{"slug": "agent-browser", "name": "agent-browser", "category": "productivity", "category_name": "Productivity", "description": "", "recommenders": 8, "commenters": 23, "warners": 2, "score": 7.9, "rising": -1.62, "first": "2026-01-23", "latest": "2026-09-21", "why": "it can be combined with agent-browser to get the best of both worlds", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 8, "neutral": 5, "compare": 10, "warn": 2}, "spark": [0, 0, 0, 3, 4, 0, 0, 0, 0, 1, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "it can be combined with agent-browser to get the best of both worlds", "kind": "", "icon": true, "domain": null, "github_repo": "github.com/vercel-labs/agent-browser", "official_url": "https://github.com/vercel-labs/agent-browser", "pricing": "", "aliases": ["agent-browser", "Agent Browser", "AgentBrowser"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 789554016, "item_id": 49347126, "url": "https://news.ycombinator.com/item?id=49347126", "by": "esafak", "date": "2026-08-18", "stance": "recommend", "quote": "agent-browser works fine", "excerpt": "agent-browser works fine, and it can use browser use as a provider: https://github.com/vercel-labs/agent-browser#browser-use I invite the author to add agent-browser to the comparison table.", "context": "", "use_case": "Browser automation for agents", "switched_from": "", "story": "NeoBrowser: An MCP server that drives real Chrome with your logged-in sessions"}, {"id": 760187025, "item_id": 47511689, "url": "https://news.ycombinator.com/item?id=47511689", "by": "gverrilla", "date": "2026-03-24", "stance": "recommend", "quote": "playwright-cli and agent-browser are much much better, give them a try.", "excerpt": "playwright-cli and agent-browser are much much better, give them a try.", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: ProofShot \u2013 Give AI coding agents eyes to verify the UI they build"}, {"id": 760123648, "item_id": 47507728, "url": "https://news.ycombinator.com/item?id=47507728", "by": "esafak", "date": "2026-03-24", "stance": "recommend", "quote": "agent-browser itself has a skill for this", "excerpt": "It looks similar to agent-video, which is also based on agent-browser: https://www.mux.com/blog/agentic-video-screen-recording I don't think you need either, though, because agent-browser itself has a skill for this: https://github.com/vercel-labs/agent-browser/blob/main/skills/agent-browser/references/video-recording.md Maybe the author would like to compare the three.", "context": "", "use_case": "browser automation for agents", "switched_from": "", "story": "Show HN: ProofShot \u2013 Give AI coding agents eyes to verify the UI they build"}, {"id": 758362914, "item_id": 47397682, "url": "https://news.ycombinator.com/item?id=47397682", "by": "jedisct1", "date": "2026-03-16", "stance": "recommend", "quote": "it can be combined with agent-browser to get the best of both worlds", "excerpt": "For context extraction, Lightpanda is a really great option. Much faster than Chrome, and it comes with a built-in MCP server. However, it will not fill forms, etc. But it can be combined with agent-browser to get the best of both worlds: https://swival.dev/pages/web-browsing.html", "context": "", "use_case": "Filling forms in browser", "switched_from": "", "story": "Let your Coding Agent debug the browser session with Chrome DevTools MCP"}, {"id": 758278673, "item_id": 47392417, "url": "https://news.ycombinator.com/item?id=47392417", "by": "Torn", "date": "2026-03-15", "stance": "recommend", "quote": "https://agent-browser.dev/", "excerpt": "https://github.com/microsoft/playwright-cli and https://agent-browser.dev/", "context": "", "use_case": "", "switched_from": "", "story": "Let your Coding Agent debug the browser session with Chrome DevTools MCP"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 768438248, "item_id": 48027390, "url": "https://news.ycombinator.com/item?id=48027390", "by": "julius", "date": "2026-05-05", "stance": "warn", "quote": "instead of relying on all the wild ways agents currently hack into the browser", "excerpt": "Click coordinates. Agentic GUI is really annoying when the multi-modal agent cannot click on x,y coordinates. I tested Qwen3.6, Gemma4, Nemotron3-nano-omni. They fully hallucinate x,y coords. (did not try GLM-5V yet) GPT-5.5 can easily do it. But also Vocaela, a tiny 500M model, is quite good at it. Hope they improve the training for x,y clicking soon on the smallish multi-modals. Recently slopped a http service toge", "context": "", "use_case": "", "switched_from": "", "story": "GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents"}, {"id": 766305360, "item_id": 47894085, "url": "https://news.ycombinator.com/item?id=47894085", "by": "reaganhsu", "date": "2026-04-24", "stance": "warn", "quote": "agent-browser uses playwright so it struggles with things like cross-origin-iframes", "excerpt": "agent-browser uses playwright so it struggles with things like cross-origin-iframes - on the other hand, browser harness uses raw cdp, which is unrestrictive. It's discussed in this blog post! https://browser-use.com/posts/bitter-lesson-agent-harnesses", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Browser Harness \u2013 simplest way to give AI control of real browser"}]}], "who": [], "tags": [], "use_cases": ["browser automation for agents", "agent automated visual checks", "filling forms in browser", "agent browser automation", "letting coding agents test code", "browser automation for ai agents"], "compared": [{"slug": "playwright", "name": "Playwright", "co": 7, "switched_from": 0, "switched_to": 0}, {"slug": "proofshot", "name": "ProofShot", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "playwright-cli", "name": "Playwright CLI", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "google-chrome", "name": "Google Chrome", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "docker", "name": "Docker", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [{"id": 787848289, "item_id": 49240518, "url": "https://news.ycombinator.com/item?id=49240518", "by": "hboon", "date": "2026-08-10", "stance": "recommend", "quote": "I've started AgentBrowser because I didn't want agent-controlled browsers to steal the focus.", "excerpt": "I've been bootstrapping my indie SaaS and revitalised old macOS apps. Along the way, I built AgentControl, so I can work better with coding agents, in ways that suits my style and preferences. The past week, I've started AgentBrowser because I didn't want agent-controlled browsers to steal the focus. I use Safari for day to day browser stuff and Chrome just for dev. This combines them.", "context": "bootstrapping indie SaaS, macOS apps", "use_case": "agent-controlled browser without focus steal", "switched_from": "", "story": "Ask HN: What are you working on? (August 2026)"}], "threads": [{"url": "https://news.ycombinator.com/item?id=47499672", "title": "Show HN: ProofShot \u2013 Give AI coding agents eyes to verify the UI they build", "mentions": 5}, {"url": "https://news.ycombinator.com/item?id=47390817", "title": "Let your Coding Agent debug the browser session with Chrome DevTools MCP", "mentions": 4}, {"url": "https://news.ycombinator.com/item?id=47890841", "title": "Show HN: Browser Harness \u2013 simplest way to give AI control of real browser", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=47208398", "title": "MCP is dead. Long live the CLI", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=46901233", "title": "Show HN: Smooth CLI \u2013 Token-efficient browser for AI agents", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=46721474", "title": "Show HN: BrowserOS \u2013 \"Claude Cowork\" in the browser (open source)", "mentions": 2}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {"compare": 1, "neutral": 1}, "2026-02": {"compare": 2, "recommend": 3}, "2026-03": {"compare": 4, "recommend": 4, "neutral": 2}, "2026-04": {"warn": 1, "neutral": 1, "compare": 1}, "2026-05": {"compare": 1, "warn": 1, "neutral": 1}, "2026-06": {}, "2026-07": {}, "2026-08": {"recommend": 1}, "2026-09": {"compare": 1}, "2026-10": {}}, "quotes": [{"id": 796547857, "item_id": 49784241, "url": "https://news.ycombinator.com/item?id=49784241", "by": "wittydeveloper", "date": "2026-09-21", "stance": "compare", "quote": "whereas agent-browser is CLI-only", "excerpt": "Does \"agent-based\" here mean a CLI/Coding agent or software-level agents you built? I'd say that Stagehand is subtly faster for local use cases (batching, in-extension design) while covering both CLI (via https://browse.sh) and framework-level use, whereas agent-browser is CLI-only.", "context": "", "use_case": "", "switched_from": "", "story": "We made Playwright 2x faster and 80% more token efficient"}, {"id": 789554016, "item_id": 49347126, "url": "https://news.ycombinator.com/item?id=49347126", "by": "esafak", "date": "2026-08-18", "stance": "recommend", "quote": "agent-browser works fine", "excerpt": "agent-browser works fine, and it can use browser use as a provider: https://github.com/vercel-labs/agent-browser#browser-use I invite the author to add agent-browser to the comparison table.", "context": "", "use_case": "Browser automation for agents", "switched_from": "", "story": "NeoBrowser: An MCP server that drives real Chrome with your logged-in sessions"}, {"id": 771917089, "item_id": 48244818, "url": "https://news.ycombinator.com/item?id=48244818", "by": "nullbio", "date": "2026-05-22", "stance": "neutral", "quote": "have agents automate visual checks using something like agent-browser", "excerpt": "One thing I don't understand with all of these, is how they're handling different worktree infrastructure spin-up? For example, if I have a webapp, I want each of the worktrees to spin up its own infrastructure, and be accessible on its own unique local url, so that I can see the changes locally for each worktree, or I can have agents automate visual checks using something like agent-browser. Currently I use docker f", "context": "", "use_case": "agent automated visual checks", "switched_from": "", "story": "Open source Kanban desktop app that runs parallel agents on every card"}, {"id": 771917057, "item_id": 48244816, "url": "https://news.ycombinator.com/item?id=48244816", "by": "nullbio", "date": "2026-05-22", "stance": "neutral", "quote": "have agents automate visual checks using something like agent-browser", "excerpt": "One thing I don't understand with all of these, is how they're handling different worktree infrastructure spin-up? For example, if I have a webapp, I want each of the worktrees to spin up its own infrastructure, and be accessible on its own unique local url, so that I can see the changes locally for each worktree, or I can have agents automate visual checks using something like agent-browser. Currently I use docker f", "context": "", "use_case": "agent automated visual checks", "switched_from": "", "story": "Launch HN: Superset (YC P26) \u2013 IDE for the agents era"}, {"id": 768438248, "item_id": 48027390, "url": "https://news.ycombinator.com/item?id=48027390", "by": "julius", "date": "2026-05-05", "stance": "warn", "quote": "instead of relying on all the wild ways agents currently hack into the browser", "excerpt": "Click coordinates. Agentic GUI is really annoying when the multi-modal agent cannot click on x,y coordinates. I tested Qwen3.6, Gemma4, Nemotron3-nano-omni. They fully hallucinate x,y coords. (did not try GLM-5V yet) GPT-5.5 can easily do it. But also Vocaela, a tiny 500M model, is quite good at it. Hope they improve the training for x,y clicking soon on the smallish multi-modals. Recently slopped a http service toge", "context": "", "use_case": "", "switched_from": "", "story": "GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents"}, {"id": 768406000, "item_id": 48025375, "url": "https://news.ycombinator.com/item?id=48025375", "by": "sudb", "date": "2026-05-05", "stance": "compare", "quote": "vercel's agent-browser", "excerpt": "I'm pretty unsurprised that the vision agent did worse. I'd be interested in a comparison between the different tools that now exist to let LLMs drive browsers (e.g. vercel's agent-browser, the relatively new dev-browser[1], etc.) There are usecases where the vision agent is the more obvious, or only choice though, e.g. prorprietary/locked-down desktop apps that lack an automation layer. 1. https://github.com/SawyerH", "context": "", "use_case": "", "switched_from": "", "story": "Computer Use Is 45x More Expensive Than Structured APIs"}, {"id": 767302976, "item_id": 47956436, "url": "https://news.ycombinator.com/item?id=47956436", "by": "jschomay", "date": "2026-04-29", "stance": "compare", "quote": "You could use something like agent-browser and it would probably work just fine", "excerpt": "OP here: Thank you and I appreciate the thoughtful questions. To answer: 1) I used a text representation because it made sense for my game and let me \"render\" certain details in a more AI-friendly way, like the compact map. You could use something like agent-browser and it would probably work just fine, but I figured it added an extra layer of indirection that I didn't need, plus it would be a lot of screenshots! Bei", "context": "", "use_case": "", "switched_from": "", "story": "Letting AI play my game \u2013 building an agentic test harness to help play-testing"}, {"id": 766369232, "item_id": 47898077, "url": "https://news.ycombinator.com/item?id=47898077", "by": "tanishqkanc", "date": "2026-04-24", "stance": "neutral", "quote": "", "excerpt": "You should check out Libretto. It can take the playwright code and turn it into a script you can deploy", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Browser Harness \u2013 simplest way to give AI control of real browser"}, {"id": 766305360, "item_id": 47894085, "url": "https://news.ycombinator.com/item?id=47894085", "by": "reaganhsu", "date": "2026-04-24", "stance": "warn", "quote": "agent-browser uses playwright so it struggles with things like cross-origin-iframes", "excerpt": "agent-browser uses playwright so it struggles with things like cross-origin-iframes - on the other hand, browser harness uses raw cdp, which is unrestrictive. It's discussed in this blog post! https://browser-use.com/posts/bitter-lesson-agent-harnesses", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Browser Harness \u2013 simplest way to give AI control of real browser"}, {"id": 760203776, "item_id": 47512736, "url": "https://news.ycombinator.com/item?id=47512736", "by": "jberthom", "date": "2026-03-24", "stance": "neutral", "quote": "For web, agent-browser already uses compact element refs", "excerpt": "Yes for now focused on web but accessibility tree dumps seems like a good alternative to screenshots for native apps. For web, agent-browser already uses compact element refs, but for mobile the a11y approach could be way more efficient. Would you be open to sharing more about how you set that up?", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: ProofShot \u2013 Give AI coding agents eyes to verify the UI they build"}, {"id": 760203345, "item_id": 47512709, "url": "https://news.ycombinator.com/item?id=47512709", "by": "jberthom", "date": "2026-03-24", "stance": "neutral", "quote": "agent-browser gives you the browser primitives (click, navigate, screenshot)", "excerpt": "ProofShot sits on top of agent-browser. agent-browser gives you the browser primitives (click, navigate, screenshot). ProofShot adds the session stuff: starts recording, pipes your server logs, collects console errors with pattern matching for 10+ languages, trims the video, syncs timestamps, and bundles it all into a standalone viewer HTML. There\u2019s also proofshot pr which uploads everything to a GitHub PR comment. S", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: ProofShot \u2013 Give AI coding agents eyes to verify the UI they build"}, {"id": 760187025, "item_id": 47511689, "url": "https://news.ycombinator.com/item?id=47511689", "by": "gverrilla", "date": "2026-03-24", "stance": "recommend", "quote": "playwright-cli and agent-browser are much much better, give them a try.", "excerpt": "playwright-cli and agent-browser are much much better, give them a try.", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: ProofShot \u2013 Give AI coding agents eyes to verify the UI they build"}, {"id": 760131696, "item_id": 47508231, "url": "https://news.ycombinator.com/item?id=47508231", "by": "ting0", "date": "2026-03-24", "stance": "compare", "quote": "How does this compare to raw https://github.com/vercel-labs/agent-browser ?", "excerpt": "How does this compare to raw https://github.com/vercel-labs/agent-browser ?", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: ProofShot \u2013 Give AI coding agents eyes to verify the UI they build"}, {"id": 760123648, "item_id": 47507728, "url": "https://news.ycombinator.com/item?id=47507728", "by": "esafak", "date": "2026-03-24", "stance": "recommend", "quote": "agent-browser itself has a skill for this", "excerpt": "It looks similar to agent-video, which is also based on agent-browser: https://www.mux.com/blog/agentic-video-screen-recording I don't think you need either, though, because agent-browser itself has a skill for this: https://github.com/vercel-labs/agent-browser/blob/main/skills/agent-browser/references/video-recording.md Maybe the author would like to compare the three.", "context": "", "use_case": "browser automation for agents", "switched_from": "", "story": "Show HN: ProofShot \u2013 Give AI coding agents eyes to verify the UI they build"}, {"id": 758362914, "item_id": 47397682, "url": "https://news.ycombinator.com/item?id=47397682", "by": "jedisct1", "date": "2026-03-16", "stance": "recommend", "quote": "it can be combined with agent-browser to get the best of both worlds", "excerpt": "For context extraction, Lightpanda is a really great option. Much faster than Chrome, and it comes with a built-in MCP server. However, it will not fill forms, etc. But it can be combined with agent-browser to get the best of both worlds: https://swival.dev/pages/web-browsing.html", "context": "", "use_case": "Filling forms in browser", "switched_from": "", "story": "Let your Coding Agent debug the browser session with Chrome DevTools MCP"}, {"id": 758282848, "item_id": 47392678, "url": "https://news.ycombinator.com/item?id=47392678", "by": "dsrtslnd23", "date": "2026-03-15", "stance": "neutral", "quote": "you mean this one?", "excerpt": "you mean this one? https://github.com/vercel-labs/agent-browser", "context": "", "use_case": "", "switched_from": "", "story": "Let your Coding Agent debug the browser session with Chrome DevTools MCP"}, {"id": 758278673, "item_id": 47392417, "url": "https://news.ycombinator.com/item?id=47392417", "by": "Torn", "date": "2026-03-15", "stance": "recommend", "quote": "https://agent-browser.dev/", "excerpt": "https://github.com/microsoft/playwright-cli and https://agent-browser.dev/", "context": "", "use_case": "", "switched_from": "", "story": "Let your Coding Agent debug the browser session with Chrome DevTools MCP"}, {"id": 758259168, "item_id": 47391198, "url": "https://news.ycombinator.com/item?id=47391198", "by": "NiekvdMaas", "date": "2026-03-15", "stance": "recommend", "quote": "Also works nicely together with agent-browser", "excerpt": "Also works nicely together with agent-browser (https://github.com/vercel-labs/agent-browser) using --auto-connect", "context": "", "use_case": "", "switched_from": "", "story": "Let your Coding Agent debug the browser session with Chrome DevTools MCP"}, {"id": 757401808, "item_id": 47337613, "url": "https://news.ycombinator.com/item?id=47337613", "by": "esafak", "date": "2026-03-11", "stance": "compare", "quote": "How does it compare with https://agent-browser.dev/ ?", "excerpt": "How does it compare with https://agent-browser.dev/ ? It would be great if you could add it to your table: https://github.com/theredsix/agent-browser-protocol?#comparison", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Open-source browser for AI agents (~90% on Mind2Web)"}, {"id": 755839328, "item_id": 47239958, "url": "https://news.ycombinator.com/item?id=47239958", "by": "el_isma", "date": "2026-03-03", "stance": "compare", "quote": "How does it compare to https://github.com/vercel-labs/agent-browser ?", "excerpt": "How does it compare to https://github.com/vercel-labs/agent-browser ? Which also provides token efficient way to interact with the browser.", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Webact \u2013 token-efficient browser control for AI agents (GitHub)"}, {"id": 755559536, "item_id": 47222471, "url": "https://news.ycombinator.com/item?id=47222471", "by": "ejholmes", "date": "2026-03-02", "stance": "recommend", "quote": "handles persistent sessions just fine as a CLI", "excerpt": "I think that's a fair argument. I'd push back a bit on that being unique to MCP. Agent browser (https://github.com/vercel-labs/agent-browser) handles persistent sessions just fine as a CLI.", "context": "", "use_case": "", "switched_from": "", "story": "MCP is dead. Long live the CLI"}, {"id": 755365952, "item_id": 47210372, "url": "https://news.ycombinator.com/item?id=47210372", "by": "ejholmes", "date": "2026-03-01", "stance": "compare", "quote": "is a similar take here, and much better than the playwright MCP.", "excerpt": "Neato! https://github.com/vercel-labs/agent-browser is a similar take here, and much better than the playwright MCP.", "context": "", "use_case": "Browser automation for agents", "switched_from": "", "story": "MCP is dead. Long live the CLI"}, {"id": 754672992, "item_id": 47167062, "url": "https://news.ycombinator.com/item?id=47167062", "by": "esafak", "date": "2026-02-26", "stance": "recommend", "quote": "is a great CLI for agent-based browser automation", "excerpt": "No, they use it because there's a lot of training material. pro-tip: vercel's https://agent-browser.dev/ is a great CLI for agent-based browser automation.", "context": "", "use_case": "Agent browser automation", "switched_from": "", "story": "just-bash: Bash for Agents"}, {"id": 752047089, "item_id": 47002943, "url": "https://news.ycombinator.com/item?id=47002943", "by": "simonw", "date": "2026-02-13", "stance": "recommend", "quote": "Did you tell it to use Playwright or agent-browser or anything like that?", "excerpt": "How did you have it testing its code changes? Did you tell it to use Playwright or agent-browser or anything like that? If coding agents can't test the code as they're editing it they're no different from pasting your entire codebase into ChatGPT and crossing your fingers. At one point you mention it hadn't run \"npm test\" - did it run that once you directly told it to? I start every one of my coding agent sessions wi", "context": "", "use_case": "letting coding agents test code", "switched_from": "", "story": "I asked Claude Code to remove jQuery. It failed miserably"}, {"id": 751470641, "item_id": 46966915, "url": "https://news.ycombinator.com/item?id=46966915", "by": "simlevesque", "date": "2026-02-10", "stance": "compare", "quote": "agent-browser: https://github.com/vercel-labs/agent-browser", "excerpt": "rodney seems to be pretty much the same as agent-browser: https://github.com/vercel-labs/agent-browser", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Showboat and Rodney, so agents can demo what they've built"}, {"id": 750715168, "item_id": 46919698, "url": "https://news.ycombinator.com/item?id=46919698", "by": "threecheese", "date": "2026-02-06", "stance": "recommend", "quote": "Vercel also released a similar tool with a unique interface/dsl", "excerpt": "Vercel also released a similar tool with a unique interface/dsl - https://github.com/vercel-labs/agent-browser > agent-browser click \"#submit\" > agent-browser fill \"#email\" \"test@example.com\" > agent-browser find role button click --name \"Submit\" I appreciate that there\u2019s innovation in the space, we will get closer to the interface that\u2019s most appropriate for models to tool-call. I\u2019m going to check your link out, sou", "context": "", "use_case": "Browser automation for AI agents", "switched_from": "", "story": "Show HN: Smooth CLI \u2013 Token-efficient browser for AI agents"}, {"id": 750623265, "item_id": 46913954, "url": "https://news.ycombinator.com/item?id=46913954", "by": "antves", "date": "2026-02-06", "stance": "compare", "quote": "compared to the CLI interface that agent-browser exposes", "excerpt": "Thanks for asking! There are a few core differences: 1. we expose a higher level interface which allows the agent to think about what to do as opposed to what to do 2. we developed a token-efficient representation of the webpages that combines both visual and textual elements, heavily optimized for what LLMs are good at. 3. because we control the agentic loop, it also means that we can do fancy things on contextual i", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Smooth CLI \u2013 Token-efficient browser for AI agents"}, {"id": 747772369, "item_id": 46735773, "url": "https://news.ycombinator.com/item?id=46735773", "by": "felarof", "date": "2026-01-23", "stance": "neutral", "quote": "BrowserOS should work with agent browser as well in headless mode!", "excerpt": "BrowserOS should work with agent browser as well in headless mode! On top of that, if you want headful mode, you can use our MCP server https://docs.browseros.com/features/use-with-claude-code Would love to understand your use case! You can hit me up at nithin[at]browseros.com", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: BrowserOS \u2013 \"Claude Cowork\" in the browser (open source)"}, {"id": 747688528, "item_id": 46730533, "url": "https://news.ycombinator.com/item?id=46730533", "by": "thawab", "date": "2026-01-23", "stance": "compare", "quote": "How does it compare to using https://github.com/vercel-labs/agent-browser", "excerpt": "Thanks a lot, i wanted to ask about the headless agent use case: How does it compare to using https://github.com/vercel-labs/agent-browser", "context": "", "use_case": "Headless browser automation for agents", "switched_from": "", "story": "Show HN: BrowserOS \u2013 \"Claude Cowork\" in the browser (open source)"}]}