{"slug": "browser-use", "name": "browser-use", "category": "productivity", "category_name": "Productivity", "description": "", "recommenders": 3, "commenters": 6, "warners": 1, "score": 2.335, "rising": 0.35, "first": "2026-02-02", "latest": "2026-10-20", "why": "we love Browser-Use <3 and we still work together closely!", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 1, "compare": 1, "warn": 1}, "spark": [0, 0, 0, 1, 0, 0, 0, 1, 0, 1, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "we love Browser-Use <3 and we still work together closely!", "icon": true, "domain": null, "github_repo": "github.com/browser-use/browser-use", "official_url": "https://browser-use.com", "pricing": "", "aliases": ["browser-use", "Browser Use", "Browser-Use"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 789533696, "item_id": 49345856, "url": "https://news.ycombinator.com/item?id=49345856", "by": "nateb2022", "date": "2026-08-18", "stance": "recommend", "quote": "has been great so far", "excerpt": "https://github.com/browser-use/browser-use has been great so far", "context": "", "use_case": "browser automation for agents", "switched_from": "", "story": "NeoBrowser: An MCP server that drives real Chrome with your logged-in sessions"}, {"id": 777312545, "item_id": 48582034, "url": "https://news.ycombinator.com/item?id=48582034", "by": "nderjung", "date": "2026-06-18", "stance": "recommend", "quote": "we love Browser-Use <3 and we still work together closely!", "excerpt": "Hi, Alex from Unikraft here. One clarification: Browser-Use didn't move away from Unikraft because of any limitation around browser startup times, snapshotting, scale-to-zero, or browser-level autoscaling. Those capabilities worked well and were a key reason they adopted the platform in the first place. The challenge they encountered was at a different layer: horizontally scaling the underlying EC2 infrastructure. At", "context": "", "use_case": "browser automation for agents", "switched_from": "", "story": "How We Run Firecracker VMs Inside EC2 and Start Browsers in <1s"}, {"id": 749853760, "item_id": 46865860, "url": "https://news.ycombinator.com/item?id=46865860", "by": "sweetrabh", "date": "2026-02-02", "stance": "recommend", "quote": "We use browser-use for password change automation", "excerpt": "We use browser-use for password change automation (thepassword.app) and the detection landscape is evolving fast. The key insight from this article: sites are shifting from \"detect bots\" to \"detect automation intent.\" For user-initiated tasks like password changes, this is actually helpful - the automation is authorized, just executed by AI instead of human fingers. The interesting challenge is that different sites h", "context": "", "use_case": "password change automation", "switched_from": "", "story": "Browser agent bot detection is about to change"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 757057904, "item_id": 47316119, "url": "https://news.ycombinator.com/item?id=47316119", "by": "hamasho", "date": "2026-03-09", "stance": "warn", "quote": "it even failed to complete the demo in its own readme!", "excerpt": "Hmm.. so this is not the same category with computer use or browser use. I love the idea. Well defined and controlled sandbox is really useful. Off topic but I\u2019m disappointed by computer use and browser use when I tried three months ago. They couldn\u2019t complete many basic tasks. Especially browser use, it easily failed slightly unorthodox website. It can\u2019t find select box implemented by div, stacks in infinite loop wh", "context": "", "use_case": "browser automation agent", "switched_from": "", "story": "Launch HN: Terminal Use (YC W26) \u2013 Vercel for filesystem-based agents"}]}], "who": [], "tags": [], "use_cases": ["browser automation for agents", "browser automation", "browser automation agent", "password change automation"], "compared": [], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=48556561", "title": "How We Run Firecracker VMs Inside EC2 and Start Browsers in <1s", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=50163896", "title": "Show HN: Make AI coding agents verify its own work", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49345320", "title": "NeoBrowser: An MCP server that drives real Chrome with your logged-in sessions", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47311657", "title": "Launch HN: Terminal Use (YC W26) \u2013 Vercel for filesystem-based agents", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46856594", "title": "Browser agent bot detection is about to change", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {"recommend": 1}, "2026-03": {"warn": 1}, "2026-04": {}, "2026-05": {}, "2026-06": {"compare": 1, "recommend": 1}, "2026-07": {}, "2026-08": {"recommend": 1}, "2026-09": {}, "2026-10": {"neutral": 1}}, "quotes": [{"id": 802623936, "item_id": 50163996, "url": "https://news.ycombinator.com/item?id=50163996", "by": "codewtensai", "date": "2026-10-20", "stance": "neutral", "quote": "i use browser use, and it's slow", "excerpt": "Looks cool, but i use browser use, and it's slow, how is this making it faster.", "context": "", "use_case": "browser automation for agents", "switched_from": "", "story": "Show HN: Make AI coding agents verify its own work"}, {"id": 789533696, "item_id": 49345856, "url": "https://news.ycombinator.com/item?id=49345856", "by": "nateb2022", "date": "2026-08-18", "stance": "recommend", "quote": "has been great so far", "excerpt": "https://github.com/browser-use/browser-use has been great so far", "context": "", "use_case": "browser automation for agents", "switched_from": "", "story": "NeoBrowser: An MCP server that drives real Chrome with your logged-in sessions"}, {"id": 777312545, "item_id": 48582034, "url": "https://news.ycombinator.com/item?id=48582034", "by": "nderjung", "date": "2026-06-18", "stance": "recommend", "quote": "we love Browser-Use <3 and we still work together closely!", "excerpt": "Hi, Alex from Unikraft here. One clarification: Browser-Use didn't move away from Unikraft because of any limitation around browser startup times, snapshotting, scale-to-zero, or browser-level autoscaling. Those capabilities worked well and were a key reason they adopted the platform in the first place. The challenge they encountered was at a different layer: horizontally scaling the underlying EC2 infrastructure. At", "context": "", "use_case": "browser automation for agents", "switched_from": "", "story": "How We Run Firecracker VMs Inside EC2 and Start Browsers in <1s"}, {"id": 777217217, "item_id": 48576076, "url": "https://news.ycombinator.com/item?id=48576076", "by": "sandGorgon", "date": "2026-06-17", "stance": "compare", "quote": "We would rather use browser-use if it had that support.", "excerpt": "have you tried running android browsers ? we run RL workloads using android browsers. We are having to maintain a fork of https://github.com/budtmo/docker-android/ and android chrome on top. We would rather use browser-use if it had that support. P.S. we do maintain our fork of a browser for rubric computation...but that is not relevant for this. The infrastructure is what we are looking for.", "context": "", "use_case": "browser automation", "switched_from": "", "story": "How We Run Firecracker VMs Inside EC2 and Start Browsers in <1s"}, {"id": 757057904, "item_id": 47316119, "url": "https://news.ycombinator.com/item?id=47316119", "by": "hamasho", "date": "2026-03-09", "stance": "warn", "quote": "it even failed to complete the demo in its own readme!", "excerpt": "Hmm.. so this is not the same category with computer use or browser use. I love the idea. Well defined and controlled sandbox is really useful. Off topic but I\u2019m disappointed by computer use and browser use when I tried three months ago. They couldn\u2019t complete many basic tasks. Especially browser use, it easily failed slightly unorthodox website. It can\u2019t find select box implemented by div, stacks in infinite loop wh", "context": "", "use_case": "browser automation agent", "switched_from": "", "story": "Launch HN: Terminal Use (YC W26) \u2013 Vercel for filesystem-based agents"}, {"id": 749853760, "item_id": 46865860, "url": "https://news.ycombinator.com/item?id=46865860", "by": "sweetrabh", "date": "2026-02-02", "stance": "recommend", "quote": "We use browser-use for password change automation", "excerpt": "We use browser-use for password change automation (thepassword.app) and the detection landscape is evolving fast. The key insight from this article: sites are shifting from \"detect bots\" to \"detect automation intent.\" For user-initiated tasks like password changes, this is actually helpful - the automation is authorized, just executed by AI instead of human fingers. The interesting challenge is that different sites h", "context": "", "use_case": "password change automation", "switched_from": "", "story": "Browser agent bot detection is about to change"}]}