OpenClaw articles
GregAGI field notes tagged OpenClaw, covering practical AI automation, agent operations, deployment, and product engineering work.
- OpenClaw 2026.4.27: fewer ways for your agent to get wedged 2026-04-30 · The owner-focused highlights from OpenClaw 2026.4.27: safer Codex Computer Use setup, faster gateway startup, less fragile channels, cleaner model behavior, and better recovery paths.
- OpenClaw 2026.4.29: less waiting, fewer silent failures 2026-04-30 · The owner-focused highlights from the OpenClaw 2026.4.29 release train: active-run steering, people-aware memory, slow-host startup fixes, channel reliability, model routing, and tighter security boundaries.
- OpenClaw 2026.4.26: the release that makes messy installs less fragile 2026-04-29 · The owner-focused highlights from OpenClaw 2026.4.26: safer updates, better recovery from bad config, stronger plugin handling, and fewer local-model surprises.
- How I gave my OpenClaw agent a browser on a headless VPS with Browserless and CapRover 2026-04-28 · A practical operator write-up on why local browser launch was the wrong model for a VPS-hosted agent, and how switching to Browserless over remote CDP made OpenClaw browser automation work cleanly.
- The practical guide to managing skills in OpenClaw 2026-04-25 · How to find, install, organize, share, and govern OpenClaw skills without creating drift across hosts, repos, and agents.
- How We Patched Around a Paperclip/OpenClaw Regression Without Forking 2026-04-20 · A practical incident write-up on diagnosing a production Paperclip/OpenClaw break, identifying the regression commit, and shipping a tiny forward patch instead of a messy rollback.
- The Control-File Pattern That Stops Agent Chaos 2026-03-23 · Use a small set of machine-readable control files (like APPROVED_PROJECTS.json and TOOLS.json) to align humans and agents without drift.