OpenClaw 3.13 now connects to a real Chrome 146 session over MCP so agents can drive your signed-in browser instead of a separate bot context. Update if captchas or auth state were blocking your web automation flows.
OpenClaw 3.13 adds Chrome 146 support via MCP. In the primary announcement, Ray Fernando says the new path lets an agent drive "your real browser session" and stresses "Not a bot. You." That is the key implementation change: the agent is no longer framed as operating in an isolated automation context, but through the users existing signed-in Chrome session.
The same post ties the release to a specific pain point by opening with "No more captchas." A follow-up post keeps the message simple update to 3.13 if browser automation has been blocked by current auth state or anti-bot checks. The attached demo video setup demo shows a terminal-based connection flow ending in a successful OpenClaw interface connection.
For engineers building browser agents, the notable part is not just another web automation connector. The supporting repost summarizes the change as access to a "real, signed-in browser," which implies existing cookies, sessions, and account state can stay in the loop when an agent acts through Chrome.
That matters because many brittle flows happen after login: internal tools, purchasing portals, dashboards, and consumer sites that aggressively challenge fresh automation contexts. OpenClaw's launch language explicitly positions 3.13 against that failure mode, and its setup note narrows the current sweet spot to Mac or PC desktop environments rather than a generic hosted runtime.
OpenClaw 2026.3.24 adds native Microsoft Teams, OpenWebUI sub-agent access, Slack reply buttons, and a control surface for skills and tools. The release expands where the runtime can plug into enterprise workflows, while also increasing the surface area teams need to secure.
breakingMalicious LiteLLM 1.82.7 and 1.82.8 releases executed .pth startup code to steal credentials and were quarantined after disclosure. Rotate secrets, audit transitive AI-tooling dependencies, and add package-age controls before letting agents install packages autonomously.
breakingTurboQuant claims 6x KV-cache memory reduction and up to 8x faster attention on H100s without retraining or quality loss on long-context tasks. If those results hold in serving stacks, teams should revisit long-context cost, capacity, and vector-search design.
releaseOpenCode is adding remote sandboxes, synced state across laptop, server, and cloud, and more product surface inside its plugin system. That makes long-running off-laptop workflows more practical, but operators should still review telemetry, sandbox, and exposure defaults.
releaseClaude Code 2.1.84 adds an opt-in PowerShell tool, new task and worktree hooks, safer MCP limits, and better startup and prompt-cache behavior. Anthropic also documented auto mode’s action classifier and added iMessage as a channel, so teams should review permissions and remote-control workflows.
No more captchas. OpenClaw 3.13 connects to Chrome 146 via MCP and your agent controls your real browser session. Not a bot. You. Update if you haven't. Easiest config is on a Mac or PC.
Chrome just became massively more agent-friendly 🔥 Your real, signed-in browser can now be natively accessible to any coding agent. No extensions. No headless browser. No screenshots. No separate logins. Just one toggle to enable it. Check this out: developer.chrome.com/blog/chrome-de…
New @openclaw beta is up: it comes with the new live browser control that Google added in latest Chrome! enable via chrome://inspect#remote-debugging Your clanker will know when to use what, or you can ast it. new "user" profile session is there! developer.chrome.com/blog/chrome-de…
