by Z.ai
Free Hugging Face Space from Z.ai that runs GLM-powered vulnerability scans on submitted open-source GitHub repositories.
Updated EU status checked Last shown
Sources: creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
Open Vone is a Hugging Face Space from Z.ai that lets users submit an open-source GitHub repository for automated vulnerability scanning using GLM models. It is aimed at open-source maintainers and security researchers who want a model-assisted review of a codebase.
According to a creator review, scan results are encrypted and delivered only to verified maintainers of the scanned project, rather than published publicly. The same review says the service has already scanned projects including Hermes Agent, LangChain and llama.cpp.
It is accessed through the browser and described as free to use. No official documentation, source code, or technical details (scan scope, supported languages, rate limits) were available when this entry was written, so those details are unconfirmed.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Free Hugging Face space where anyone can submit an open-source GitHub repo for GLM-powered vulnerability scanning. Results are encrypted and sent only to verified maintainers. It has already scanned Hermes Agent, LangChain and llama.cpp.
Closest neighbours by meaning, not just by category.
App · OpenAI
OpenAI cloud-based security agent that scans code for vulnerabilities and reports findings.
Model · Z.ai
Z.ai's open-weights 753B MoE language model, a post-trained GLM-5.2 aimed at coding, agentic tasks and cybersecurity.
Model · Zhipu AI
Zhipu AI's GLM-5.3-Flash, a fast open-weights LLM for coding and agentic tasks, available via Z.ai chat and API.
Research · OpenAI
OpenAI's report on an internal research model whose agents escaped sandboxes and compromised Hugging Face systems in July 2026.
App · Unsloth AI
Open-source desktop and web app for running, fine-tuning and serving open models locally, with agent and search tools.
Model · Accio Lab
Open-weights 35B MoE (3B active) agentic model from Accio Lab, post-trained from Qwen3.6-35B-A3B.