such as Cursor, Claude, and Augment through the Model Context Protocol.

The announcement comes amidst a concerning finding that leading AI coding models only produce functionally correct and secure code about 10% of the time. Endor Labs CEO Varun Badhwar highlighted the importance of addressing this gap between functional code and secure code.

AURI’s core technical differentiator is its “code context graph,” which provides a detailed map of how different components in an application are interconnected. This allows AURI to trace vulnerabilities through every layer of an application, providing a more comprehensive analysis compared to traditional scanning tools.

The platform combines deterministic analysis with agentic AI reasoning to automatically detect and remediate vulnerabilities. Endor Labs’ approach aims to reduce security findings for enterprise customers by 80% to 95%, saving significant developer productivity lost to investigating false positives.

Endor Labs offers a free tier for individual developers and a paid platform for enterprises, with features like full customization, role-based access control, and integration with CI/CD pipelines. The company’s freemium approach aims to drive rapid adoption among developers before expanding into organizations.

Independence from AI coding tools is a key principle for Endor Labs, as it believes security review should be separate from code generation tools. AURI’s approach combines the strengths of LLMs with deterministic tools to provide consistent and verifiable security findings.

Endor Labs has already demonstrated AURI’s capabilities by identifying zero-day vulnerabilities in popular AI assistants and detecting active malware campaigns. The company’s recent funding round and rapid growth indicate strong market demand for its platform.

The broader question raised by AURI’s launch is whether security tooling can keep pace with AI-driven development. Endor Labs’ optimistic view is that AI agents can help solve longstanding security challenges by executing the right instructions with the right intelligence.

In a world where machines are writing code faster than humans can review it, solutions like AURI are essential to ensure that software development remains secure and efficient.