You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
- Platform → Cloud: reposition for cloud performance — emphasize
bare-metal speed, zero noisy neighbors, no hypervisor overhead
- Enclaves → Sandbox: rename to clearly signal AI agent sandboxing
- Resilience → Upgrade: rename to describe zero-downtime kernel upgrades
Updated homepage cards, nav dropdowns, mobile nav, footer links, and
all three product page hero/description copy. URLs unchanged.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Copy file name to clipboardExpand all lines: index.html
+11-11Lines changed: 11 additions & 11 deletions
Original file line number
Diff line number
Diff line change
@@ -124,28 +124,28 @@ <h2 class="section-title">Isolation Built into the Architecture</h2>
124
124
<span>Products</span>
125
125
</div>
126
126
<h2class="section-title">Built on Split-Kernel Architecture</h2>
127
-
<pclass="section-subtitle">Three products that deliver the benefits of split-kernel architecture for different use cases: enterprise infrastructure, AI agent isolation, and kernel resilience.</p>
127
+
<pclass="section-subtitle">Three products that deliver the benefits of split-kernel architecture for different use cases: cloud performance, AI sandboxing, and zero-downtime kernel upgrades.</p>
<pclass="capability-description">The enterprise split-kernel distribution. Validated kernel builds, Kerf orchestration, and production tooling for deploying and managing split-kernel environments at scale.</p>
<pclass="capability-description">Split-kernel architecture for cloud workloads. Eliminate noisy neighbors, remove virtualization overhead, and get bare-metal performance inside any standard cloud VM.</p>
<pclass="capability-description">Kernel-level isolation for AI agents. Each agent gets its own kernel with full GPU access and strong sandboxing. No nested virtualization required.</p>
<pclass="capability-description">Kernel-level sandboxing for AI agents. Each agent runs in its own kernel with full GPU access and strong isolation. No nested virtualization required.</p>
<pclass="capability-description">Zero-downtime kernel upgrades with instant rollback, plus sub-second automatic failover when a kernel crashes. Your kernel never goes down.</p>
<pclass="capability-description">Zero-downtime kernel upgrades with instant rollback. Apply security patches and kernel updates without rebooting or interrupting running workloads.</p>
Copy file name to clipboardExpand all lines: products/enclaves.html
+10-10Lines changed: 10 additions & 10 deletions
Original file line number
Diff line number
Diff line change
@@ -1,7 +1,7 @@
1
1
---
2
2
layout: default
3
-
title: "Multikernel Enclaves - AI Agent Isolation"
4
-
description: "Kernel-level isolation for AI agents. Full GPU access, strong sandboxing, and fast checkpoint/restore without virtualization overhead."
3
+
title: "Multikernel Sandbox - AI Agent Sandboxing"
4
+
description: "Kernel-level sandboxing for AI agents. Full GPU access, strong isolation, and fast checkpoint/restore without virtualization overhead."
5
5
permalink: /products/enclaves.html
6
6
---
7
7
@@ -10,11 +10,11 @@
10
10
<divclass="hero-container">
11
11
<divclass="hero-badge">
12
12
<idata-lucide="brain"></i>
13
-
<span>Multikernel Enclaves</span>
13
+
<span>Multikernel Sandbox</span>
14
14
</div>
15
15
16
-
<h1>Kernel-Level Isolation for AI Agents</h1>
17
-
<pclass="subtitle">Give each AI agent its own Linux kernel with full GPU access and strong sandboxing. No virtualization layer between the agent and hardware. No nested virtualization required. Works inside any standard cloud VM.</p>
16
+
<h1>Kernel-Level Sandboxing for AI Agents</h1>
17
+
<pclass="subtitle">Give each AI agent its own Linux kernel with full GPU access and strong isolation. No virtualization layer between the agent and hardware. No nested virtualization required. Works inside any standard cloud VM.</p>
<pclass="capability-description">Each agent gets its own kernel with direct GPU access. Kernel-level isolation without virtualization. Native performance inside any cloud VM.</p>
<pclass="capability-description">Each agent gets its own kernel with direct GPU access. Kernel-level sandboxing without virtualization. Native performance inside any cloud VM.</p>
<pclass="feature-description">Each agent is sandboxed in its own kernel. A compromised agent cannot access other agents' memory, devices, or kernel state.</p>
description: "A supported, enterprise-ready distribution of the split-kernel architecture. Validated kernel builds, Kerf orchestration, and production-grade tooling."
3
+
title: "Multikernel Cloud - Cloud Performance Without Virtualization Overhead"
4
+
description: "Split-kernel architecture for cloud workloads. Eliminate noisy neighbors, remove virtualization overhead, and get bare-metal performance inside any standard cloud VM."
5
5
permalink: /products/platform.html
6
6
---
7
7
@@ -10,11 +10,11 @@
10
10
<divclass="hero-container">
11
11
<divclass="hero-badge">
12
12
<idata-lucide="layers"></i>
13
-
<span>Multikernel Platform</span>
13
+
<span>Multikernel Cloud</span>
14
14
</div>
15
15
16
-
<h1>The Enterprise Split-Kernel Distribution</h1>
17
-
<pclass="subtitle">A supported, production-ready distribution of the Multikernel split-kernel architecture. Validated kernel builds, Kerf orchestration, and the tooling your infrastructure team needs to deploy and manage split-kernel environments at scale.</p>
16
+
<h1>Cloud Performance Without Virtualization Overhead</h1>
17
+
<pclass="subtitle">Split-kernel architecture for cloud workloads. Each application gets its own kernel with dedicated cores and native hardware access. No hypervisor, no noisy neighbors, no performance tax. Runs inside any standard cloud VM on AWS, GCP, or Azure.</p>
<pclass="capability-description">Pre-built, tested kernel configurations for app-kernels and device-kernels. Optimized for common workload profiles and validated against enterprise hardware.</p>
45
+
<pclass="capability-description">Pre-built, tested kernel configurations optimized for cloud workloads. Tuned for low latency, high throughput, and validated against AWS, GCP, and Azure instance types.</p>
<pclass="feature-description">Each workload runs in its own kernel with a minimal attack surface. No device drivers, no interrupt handlers, no shared kernel vulnerabilities.</p>
<pclass="feature-description">Each workload runs in its own kernel on dedicated cores. No interrupt interference, no CPU contention, no shared kernel overhead stealing your cycles.</p>
88
88
</div>
89
89
90
90
<divclass="feature-card">
91
91
<divclass="feature-icon">
92
92
<idata-lucide="zap"></i>
93
93
</div>
94
-
<h3class="feature-title">Native Performance</h3>
95
-
<pclass="feature-description">No hypervisor, no nested virtualization. Applications run directly on hardware inside any standard cloud VM.</p>
<pclass="feature-description">No hypervisor tax, no nested virtualization. Applications access hardware directly, closing the performance gap between cloud VMs and bare metal.</p>
Copy file name to clipboardExpand all lines: products/resilience.html
+8-8Lines changed: 8 additions & 8 deletions
Original file line number
Diff line number
Diff line change
@@ -1,20 +1,20 @@
1
1
---
2
2
layout: default
3
-
title: "Multikernel Resilience - Zero-Downtime Upgrades and Auto-Healing"
4
-
description: "Zero-downtime kernel upgrades with instant rollback and sub-second automatic failover. Keep your applications running through planned and unplanned kernel events."
description: "Upgrade your Linux kernel without rebooting. Apply security patches and kernel updates with instant rollback while applications keep running."
5
5
permalink: /products/resilience.html
6
6
---
7
7
8
8
<main>
9
9
<sectionclass="hero">
10
10
<divclass="hero-container">
11
11
<divclass="hero-badge">
12
-
<idata-lucide="heart-pulse"></i>
13
-
<span>Multikernel Resilience</span>
12
+
<idata-lucide="arrow-up-circle"></i>
13
+
<span>Multikernel Upgrade</span>
14
14
</div>
15
15
16
-
<h1>Your Kernel Never Goes Down</h1>
17
-
<pclass="subtitle">Zero-downtime kernel upgrades with instant rollback. Sub-second automatic failover when a kernel crashes. Keep your applications running through both planned and unplanned kernel events.</p>
16
+
<h1>Upgrade Your Kernel Without Rebooting</h1>
17
+
<pclass="subtitle">Apply kernel security patches and updates without downtime. Boot the new kernel alongside the old one, migrate workloads, and roll back instantly if anything goes wrong. No maintenance windows required.</p>
<pclass="section-subtitle">Kernel upgrades are one of the most painful operations in production Linux. Teams delay security patches for weeks because they require reboots. Multikernel Resilience removes that tradeoff.</p>
36
+
<pclass="section-subtitle">Kernel upgrades are one of the most painful operations in production Linux. Teams delay security patches for weeks because they require reboots. Multikernel Upgrade removes that tradeoff.</p>
<pclass="section-subtitle">When a kernel crashes today, the answer is reboot and hope. Multikernel Resilience turns a minutes-long outage into a sub-second failover.</p>
71
+
<pclass="section-subtitle">When a kernel crashes today, the answer is reboot and hope. Multikernel Upgrade turns a minutes-long outage into a sub-second failover.</p>
0 commit comments