Blog
Engineering insights, product updates, and lessons learned building a managed AI hosting platform.
Self-Hosted OpenClaw Browser Profiles on Mac: `openclaw`, `user`, and the Fixes That Actually Matter
A simple macOS guide to configuring self-hosted OpenClaw browser profiles. Learn the difference between `openclaw` and `user`, how to switch the default profile, how to configure Brave correctly, and how to troubleshoot Chrome MCP attach issues.
How to Connect Claude Code to Your Active Browser Session with Chrome DevTools MCP
Learn how to connect Claude Code to your active browser session with Chrome DevTools MCP so it can reuse tabs, cookies, and logged-in web context.
How to Configure Ollama and OpenClaw Locally: Browser Control, Telegram, and Best Models for Mac
A complete guide to running OpenClaw locally with Ollama. Learn how to launch OpenClaw with one command, configure browser control, connect to Telegram, and choose the best models for your MacBook or Mac Mini.
How We Test OpenClaw Box: Evaluation-Driven Quality with Telegram CLI, Browser CDP, and Live Canary Checks
Deep dive into OpenClaw Box evaluation testing: Telegram CLI via Telethon, browser CDP verification, code execution probes, multi-turn context checks, and canary validation before every merge.
Cloud Google Chrome and Remote Browser Control in OpenClaw Box
Every tenant now ships with a cloud browser path: a browser UI, a preinstalled `chrome-cdp` binary, and a bundled Chrome skill that lets OpenClaw browse remotely in the cloud.
How to Set Up OpenClaw with Chrome CDP - Or Use the Version We Already Set Up for You
A practical guide to giving OpenClaw a real cloud browser with `chrome-cdp`, a Chrome skill, and a browser UI - plus how OpenClaw Box already ships that stack out of the box.
OpenClaw Box vs Self-Hosting vs Other Managed Hosting: The 2026 Technical Comparison
Why OpenClaw Box is the easiest way to run OpenClaw. Compare one-click Telegram deployment, built-in cloud Chrome, included AI models, and zero infrastructure setup against self-hosting and other managed alternatives.
Week of March 10: Better /status Links, Telegram-Native Media, and Stronger Delivery Reliability
This week's release notes cover clearer `/status` URLs, much broader Telegram-native message support, and reliability work across proxy-mode delivery, media handling, and gateway error handling.
Why We Run OpenClaw on Kubernetes (And What It Actually Costs Us)
The technical trade-offs of hosting personal AI assistants in Kubernetes: how we provision tenants in seconds, persist user-installed tools across restarts, and deal with cloud IP restrictions on headless Chrome.
OpenClaw Box: Why We Started This Service Three Weeks Ago
A few weeks into launch, here is why we built OpenClaw Box: Telegram-native managed OpenClaw hosting with one-command deployment, isolated tenants on AKS, and no server setup.
We Started Building MobileClaw on Android First, With Local OpenClaw and Browser Support
Why we started building MobileClaw on Android first, with local OpenClaw runtime support, browser-backed tasks, notifications, files, voice, and better session UX than a Mac mini at home.
Vibe Engineering: Reflection - A Completion Verification Layer for Autonomous AI Coding Agents
Why the reflection layer is the reason I only use open-source coding agents.
Vibe Engineering: Visual Testing for Browser Extensions: From Puppeteer to GIF-Powered PR Reviews
When AI Agents writes a lot of code, reviewing and testing browser extensions is notoriously difficult. Extensions live in a sandboxed…
Vibe Engineering: The AI Browser That Gets Power Users
Why Silicon Valley keeps building the wrong AI tools — and what we’re doing differently
Vibe Engineering: Docusarus + Azure AI Search + Azure OpenAI = GenAI-based support portal in a few…
How we built a self-service documentation chatbot with human escalation in 2 days for vibebrowser.app using Azure’s AI stack
Building a Tier-Based LLM API Gateway with LiteLLM, Stripe, and k3s
This post covers the architecture we built for Vibe Browser’s API gateway — a self-hosted solution that routes LLM requests through a…
Vibe Engineering: The Invisible Walls: Why AI Browser Agents Need More Than Extensions
At vibebrowser.app We hit an interesting bug recently. Our AI agent was asked to fill a form on the Chrome Web Store developer console. The…
Software Engineering: TypeScript + Bun for Development… But Wait, It’s Built in Zig?
I’ve been working on vibebrowser.app recently, and like most modern JavaScript projects, I naturally reached for TypeScript for our…
Vibe Engineering: Testing AI Browser Automation Tools with a Mock LLM Server
Building reliable browser automation for AI agents at vibebrowser.app requires rigorous testing. At Vibe Browser, we developed a…
Vibe Engineering: Accelerating Agentic Browsing: Implementing Parallel Execution and Fast Web…
In our quest to build the most capable and efficient browser agent — vibebrowser.app, we’ve recently introduced two powerful architectural…
Vibe Engineering: Testing an Agentic AI Browser Auto Pilot: A Three-Stage Verification Strategy
Testing an AI-powered browser automation agent at vibebrowser.app presents unique challenges. Unlike traditional software where inputs…