OpenWorker Adds Built-In Security Agents — Andrew Ng's Open-Source AI Coworker Bets on Model Independence Over Vendor Lock-In
After our initial release, many users found it especially useful for cybersecurity. Attackers are already using AI; OpenWorker is committed to giving defenders the same leverage. Running an agent requires both (i) A model and (ii) A harness (the software around the model). Because the OpenWorker harness is fully open source, security teams can audit it to make sure we haven't built any backdoors that exfiltrate your code and data to some company or even a foreign adversary.
OpenWorker now comes with built-in cybersecurity agents for (i) Scanning your code for vulnerabilities. (ii) Scanning dependencies for supply chain injections. (iii) Checking your cloud security configuration for attack surfaces. This enables developers to do much more security work before deployment (part of what's called the "shift left" movement).
You choose the model: you can run open weight models fully locally so sensitive code never leaves your machine. This helps with legitimate security work (like reproducing a known exploit to defend against it) that can trigger refusals in leading closed models. Or use your ChatGPT subscription, or stealth preview models like Ox Alpha, or any model via API key.
Thanks also to all the open source contributors!
Join work with Rohit Prsad so please follow him too to get more frequent updates.
Try it out: https://openworker.com/
Code: https://lnkd.in/gvZYspRv
OpenWorker, the open-source AI agent from Andrew Ng and Rohit Prasad that completes tasks (not just chats) on your machine, has shipped a security-focused update. It now includes built-in agents for: (1) scanning code for vulnerabilities, (2) scanning dependencies for supply-chain risks, and (3) checking cloud configurations for exposed attack surfaces — aimed at "shift-left" security work before deployment.
Because the harness itself is open source, it can be independently audited. Users choose their own model — via local open-weight models (for sensitive/offline work), a ChatGPT subscription, an API key, or currently-free stealth previews like Ox Alpha (since identified by Z.ai as a GLM-5.3-Flash preview). Ng argues this flexibility helps with legitimate defensive security tasks that he says have triggered refusals in some closed-model agent harnesses — a claim from his own account, not independently verified.
Built with Rohit Prasad (correct spelling), on GitHub at github.com/andrewyng/openworker.