PS4 is quite the engineering marvel


Recommended Posts

I wouldn't judge anything relating to performance, bugs or heating until both consoles are released and they can be properly analysed in their finished state.

I don't see why anyone would presume the PS4 should have heating issues though. Devices get smaller, electronics get more power/heat efficient, heatsinks have improved etc. My smartphone has considerably more power than my first computer without any fans at all. My Mum's ultrabook (GPU aside) is as powerful as my desktop, as thin as my smartphone and has just one small fan. With a well thought out internal layout for good airflow, decent heatsinks and heat-efficient electronics, there is no reason why the PS4 should suffer heating problems. Proof will be in the pudding though.

Apples to oranges with framerates? What?

 

Even the 1st party game Killzone barely hit 30FPS according to that article. That could mean quite a few things. The hardware is not stable, having problems with heat, or the developers are really struggling with it. It also could be a mix. Judging by some of the jumps from the E3 demos, I'd say its a mix of the hardware and software. You've got to remember, MS are the king of anything developer, API's SDK's etc. People are also quick to jump on the 50% bandwagon but that claim is completely false, along with the rumors of the specifications anyway.

 

I hope Sony do create a stable console at launch. An internal PSU is a nice consumer benefit but an engineering nightmare.

 

 

Yes, comparing the framerates of COMPLETELY DIFFERENT GAMES is as "apples to oranges" as you can get.

 

Example: Comparing the framerate of BF4 on the xbone and ps4 = valid comparison. Comparing the framerates of Killzone to Halo 5 would be totally irrelevant because they aren't even the same game.

 

If you cannot understand that then I cannot help you.

 

I am sure both consoles will end up launching with a mix of 30/60 fps games. Saying the PS4 has inferior hardware based on some pre-release speculation is silly, and comparing the framerates of different games is meaningless. Technical inconsistencies and games not taking full advantage of the hardware with launch games is typical of all consoles, same happened with 360 and ps3, compare the graphics and performance of their launch titles to the later ones. Its "launch game syndrome"

Yes, comparing the framerates of COMPLETELY DIFFERENT GAMES is as "apples to oranges" as you can get. If you cannot understand that then I cannot help you.

 

I am sure both consoles will end up launching with a mix of 30/60 fps games. Saying the PS4 has inferior hardware based on some pre-release speculation is silly, and comparing the framerates of different games is meaningless.

His point is pretty simple: Why is there not a single 1080p 60fps demo of a PS4 game yet? You are being obtuse with different games argument.

  • Like 1

His point is pretty simple: Why is there not a single 1080p 60fps demo of a PS4 game yet? You are being obtuse with different games argument.

What this guy said.

 

If 1st party developers for the X1 all can get 1080p 60fps, why can't 1st party Sony developers?

 

Also, BF4 was also stated to be 60FPS on the X1.

  • Like 2

I wouldn't judge anything relating to performance, bugs or heating until both consoles are released and they can be properly analysed in their finished state.

I don't see why anyone would presume the PS4 should have heating issues though. Devices get smaller, electronics get more power/heat efficient, heatsinks have improved etc. My smartphone has considerably more power than my first computer without any fans at all. My Mum's ultrabook (GPU aside) is as powerful as my desktop, as thin as my smartphone and has just one small fan. With a well thought out internal layout for good airflow, decent heatsinks and heat-efficient electronics, there is no reason why the PS4 should suffer heating problems. Proof will be in the pudding though.

in the article the devs that spoke to eurogamer said they were targeting 30fps, non was targeting 60fps on the ps4. I think this is a telling piece of information as to how far devs have gotten with the system even though it was rumored that the ps4 had started developing way before the xbox one. so if that was the case then devs should've had a better understanding of the system by now I should be able to pull more performance out of the system.

Knack is one of those 1st party games that basically started WITH the ps4 development and this game should be pushing at least 30fps, but so far it's in the 20fps and lower range.

 

metal gear solid 5: phantom pain dev, Kojima Productions is targeting 1080p@60fps on the xbox one.

http://www.eurogamer.net/articles/digitalfoundry-watch-mgs5-at-60fps

in the article the devs that spoke to eurogamer said they were targeting 30fps, non was targeting 60fps on the ps4. I think this is a telling piece of information as to how far devs have gotten with the system even though it was rumored that the ps4 had started developing way before the xbox one. so if that was the case then devs should've had a better understanding of the system by now I should be able to pull more performance out of the system.

Knack is one of those 1st party games that basically started WITH the ps4 development and this game should be pushing at least 30fps, but so far it's in the 20fps and lower range.

 

metal gear solid 5: phantom pain dev, Kojima Productions is targeting 1080p@60fps on the xbox one.

http://www.eurogamer.net/articles/digitalfoundry-watch-mgs5-at-60fps

Wow. That video was exquisite.

 

To be honest, with this next-generation hardware, I wouldn't expect anything less than 60fps.

Yes, comparing the framerates of COMPLETELY DIFFERENT GAMES is as "apples to oranges" as you can get.

 

Example: Comparing the framerate of BF4 on the xbone and ps4 = valid comparison. Comparing the framerates of Killzone to Halo 5 would be totally irrelevant because they aren't even the same game.

 

If you cannot understand that then I cannot help you.

 

I am sure both consoles will end up launching with a mix of 30/60 fps games. Saying the PS4 has inferior hardware based on some pre-release speculation is silly, and comparing the framerates of different games is meaningless. Technical inconsistencies and games not taking full advantage of the hardware with launch games is typical of all consoles, same happened with 360 and ps3, compare the graphics and performance of their launch titles to the later ones. Its "launch game syndrome"

 

 

Then again, he compared massively graphic games with the rather simplistic Knack. MS managed 60fps at 1080p on their first party titles of photoreal high speed graphics. Sony didn't manage a steady 30 on a lighthearted simple game like Knack... 

 

sometimes you can compare apples to oranges. especially when you're comparing the size of them, and not the taste or color. 

 

You're missing or ignoring the point though it's not about comparing the graphics or anything like that, it's about the fact that the first part developers developing the launch titles on the Sony platform isn't capable of reaching a steady 30 FPS even. whereas MS is hitting steady 60 on theirs. You should see the issue there.

in the article the devs that spoke to eurogamer said they were targeting 30fps, non was targeting 60fps on the ps4. I think this is a telling piece of information as to how far devs have gotten with the system even though it was rumored that the ps4 had started developing way before the xbox one. so if that was the case then devs should've had a better understanding of the system by now I should be able to pull more performance out of the system.

Knack is one of those 1st party games that basically started WITH the ps4 development and this game should be pushing at least 30fps, but so far it's in the 20fps and lower range.

 

metal gear solid 5: phantom pain dev, Kojima Productions is targeting 1080p@60fps on the xbox one.

http://www.eurogamer.net/articles/digitalfoundry-watch-mgs5-at-60fps

 

 

I suspect the main issue is simply about dev kits and dev tools.

 

Xbox devs are using familiar and well developed dev tools running on the directx platform. Sony has yet again changed platforms and their devs have to learn how to program for it all over again. And we all know how good sony is at making dev tools to start with :/

in the article the devs that spoke to eurogamer said they were targeting 30fps, non was targeting 60fps on the ps4. I think this is a telling piece of information as to how far devs have gotten with the system even though it was rumored that the ps4 had started developing way before the xbox one. so if that was the case then devs should've had a better understanding of the system by now I should be able to pull more performance out of the system.

Knack is one of those 1st party games that basically started WITH the ps4 development and this game should be pushing at least 30fps, but so far it's in the 20fps and lower range.

 

metal gear solid 5: phantom pain dev, Kojima Productions is targeting 1080p@60fps on the xbox one.

http://www.eurogamer.net/articles/digitalfoundry-watch-mgs5-at-60fps

It isn't telling at all, it just says they're targeting 30fps. Targeting 30fps does not make it incapable of 60fps.

 

Frame drops at this stage are nothing to be concerned about IMHO. From my (albeit limited) knowledge of how games are developed, the demos shown off at E3 were likely older versions of the games. Plus there is still a few months of time left to do final optimizations and bug fixes. I'd be very surprised if there were any performance issues come launch for either console.

It isn't telling at all, it just says they're targeting 30fps. Targeting 30fps does not make it incapable of 60fps.

 

Frame drops at this stage are nothing to be concerned about IMHO. From my (albeit limited) knowledge of how games are developed, the demos shown off at E3 were likely older versions of the games. Plus there is still a few months of time left to do final optimizations and bug fixes. I'd be very surprised if there were any performance issues come launch for either console.

But prevailing wisdom is that Xbox One is lagging behind in development so...

Then again, he compared massively graphic games with the rather simplistic Knack. MS managed 60fps at 1080p on their first party titles of photoreal high speed graphics. Sony didn't manage a steady 30 on a lighthearted simple game like Knack... 

 

sometimes you can compare apples to oranges. especially when you're comparing the size of them, and not the taste or color. 

 

You're missing or ignoring the point though it's not about comparing the graphics or anything like that, it's about the fact that the first part developers developing the launch titles on the Sony platform isn't capable of reaching a steady 30 FPS even. whereas MS is hitting steady 60 on theirs. You should see the issue there.

 

 

I suspect the main issue is simply about dev kits and dev tools.

 

Xbox devs are using familiar and well developed dev tools running on the directx platform. Sony has yet again changed platforms and their devs have to learn how to program for it all over again. And we all know how good sony is at making dev tools to start with :/

 

 

dev tools and kits might actually play a role in performance issues that's going on with the ps4 but I think it's actually goes a lot deeper than that all the way to the hardware level. let me explain my view: 

even though the ps4 has GDDR5 memory that has a huge bandwidth limit available it's just located too far from the gpu and cpu that it feeds all the way over the north bridge. there's no large on chip memory cache.

 

while on the other hand the xbox has a large on die memory cache along with data move units (that seems to completely sidestep the north bridge) so devs can keep the cpu and gpu full much faster.

 

on the ps4 side is like having a huge highway but your cars and trucks aren't moving fast enough over the bridge

while on the xbox one side moves a bit slower, but once they reach the express lane (on die cache) it's almost as if they teleport to their destination. plus the data move shuttles

dev tools and kits might actually play a role in performance issues that's going on with the ps4 but I think it's actually goes a lot deeper than that all the way to the hardware level. let me explain my view: 

even though the ps4 has GDDR5 memory that has a huge bandwidth limit available it's just located too far from the gpu and cpu that it feeds all the way over the north bridge. there's no large on chip memory cache.

 

while on the other hand the xbox has a large on die memory cache along with data move units (that seems to completely sidestep the north bridge) so devs can keep the cpu and gpu full much faster.

 

on the ps4 side is like having a huge highway but your cars and trucks aren't moving fast enough over the bridge

while on the xbox one side moves a bit slower, but once they reach the express lane (on die cache) it's almost as if they teleport to their destination. plus the data move shuttles

 

Couple things wrong with this post here.

 

Firstly the distance between the components would be a matter of latency, not bandwidth. Secondly, AMD haven't used a Front-Side Bus design since the Athlon XP hit EOL - the memory controller is located on the APU/CPU die and communicates directly to main memory.

But prevailing wisdom is that Xbox One is lagging behind in development so...

And I took those comments with the same pinch of salt that I'm taking these comments. There's a lot of things that can be judged about the consoles already, but performance, overheating issues, etc are not among them. Until everything is "final" we can't get a clear picture whatsoever.

Couple things wrong with this post here.

 

Firstly the distance between the components would be a matter of latency, not bandwidth. Secondly, AMD haven't used a Front-Side Bus design since the Athlon XP hit EOL - the memory controller is located on the APU/CPU die and communicates directly to main memory.

 

the north bridge is integrated doesn't mean it's not there.

I wasn't anything bad about the bandwidth I was talking the data traveling on those large lanes that they can't keep the cpu/gpu fed properly. this was the reason I think sony opened a 3rd lane

the north bridge is integrated doesn't mean it's not there.

I wasn't anything bad about the bandwidth I was talking the data traveling on those large lanes that they can't keep the cpu/gpu fed properly. this was the reason I think sony opened a 3rd lane

 

There is no such thing as a northbridge component, it's an old designation for a on-motherboard chip that traditionally contained the memory controller, other misc onboard device controllers (AGP/PCI) and connected to the CPU via the FSB.

 

The Athlon 64 killed the northbridge / FSB and moved the memory controller to the CPU die, while implementing HyperTransport as a replacement for the now defunct FSB.

 

Even if there was such a thing as a discrete northbridge component, it would not be involved with main memory as the FSB is gone.

There is no such thing as a northbridge component, it's an old designation for a on-motherboard chip that traditionally contained the memory controller, other misc onboard device controllers (AGP/PCI) and connected to the CPU via the FSB.

 

The Athlon 64 killed the northbridge / FSB and moved the memory controller to the CPU die, while implementing HyperTransport as a replacement for the now defunct FSB.

 

Even if there was such a thing as a discrete northbridge component, it would not be involved with main memory as the FSB is gone.

 

you might think you know what you're talking about but you're missing a lot. the north bridge is still there it's integrated but it's still there. the reason why it's integrated is to minimize the followthrough distance between other components and the actual cpu/gpu which increased throughput and latency when compared to having the northbridge off die. anyway the component wasn't eliminated, it was just moved.

 

but just a little searching about the new architecture can go a long way:

http://www.anandtech.com/show/6976/amds-jaguar-architecture-the-cpu-powering-xbox-one-playstation-4-kabini-temash

you'll notice there is a northbridge.

 

anyways, I think I know a little about the amd Athlon intel p4 history and about their architecture.

His point is pretty simple: Why is there not a single 1080p 60fps demo of a PS4 game yet? You are being obtuse with different games argument.

 

Just curious, I thought all of the XBox One demos were confirmed to be running on a PC where they not? So are there really technically any demos of XBox one games actually running on a One? 

 

You are all trying to tell me that you honestly think when looking at the specs of both consoles side by side that if one is capable of doing 60 FPS the other is not? Really? The specs are nearly identical. It is honestly crazy to think the games will not be. Somehow you all have yourselves convinced that the custom cpu of the One is so much more powerful than the PS4's CPU, which from my understanding is the same AMD architecture? Seriously???

  • Like 3

Just curious, I thought all of the XBox One demos were confirmed to be running on a PC where they not? So are there really technically any demos of XBox one games actually running on a One? 

 

You are all trying to tell me that you honestly think when looking at the specs of both consoles side by side that if one is capable of doing 60 FPS the other is not? Really? The specs are nearly identical. It is honestly crazy to think the games will not be. Somehow you all have yourselves convinced that the custom cpu of the One is so much more powerful than the PS4's CPU, which from my understanding is the same AMD architecture? Seriously???

According to this, they have seen games running on actual Xbox One hardware.

 

I agree with the rest of what you said, but it is still puzzling at this stage.

Apples to oranges with framerates? What?

 

Even the 1st party game Killzone barely hit 30FPS according to that article. That could mean quite a few things. The hardware is not stable, having problems with heat, or the developers are really struggling with it. It also could be a mix. Judging by some of the jumps from the E3 demos, I'd say its a mix of the hardware and software. You've got to remember, MS are the king of anything developer, API's SDK's etc. People are also quick to jump on the 50% bandwagon but that claim is completely false, along with the rumors of the specifications anyway.

 

I hope Sony do create a stable console at launch. An internal PSU is a nice consumer benefit but an engineering nightmare.

 

That is very very true, but it doesn't mean to say that the hardware is better. It simply means the hardware is easier to work with. Those are two very different things.

 

So alternatively, if the PS4 is difficult to get to grips with, does it mean the hardware is lacking? Or maybe that developers just need more time to get to know it and it's capabilities. Just look at Naughty Dog's progression from Uncharted 1 to TLoU.

Just curious, I thought all of the XBox One demos were confirmed to be running on a PC where they not? So are there really technically any demos of XBox one games actually running on a One? 

 

You bring up a valid point, but I think we can assume these games were created to run on the dev hardware, so it would be a huge waste of time for something to be developed that couldn't be run on the actual hardware.  I'm sure the actual hardware is still being finalized, so it simply made more sense for them to run the previews on comparable hardware that they know will work.  Just a thought.

you might think you know what you're talking about but you're missing a lot. the north bridge is still there it's integrated but it's still there. the reason why it's integrated is to minimize the followthrough distance between other components and the actual cpu/gpu which increased throughput and latency when compared to having the northbridge off die. anyway the component wasn't eliminated, it was just moved.

 

but just a little searching about the new architecture can go a long way:

http://www.anandtech.com/show/6976/amds-jaguar-architecture-the-cpu-powering-xbox-one-playstation-4-kabini-temash

you'll notice there is a northbridge.

 

anyways, I think I know a little about the amd Athlon intel p4 history and about their architecture.

 

As I just said, there is no such thing as a discrete Northbridge component, it's nothing more than a label for a grouping of components.

 

The premise of your argument is based on the notion of the old FSB-based CPU/Northbridge setup, the article you linked to shows nothing fundamentally different from the original Athlon 64 design other than the inclusion of a GPU which shares access to the on-die memory controller. The only change other than that is labelling.

Just curious, I thought all of the XBox One demos were confirmed to be running on a PC where they not? So are there really technically any demos of XBox one games actually running on a One? 

 

You are all trying to tell me that you honestly think when looking at the specs of both consoles side by side that if one is capable of doing 60 FPS the other is not? Really? The specs are nearly identical. It is honestly crazy to think the games will not be. Somehow you all have yourselves convinced that the custom cpu of the One is so much more powerful than the PS4's CPU, which from my understanding is the same AMD architecture? Seriously???

1. I am just explaining someone else's point

2. This is factually wrong (see how FUD works?). Only Lococycle was running on PCs. Forza, Ryse, KI all were running on XB1 hardware/devkit.

According to this, they have seen games running on actual Xbox One hardware.

 

I agree with the rest of what you said, but it is still puzzling at this stage.

Is it that far off to think the Xbox hardware is more efficiently designed to work with the software? Also from what I recall, Xbox One uses Direct X 11.1 API's.  MS has a vast library of API's and software's to choose from and refine which includes a pretty powerful kernel. That kernel is getting smaller and smaller with each new version. Lets also not forget that Microsoft has 32MB of ESRAM embedded onto their die, Sony does not. Maybe this is where they are seeing gains in performance?

 

What graphics API does the PS4 use? From what I can tell, Sony's software library is rather small, and they have to make it up as they go. Also, there is a reason PC's use DDR3 rather than GDDR5. It's not good at handling computational tasks outside of graphics.

Just curious, I thought all of the XBox One demos were confirmed to be running on a PC where they not? So are there really technically any demos of XBox one games actually running on a One? 

 

You are all trying to tell me that you honestly think when looking at the specs of both consoles side by side that if one is capable of doing 60 FPS the other is not? Really? The specs are nearly identical. It is honestly crazy to think the games will not be. Somehow you all have yourselves convinced that the custom cpu of the One is so much more powerful than the PS4's CPU, which from my understanding is the same AMD architecture? Seriously???

 

 

Nope, ONE acrade game was demoed on the developers windows developer box. the other demos ran Xbox One dev kits or Xbox One pre production models. 

I was talking about 1st party titles, if any dev was to be able to hit it, it should've been 1st party devs correct?

Respawn isn't first party.

 

What graphics API does the PS4 use? 

http://www.geek.com/games/sony-iimprove-directx-11-for-the-ps4-blu-ray-1544364/

 

The PS4 sees Sony move to a 64-bit x86 chip architecture, which will be music to the ears of developers, especially those used to working on PC games. The good news doesn?t stop there, though. Developers will be able to take advantage of Microsoft?s latest industry standardDirectX API ? DirectX 11.1, but Sony has taken the time to improve upon it, pushing the feature set beyond what is available for PC games development.

 

Those improvements include better shader pipeline access, improved debugging support features out the box, and much lower level access to the system hardware enabling developers to do ?more cool things.? That?s achieved not only through an modified DirectX 11.1 API, but also a secondary low-level API specifically for the PS4 hardware.

 

This topic is now closed to further replies.
  • Recently Browsing   0 members

    • No registered users viewing this page.
  • Posts

    • I'm still on Windows 10 22H2 because I didn't want to deal with all the issues in Windows 11, so I waited almost a week before installing the latest Patch Tuesday update (KB5094127), I went ahead and did it, and it was a huge mistake—ever since then, my File Explorer has seen a performance drop of about 30% when transferring large files... Once again, Microsoft has outdone itself! This update cannot be uninstalled, either through the Control Panel (via Settings) or by accessing Advanced Startup Options. The only possible alternative would be to use system restore points, but I’d have to reinstall all app and driver updates (and there’s no guarantee it would work). Or there’s the “nuclear option” of a in-place repair without losing files or apps, but even then, all my customizations would be lost! Microsoft just can’t help but mess everything up! Way to go, Microsoft! But I still don’t want your c****y Windows 11!
    • Microsoft: Windows 11 could finally solve a major issue across AMD, Nvidia, and Intel GPUs by Sayan Sen While Microsoft has been trying to improve it, Windows 11 is definitely not flawless, as even today some issues are taking a year to publicly acknowledge. However, one area of trouble that may finally see much better results soon is graphics driver crashes. Work on graphics driver timeouts, also called Timeout and Detection Recovery (TDR), is not new as the latest WDDM 3.2 also has specific improvements regarding it. Windows Display Driver Model (WDDM) version 3.2 is supported on Windows 11 24H2 and 25H2. However, with the upcoming version 26H2, TDR crash diagnosis could go to the next level as Microsoft is introducing a new DirectX 12 API feature called "DirectX Dump Files". Similar to how system memory dump files work when a system crashes or freezes or encounters any such major issue, DirectX Dump Files (DDF) will essentially record a snapshot of the GPU execution right at the moment a graphics-related crash or hang or freeze occurs, so that developers can better understand and diagnoze these TDR and timeout detection errors. The dump will be available as a .dxdmp file for analysis and it will be a comprehensive dump file generated with detailed insights about the hardware, drivers, Windows, as well as the affected application. This should be another welcome change in this department. Earlier at GDC 2026, when the technology was first debuted, Microsoft had shared more details regarding it. The company had explained how DDF is designed to gather data from every layer of the graphics stack into a single file, eliminating the need for developers to manually correlate logs from multiple tools. As mentioned above, the dump can contain a lot of useful details like GPU hardware state information such as register values, shader program counters, page fault virtual addresses, shader memory data, and command buffers. Alongside that, it also captures DirectX runtime and kernel information, including D3D objects, pipeline state objects, device error data, adapter details, and CPU call stacks. Microsoft says the feature has been built around two primary use cases: retail device removals and local device removals. The former allows developers to collect crash information from end users' systems in the field, while the latter helps QA teams and developers investigate issues on test machines. Developers will also be able to include up to 2 MB of custom application data through new D3D12 APIs, providing additional context for troubleshooting. In addition, Microsoft is introducing three dump collection modes ranging from zero-overhead capture, which has no runtime performance impact on supported hardware, to higher-detail modes that collect more vendor-specific debugging data. On compatible Tier 2 hardware, zero-overhead dumps will be enabled by default, meaning developers may begin receiving useful crash diagnostics without making any code changes. The table below explains the three tiers: Tier Description NO_OVERHEAD Enables crash capture with no runtime cost and is suitable for broad deployment MEDIUM_OVERHEAD Provides a balance, capturing additional diagnostic data with moderate impact HIGH_OVERHEAD Collects the most detailed GPU and driver state available, enabling deeper investigation at the cost of higher runtime overhead In terms of availability, the company expects broader release to be around the fall of 2026, which should be right around the time when Windows 11 version 26H2 lands. Right now, DirectX Dump Files are available as a preview and currently, only AMD has the compatible AgilitySDK Developer Preview driver version 26.10.07.02. You can find the official announcement post here on Microsoft's website.
    • And with SO much better perf than the laggy mess that is Files.
    • BrowserOS 0.46.0 by Razvan Serea BrowserOS is a free, open-source Chromium-based browser that runs AI agents natively, offering a smarter, more productive browsing experience. It supports Chrome extensions and integrates AI agents to automate tasks, fill forms, and streamline workflows. Your data stays on your computer: you can use your own API keys or run local models via Ollama, making it a privacy-first alternative to tools like Perplexity, Comet, or Dia. With built-in productivity tools and app integrations, BrowserOS boosts efficiency while keeping control firmly in your hands. Being Chromium-based, BrowserOS lets you effortlessly import your bookmarks, passwords, and Chrome extensions in just a few clicks. BrowserOS works with OpenAI GPT models, Anthropic Claude, Google Gemini, and local AI models via Ollama or LMStudio. You can use your own API keys and effortlessly switch between providers. BrowserOS Agent Your AI productivity assistant that organizes and manages your browsing effortlessly Quickly list, group, or close tabs Save and resume browsing sessions Search your history and organize bookmarks Switch instantly to the tab you need BrowserOS Navigator – Automate web tasks with ease Navigate websites and search automatically Interact with pages without manual effort Handle repetitive tasks in seconds What makes BrowserOS special Feels like home - same familiar interface as Google Chrome, works with all your extensions AI agents that run on YOUR browser, not in the cloud Privacy first - bring your own keys or use local models with Ollama. Your browsing history stays on your computer Open source and community driven - see exactly what's happening under the hood MCP store to one-click install popular MCPs and use them directly in the browser bar (coming soon) Built-in AI ad blocker that works across more scenarios! BrowserOS 0.46.0 changelog: Run Claude Code & Codex right in your browser — We've extended the agent harness to bring full coding agents into BrowserOS. Claude Code and Codex now come bundled and plug straight into the assistant, so you can drive your browser with the agent — and the subscription — you already use. A brand new experience — A redesigned new tab, a calmer composer, and a rebuilt command center for switching between agents. The whole assistant is cleaner, faster to reach, and easier to live in. New MCP tools — We rebuilt the browser tool surface from the ground up — a tighter, more reliable set of tools for agents to drive the browser. Plus one-click install of BrowserOS as an MCP server into the agents you already run, with automatic URL sync. Chromium 148 — Updated to the latest Chromium base with all recent upstream fixes and security patches. Streamlined — We've pulled back a few features that weren't getting much use — Skills, Soul, and Memory — so we can focus and ship better versions of them soon. Download: BrowserOS 0.46.0 | 181.0 MB (Open Source) Download: BrowserOS for macOS | 485.0 MB Links: BrowserOS Homepage | Github | Screenshot Get alerted to all of our Software updates on Twitter at @NeowinSoftware
  • Recent Achievements

    • Week One Done
      Jordan Smith earned a badge
      Week One Done
    • Reacting Well
      BizSAR earned a badge
      Reacting Well
    • First Post
      AndreaB earned a badge
      First Post
    • Week One Done
      Huge Trailer earned a badge
      Week One Done
    • Week One Done
      Classifyskilleducation earned a badge
      Week One Done
  • Popular Contributors

    1. 1
      +primortal
      590
    2. 2
      +Edouard
      186
    3. 3
      PsYcHoKiLLa
      76
    4. 4
      Michael Scrip
      73
    5. 5
      Steven P.
      67
  • Tell a friend

    Love Neowin? Tell a friend!