VQV Signal

AI AT WORK WATCH TECHNICAL

OpenCode Browse lets coding agents drive the user's real browser

According to a post on X by @EveryDevAi, OpenCode has added a Browse feature that lets coding agents control the user's real browser, including their tabs, logins and extensions. The feature works through MCP and a Chrome extension. When the agent reaches a login or two-factor prompt, it hands the tab to the user and resumes after they click Continue. The available text is a partial snippet, so other details are not covered here.

Source: Scobleizer News Pulse (X) · x.com Found via Robert Scoble’s Scobleizer News Pulse · a post on X, not independently verified Published 2026-11-07T17:30:00+00:00 Detected 2026-11-08T02:21:22+00:00
View original source

According to a post on X by @EveryDevAi, OpenCode has added a Browse feature that lets coding agents control the user's real browser, including their tabs, logins and extensions. The feature works through MCP and a Chrome extension. When the agent reaches a login or two-factor prompt, it hands the tab to the user and resumes after they click Continue. The available text is a partial snippet, so other details are not covered here.

AI-assisted summary based on the listed source.

OpenCode's new Browse feature lets coding agents control the user's real browser, with their tabs, logins and extensions, through MCP and a Chrome extension. When it hits a login or two-factor prompt, it hands the tab to the user and resumes after they click Continue. Why it matters: Agents can work on sites that...

The post says agents can work on sites that require signed-in sessions while the user keeps control of logins. Developers and teams using AI coding tools may find this relevant for tasks that depend on existing browser sessions. Next, it will be worth checking OpenCode's own documentation for how the feature and its Chrome extension work in practice.

Teams using AI at work may want to compare this against current productivity and review workflows.

Signal Strength 83% Technical label WATCH Public Interest 56 Category AI AT WORK Reader Depth TECHNICAL

Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.

Public Interest components
Recognizable Entity Score 51 Practical Impact Score 64 Novelty Interest Score 94 Consequence Score 22 Curiosity Score 16 Shareability Score 68

VQV surfaced this signal because it is recent, relevant to AI Coding Tools, connected to Scobleizer News Pulse (X).