OpenClaw

5 articles

Editorial illustration of Microsoft Scout as an always-on Autopilot agent working autonomously across a Microsoft 365 workspace โ€” calendar, email, Teams and files โ€” built on the open-source OpenClaw framework, 2026
AI ToolsMicrosoft ScoutAI Agents

Microsoft Scout, Explained: The Always-On 'Autopilot' Built on OpenClaw

Microsoft Scout is the first of a new category Microsoft calls 'Autopilots' โ€” a Windows and macOS desktop agent that acts on your files, shell, browser and Microsoft 365, and works autonomously in the background. Here's what's actually confirmed, what isn't, how to get it, and why it's built on the open-source OpenClaw framework.

Marco Lobo
Marco Loboยท8 Jun 2026ยท11 min read
Handdrawn enterprise AI agent fleet diagram with role agents connected to departments, systems, memory, and governance layers
AI GuidesAI AgentsClaude

Building AI Agents in the Enterprise: Implementation Patterns for 2026

Anthropic's playbook is right about the enterprise shape. The missing layer is implementation: governed skills, MCP tools, memory, observability, worktree-safe orchestration, and agent fleets that survive contact with a 1,000-person company.

Marco Lobo
Marco Loboยท19 May 2026ยท11 min read
Handdrawn city-scale software codebase with agent figures traversing modules, worktrees, hooks, and review gates
AI EngineeringClaude CodeLarge Codebases

Claude Code in Large Codebases: The 2026 Implementation Guide

Claude Code does not win large codebases by swallowing the repo. It wins when you build a navigation and governance layer around it.

Marco Lobo
Marco Loboยท19 May 2026ยท11 min read
Photograph of a UK Sun-style tabloid newspaper front page lying on a desk โ€” masthead THE SUN, screaming red-and-black headline TAN vs CLAW with deck Silicon Valley benchmark BLOODBATH, split press-photo of Garry Tan and the OpenClaw lobster mascot facing off, yellow EXCLUSIVE sticker, bottom strip of unrelated tabloid teasers, real desk context with bacon sandwich and tea ring
AI EngineeringAgent MemoryRetrieval

We benchmarked Garry Tan's gbrain against our own agent memory on 150 real questions (May 2026)

A 352-file, 150-question apples-to-apples retrieval benchmark between gbrain and our existing OpenClaw qmd setup. gbrain wins 8.3x more often on hard, cross-source, and discrimination questions โ€” but the headline is messier than the marketing.

Marco Lobo
Marco Loboยท5 May 2026ยท17 min read
A developer asleep at a vintage Mac while OpenClaw agents work through the night โ€” the house keys problem visualised
AI ToolsOpenClawClaude Code

The House Keys Problem: What OpenClaw and Claude Code Are Really Fighting About

There's a story about the moment OpenClaw clicked for its creator. It involves house keys, a sleeping founder, and an agent that booked a restaurant without being asked. That story still tells you everything you need to know โ€” even now that Claude Code has started asking for a small keyring of its own.

Marco Lobo
Marco Loboยท10 Mar 2026ยท9 min read