From 3fd6d63fa3e2ec38fe3fce5b8d7e7d0ede17af52 Mon Sep 17 00:00:00 2001 From: Nik L Date: Wed, 1 Apr 2026 15:59:59 -0400 Subject: [PATCH] feat: frictionless sandboxing --- app/layout.tsx | 8 ++++---- components/comparison.tsx | 3 +-- components/control.tsx | 4 ++-- components/faq.tsx | 2 +- components/hero.tsx | 2 +- components/problem.tsx | 15 +++++++++------ public/llms.txt | 2 +- 7 files changed, 19 insertions(+), 17 deletions(-) diff --git a/app/layout.tsx b/app/layout.tsx index b8e3a33..03f28a2 100644 --- a/app/layout.tsx +++ b/app/layout.tsx @@ -20,7 +20,7 @@ export const metadata: Metadata = { metadataBase: new URL('https://greywall.io'), title: 'Greywall: Sandbox for AI Agents', description: - 'Container-free, default-deny sandboxing with real-time observability for AI agents on Linux and macOS. Five kernel-enforced security layers in one command. Open source.', + 'Frictionless, default-deny sandboxing with real-time observability for AI agents on Linux and macOS. One command, nothing to configure. Open source.', icons: { icon: [ { url: '/icon.svg', type: 'image/svg+xml' }, @@ -31,7 +31,7 @@ export const metadata: Metadata = { }, openGraph: { title: 'Greywall: Sandbox for AI Agents', - description: 'Container-free, default-deny sandboxing with real-time observability for AI agents. Five kernel-enforced security layers in one command.', + description: 'Frictionless, default-deny sandboxing with real-time observability for AI agents. One command, nothing to configure.', url: 'https://greywall.io', siteName: 'Greywall', type: 'website', @@ -40,7 +40,7 @@ export const metadata: Metadata = { twitter: { card: 'summary_large_image', title: 'Greywall: Sandbox for AI Agents', - description: 'Container-free, default-deny sandboxing with real-time observability for AI agents. Five kernel-enforced security layers in one command.', + description: 'Frictionless, default-deny sandboxing with real-time observability for AI agents. One command, nothing to configure.', images: ['/og-image.png'], }, alternates: { @@ -71,7 +71,7 @@ const jsonLd = { '@id': 'https://greywall.io/#software', name: 'Greywall', description: - 'Container-free, default-deny sandboxing with real-time observability and dynamic controls for AI agents on Linux and macOS.', + 'Frictionless, default-deny sandboxing with real-time observability and dynamic controls for AI agents on Linux and macOS.', applicationCategory: 'SecurityApplication', operatingSystem: 'Linux, macOS', url: 'https://greywall.io', diff --git a/components/comparison.tsx b/components/comparison.tsx index 9323ae6..81f79d9 100644 --- a/components/comparison.tsx +++ b/components/comparison.tsx @@ -148,8 +148,7 @@ export function Comparison() { Not all sandboxes are equal.

- Greywall combines filesystem isolation, network control, syscall filtering, - and real-time monitoring in a single tool. Here's how it stacks up. + Security that adds friction doesn't get used. Here's how Greywall compares to the alternatives.

diff --git a/components/control.tsx b/components/control.tsx index 3f56c03..3375ceb 100644 --- a/components/control.tsx +++ b/components/control.tsx @@ -239,8 +239,8 @@ export function Control() {

{platform === 'linux' - ? 'Uses strace to trace filesystem access. No special permissions needed. Auto-generates a template from observed paths.' - : 'Uses macOS Endpoint Security (eslogger) to trace access. Auto-generates a least-privilege template from observed paths.'} + ? 'No need to figure out which paths to allow. Traces what your agent accesses via strace and generates a least-privilege policy automatically. No special permissions needed.' + : 'No need to figure out which paths to allow. Traces what your agent accesses via macOS eslogger and generates a least-privilege policy automatically.'}

diff --git a/components/faq.tsx b/components/faq.tsx index 0821376..28efb95 100644 --- a/components/faq.tsx +++ b/components/faq.tsx @@ -17,7 +17,7 @@ const faqs = [ { 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.', + '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. That friction is why most people just don\'t bother. 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?', diff --git a/components/hero.tsx b/components/hero.tsx index 835575a..874d5cc 100644 --- a/components/hero.tsx +++ b/components/hero.tsx @@ -18,7 +18,7 @@ export function Hero() { Greywall your agent & let it cook.

- Container-free sandboxing with real-time observability & dynamic controls, for Linux & MacOS. + Frictionless sandboxing with real-time observability & dynamic controls, for Linux & macOS.

diff --git a/components/problem.tsx b/components/problem.tsx index bc172ca..e25a32b 100644 --- a/components/problem.tsx +++ b/components/problem.tsx @@ -119,14 +119,17 @@ export function Problem() { {/* Resolution: Verification creates trust */}
-
+

+ Run in YOLO mode without risking anything outside your project. +

+

+ The security layer around your tools should be independent of the company selling you the AI. + Greywall gives you complete observability into + what your agent touches and full control over what it can reach. +

+
“The act of verification creates trust.”
-

- Greywall gives you complete observability into - every interaction between a model and your system, as well as an - ergonomic mechanism for control. -