greywall -- claude, greywall -- opencode, or any other CLI agent. That is the whole process. Greywall operates at the OS level, so it does not need plugins, extensions, or agent-specific configuration. The agent launches inside a kernel-enforced sandbox and runs normally — it just cannot reach things you have not explicitly allowed. If you want to see what the agent is trying to access, open the GreyProxy dashboard.',
+ },
+ {
+ question: 'How is Greywall different from running agents in Docker?',
+ answer:
+ 'Containers were designed to ship software, not to babysit it. When you run an AI agent inside Docker, you get isolation, but you lose access to your local tools, editor integrations, and filesystem. Every dependency change means rebuilding an image. Greywall takes a different approach: the agent runs natively on your machine with full access to your toolchain, but the kernel enforces boundaries around what it can reach. Think of it as the difference between locking someone in a room versus letting them walk around the house with certain doors locked. You also get real-time visibility into what the agent is doing, which Docker does not offer.',
+ },
+ {
+ question: 'Does Greywall work on macOS?',
+ answer:
+ 'Yes. On macOS, Greywall uses Seatbelt — Apple\'s built-in kernel sandbox, the same one that constrains App Store applications. It generates a deny-by-default sandbox profile for each session, covering filesystem access, network connections, and IPC. Network traffic is routed through GreyProxy via environment variables. On Linux, there are more layers available (Bubblewrap, Landlock, Seccomp BPF, eBPF, and a TUN device for network capture), but the macOS implementation provides strong isolation using only built-in OS capabilities. No additional packages required.',
+ },
+ {
+ question: 'Is Greywall open source?',
+ answer:
+ 'Yes. Apache 2.0 license, source code on GitHub. For a security tool, this is not a philosophical position so much as a practical necessity. You should be able to read the code that stands between an AI agent and your production credentials. Greywall is built by Greyhaven, who use it in their own production deployments. As the saying goes — never trust a lock you cannot pick apart.',
+ },
+ {
+ question: 'What kernel version does Linux require?',
+ answer:
+ 'The minimum is Linux 3.8 for namespace isolation via Bubblewrap. Landlock filesystem controls need 5.13. Seccomp BPF needs 3.5. eBPF monitoring needs 4.15. The network proxy works on any kernel. Greywall detects what your system supports at runtime and activates every available layer. If you are on a reasonably modern distribution — anything from the last few years — you will get all five layers. Run greywall --linux-features to see what is available. The tool degrades gracefully rather than refusing to start, which is a courtesy more software should extend.',
+ },
+ {
+ question: 'Which AI agents does Greywall support?',
+ answer:
+ 'All of them. Claude Code, Codex, Cursor, Aider, Goose, Amp, Gemini CLI, Cline, OpenCode, Copilot — anything that runs as a process on your machine. Greywall does not need agent-specific configuration because it operates at the OS level, below the agent. The agent does not know it is sandboxed, which is, in a way, the whole point. It simply discovers that certain operations fail, adapts, and carries on with its work. Most of the time, this is exactly what you wanted it to do in the first place.',
+ },
+]
+
+const faqJsonLd = {
+ '@context': 'https://schema.org',
+ '@type': 'FAQPage',
+ mainEntity: faqs.map((faq) => ({
+ '@type': 'Question',
+ name: faq.question,
+ acceptedAnswer: {
+ '@type': 'Answer',
+ text: faq.answer.replace(/<[^>]*>/g, ''),
+ },
+ })),
+}
+
+function FAQItem({ question, answer }: { question: string; answer: string }) {
+ const [open, setOpen] = useState(false)
+
+ return (
+ +
Container-free sandboxing with real-time observability & dynamic controls, for Linux & MacOS.
+ ) diff --git a/components/problem.tsx b/components/problem.tsx index 98f5c27..391040f 100644 --- a/components/problem.tsx +++ b/components/problem.tsx @@ -122,11 +122,22 @@ export function Problem() {“The act of verification creates trust.”-
+
Greywall gives you two pillars: control over what agents can reach, and clarity into every operation they perform.
+