Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for agent builders who want a leaner browser-control layer and care about token cost, faster orientation, and fewer round trips during web tasks.
Where this stands now
dondai1234/agent-browser ranks #4 of 9 tracked AI Automation items by composite score (7.9 against a section median of 7.9). The section currently carries 7 Silver, 2 Gold. RepoRadar has retained observations for this record since 2026-06-30 (95 days in the current window). Signal extremes versus the section: momentum at the 17th percentile.
Who should use it
Who should skip it
Skip dondai1234/agent-browser if the source link, documentation, or setup requirements do not align with your current workflow or stack.
About this signal
dondai1234/agent-browser is tracked by RepoRadar as an MCP server in the AI Automation section. First seen 2026-06-30; the source record was last checked on 2026-06-30. The current verdict is 'try now' with a Silver tier and moderate setup difficulty. Across RepoRadar's eight signals, dondai1234/agent-browser is strongest on workflow potential (9.4) and open-source/build quality (8.4) and weakest on momentum (5.0) — a profile worth weighing against your own priorities. This page summarizes the public evidence on the linked source page and states where additional review is still needed.
How this item is evaluated
The dondai1234/agent-browser record combines a 7.9/10 composite score with separate popularity (1.0), risk (conditional), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.
Questions worth asking before you adopt this
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
It can act inside logged-in browser sessions, so first evaluation should use a separate browser profile with only the accounts and sites you intend to expose; Automated site actions can still hit CAPTCHAs, rate limits, or unintended form submissions, so keep early runs on test flows and non-production accounts.