Anthropic's Claude Code Goes Web-Based: A Game-Changer for AI-Assisted Coding

Claude Code gets a web version -- but it's the new sandboxing that really matters

Anthropic has added web and mobile interfaces for Claude Code, its immensely popular command-line interface (CLI) agentic AI coding tool. The web interface appears to be well-baked at launch, but the mobile version is limited to iOS and is in an earlier stage of development. The web version of Claude Code can be given access to a GitHub repository. Once that's done, developers can give it general marching orders like "add real-time inventory tracking to the dashboard." As with the CLI version, it gets to work, with updates along the way approximating where it's at and what it's doing. The web interface supports the recently implemented Claude Code capability to take suggestions or requested changes while it's in the middle of working on a task. (Previously, if you saw it doing something wrong or missing something, you often had to cancel and start over.) Developers can run multiple sessions at once and switch between them as needed; they're listed in a left-side panel in the interface. Alongside this web and mobile rollout, Anthropic has also introduced a new sandboxing runtime to Claude Code that, along with other things, aims to make the experience both more secure and lower friction. In the past, Claude Code worked by asking permission before making most changes and steps along the way. Now, it can instead be given permissions for specific file system folders and network servers. That means fewer approval steps, but it's also more secure overall against prompt injection and other risks. According to Anthropic's engineering blog, the new network isolation approach only allows Internet access "through a unix domain socket connected to a proxy server running outside the sandbox. ... This proxy server enforces restrictions on the domains that a process can connect to, and handles user confirmation for newly requested domains." Additionally, users can customize the proxy to set their own rules for outgoing traffic. This way, the coding agent can do things like fetch npm packages from approved sources, but without carte blanche for communicating with the outside world, and without badgering the user with constant approvals. For many developers, these additions are more significant than the availability of web or mobile interfaces. They allow Claude Code agents to operate more independently without as many detailed, line-by-line approvals. That's more convenient, but it's a double-edged sword, as it will also make code review even more important. One of the strengths of the too-many-approvals approach was that it made sure developers were still looking closely at every little change. Now it might be a little bit easier to miss Claude Code making a bad call. The new features are available in beta now as a research preview, and they are available to Claude users with Pro or Max subscriptions.

Anthropic brings Claude Code to the web | TechCrunch

Anthropic launched a web app on Monday for its viral AI coding assistant, Claude Code, which lets developers create and manage several AI coding agents from their browser. Claude Code for web is now rolling out to subscribers to Anthropic's $20-per-month Pro plan, as well as its $100 and $200-per-month Max plans. Pro and Max users can access Claude Code on the web by navigating to claude.ai (the same website for Anthropic's consumer chatbot) and clicking into the "Code" tab. The launch marks Anthropic's latest attempt to evolve Claude Code beyond a command-line interface (CLI) tool that developers access from a terminal. By putting Claude Code on the web, Anthropic hopes developers will spin up AI coding agents in more places. It's increasingly competitive for tech companies trying to make their AI coding tools stand out. While Microsoft's GitHub Copilot once dominated the space, Cursor, Google, OpenAI, and Anthropic now have highly performant AI coding tools of their own -- many of them already available on the web. That said, Claude Code is arguably one of the most popular. Anthropic's flagship coding tool has grown 10x in users since its broader launch in May, and the product now accounts for more than $500 million of the company's revenue on an annualized basis. Anthropic Product Manager Cat Wu tells TechCrunch in an interview that she attributes a large part of Claude Code's success to the company's AI models, which have become a favorite among developers in recent years. However, Wu also says the Claude Code team deliberately tries to "sprinkle in some fun" to the product wherever they can. Wu said that Anthropic will continue to put Claude Code in more places, but the terminal will likely remain the home base for their AI coding product. "As we look forward, one of our key focuses is making sure the CLI product is the most intelligent and customizable way for you to use coding agents," said Wu. "But we're continuing to put Claude Code everywhere, helping it meet developers wherever they are. Web and mobile are a big step in this direction." Anthropic claims that 90% of the Claude Code product itself is written by the company's AI models. Wu, who was previously an engineer, says that she rarely ever sits down at a keyboard to write code anymore, and mostly just reviews Claude Code's outputs. Early AI coding tools worked like an autocomplete tool, finishing lines of code as developers wrote them. But the agentic generation of AI coding tools -- including Claude Code -- allow developers to spin up agents that work autonomously. This shift has made millions of software engineers act more like managers of AI coding assistants in their day-to-day jobs. The change has not been welcome to every developer. One recent study found that some engineers were actually slower when using AI coding tools like Cursor. Researchers suggested one factor could be engineers spending much of their time prompting and waiting for AI tools to finish, rather than working on other problems. AI coding tools also struggle in large, complex code bases, so engineers may have spent a lot of time working through incorrect responses from the AI model. Nevertheless, companies like Anthropic are continuing to push ahead with making AI models code more agentically. Anthropic CEO Dario Amodei predicted a few months ago that AI should soon write 90% of code for software engineers. While that may be true inside of Anthropic, that shift may be taking longer to pan out in the broader economy.

You can use Anthropic's popular Claude Code tool on the web now - how to get access

This means you can start coding sessions outside the terminal. Anthropic's Claude Code tool has become a go-to-assistant for developer's coding needs within their terminal. Now, the company is making it accessible directly from the browser, meaning users can access the coding assitant without even opening the terminal. Also: I've tested free vs. paid AI coding tools - here's which one I'd actually use Starting today, users can assign coding tasks to Claude using Anthropic-managed cloud infrastructure, giving developers the ability to code in the GitHub repository via a web interface -- similar to how OpenAI's Codex and Google's Jules operate. This builds on Claude's previous capabilities, which allow users to run the coding assistant directly in their workspace to write or manage code. According to Anthropic, the benefits of using Claude Code on the web include accessing Claude's assistance on multiple tasks across different repositories at the same time, getting answers to questions on how repositories are mapped, shipping faster with automatic PT creation and clear change summaries, and more. As part of this research preview, Anthropic is also making Claude Code available on the iOS app, so that developers can access it on the go. Since its in early preview, the company added the caveat that it is collecting feedback to refine the mobile experience. Also: That new Claude feature 'may put your data at risk,' Anthropic admits To address security concerns, the company said that each Claude Code task runs in an "isolated sandbox environment with network and filesystem restrictions," while Git interactions use secure proxy service which allows Claude to only access authorized repositories. Want more stories about AI? Sign up for AI Leaderboard, our weekly newsletter. Claude Code for web is available in research preview for Pro and Max plans, which are $20 per month and $100 to $200 (depending on usage tier) respectively. Both plans offer other benefits over the free user experience, including higher usage limits, access to Research, the ability to connect to Google Workspace, additional Claude models, and more.

Interview With Claude Code Creator: It Was an Accident That Changed Everything

Emily is an experienced reporter who covers cutting-edge tech, from AI and EVs to brain implants. She stays grounded by hiking and playing guitar. Don't miss out on our latest stories. Add PCMag as a preferred source on Google. Claude Code was a boon for software engineers when it launched in February 2025, but its development was "very much an accident," Boris Cherny, Head of Claude Code, tells us. The agentic coding tool has become an everyday habit among engineers at Anthropic, as well as for clients like Salesforce, Uber, and Deloitte, he says. Last week, Anthropic made Claude Code available on standard web browsers, not just professional coding tools. And while its target audience is still engineers, the ease of accessing it on a phone or computer makes it more inviting for everyone with a Pro ($17 monthly) or Max ($100) subscription to try. Even for the pros, "it's kind of annoying to have to open [command-line tools] every time you want to code," says Cherny. Since Claude Code became available on the web, he's been accessing it from his phone in the morning, using it to kick off a few tasks that he checks on once he's in the office. Claude Code runs on Anthropic's AI models. It can fix bugs, update files, perform code reviews, and more. It can even create tasks in project management tools like Asana. "Whatever tools you use as an engineer, Claude Code can use," Cherny says. It's just one component of Anthropic's Claude chatbot, which last week got a major update: A memory of your prior conversations, so each one isn't a fresh start. In an exclusive interview, Cherny shares more about Claude Code's backstory and offers an inside look at how the tech industry is utilizing it to accelerate product development. Emily Forlini: You've previously worked at Meta and other tech companies and joined Anthropic in September 2024. Were you hired specifically to build Claude Code? Boris Cherny: No, I was hired on a team called Labs, which doesn't exist anymore, because we kind of fulfilled our purpose, I think. There's a feeling in research that [AI] models can do all kinds of things that no product has yet captured. And so [Anthropic] was interested in having an in-house prototyping team that figures out what these frontiers models can do. Claude Code is just one of those prototypes that I did. It was definitely not intentional, and very much an accident. But, yeah, it just kind of worked. What did the early days look like after you built it? The Labs team started using it immediately, the next day after I gave it to them. I walked in and was like, "Wow, this is crazy." I've built a lot of products, but never really seen that before. And then we gave it to all of Anthropic, and pretty soon everyone was a daily active user. I think still 80% to 90% of people use it daily, and it's like 100% weekly. Why did you decide to release it to the public? We weren't totally sure if we should even release it, to be honest. We thought it was our secret sauce since it makes our researchers more productive, by a lot. And so we were like, "Should we give this to other people?" Eventually, we decided "yes," because our job is to learn about safety, and this is kind of the frontier of it. We need to learn about how the agents actually work in the wild. Is Claude Code truly the first AI coding tool? Replit Agent came out in late 2024, and ChatGPT could generate code years ago. I consider it the first fully agentic coding product. There have been a lot of [systems] with something like auto-complete, where you start writing a line of code and the AI completes it. This has been around since the early 2000s, or even the late 90s. But it's not really AI. It's just deterministic; it's static analysis. Then, there was a [Microsoft] Copilot and a bunch of similar tools that used AI to write a single line at a time. But it was still kind of a human coding. The AI was just completing the step. Fully agentic coding is when the model does all the coding. You just describe what you want. What makes it agentic? The word agentic has been abused to hell. It's lost all meaning. We might need a new word because everyone uses it wrong. But agentic, what it means, is you have a model, and you give it tools, and then you give it some sort of context and a task to do. Then, it uses the tools to accomplish the task. It's different than ChatGPT, because it's not one-shot, [meaning] you give it a prompt, and then it gives you a response, and you're done. [Claude Code] will keep going...until it's done. We published a case study with Rakuten where they did this gnarly task and ran Claude Code for seven hours straight, uninterrupted. It just kept going until the task was done. This is something we hear from all sorts of customers, and something we do all the time. The basic building block is you give it tools, and it can use the tools to act in the world. So it's really, really different than what came before. Releasing Claude Code seems to have lit a fire under your competition. A few months later, ChatGPT released a more advanced version of Codex. Many other AI coding products have launched this year since then. Imitation is the greatest form of flattery. And, you know, we're friends with all the other people that work on these teams at other companies. So we talk a lot, and we make fun of them, like, "Hey, you copied our feature." Do you think Claude Code being accessible on the web would make it easier for non-professional programmers, like me, to finally take a stab at serious vibe coding? I think so. It's actually super easy to use, even if you're not an engineer. What if someone wants to become an armchair professional engineer? Now's your golden age. It's an incredible moment right now. You can do this now. (Anthropic's product communications manager Amie Rotherham chimed in at this point to add that, "There are still barriers to entry since it's for engineers, but [Claude Code on the web] is easier or less intimidating, because you don't have to be working from the terminal as much. I think the terminal can really trip people up because it's so foreign, whereas we use browsers all the time anyway.") You can also ask Claude if you need help getting started, right? Yeah, exactly. We now teach about code in the first day of onboarding at Anthropic when people join, and they learn it immediately. It's amazing. We had a manager join the team the other day, and she hasn't coded in 15 years. But she was coding on her first day, and she probably still codes every day or every other day. As a manager, is she working on the main product, or is her team doing most of the work? She's working on the core product. This is Fiona [Fung], the new manager for Claude Code. She built some parts of the Resume feature, and she built a couple other things, too. But these kinds of tools aren't perfect yet, and there are a lot of risks to coding with AI. Do you double-check all of its outputs? All code that you land must go through human review. There has to be a person somewhere in the loop that says, "Yes, this code is okay." But also at Anthropic, and at many companies, now you have like eight coding agents that are doing code review. So at Anthropic, every single pull request, every single change, Claude Code code reviews it on GitHub. If the AI is reviewing the code and writing it, do the humans even know what's in there? Claude Code reviews it, but then a human still has to check it to make sure it's okay. Claude Code does a first pass and finds all kinds of bugs I never would. It's kind of shocking. I didn't think it'd be that good at it. So what's next for Claude Code? Things are moving so fast, but is there a long-term vision? Honestly, we're discovering it along with everyone else right now. In the next six months, I think there's gonna be a lot more agency. The models are gonna run for a longer period of time without human intervention. That's going to be very common, and something every engineer will do all the time. Another thing is having the model working together with other models. A Claude will have a team of Claudes doing stuff. So, for example, we launched plugins last week. An engineer, Daisy, built that over the weekend. She had her Claudes make a bunch of Asana tasks, and then she had a swarm of 20 Claudes that picked off the tasks and built it. By the end of the weekend, we had plugins, and that's the thing we shipped. Anything else we need to know? The most exciting thing is how much engineers love the product. We have Slack channels with a dozen or so companies [that are using Claude Code], and I check in with them every day. It's amazing the amount of love that we get and just how much people care about it. If there's a little bug, everyone's like, "Please, can you fix this?" And we fix it. I've worked on Facebook, I worked on Instagram, I worked on all sorts of products, but I've never worked on a product that people love this much and care this much about all the little details. So yeah, it just makes my job awesome. This interview has been lightly edited and condensed for clarity.

Anthropic extends Claude Code to browsers

Anthropic has launched Claude Code on the web, enabling developers to use the company's AI coding assistant directly from their browser or smartphone, with no terminal required. Developers can connect a first GitHub repository to Claude Code on the web at claude.com/code. Claude Code on the web was launched as a beta research preview for Pro and Max users on October 20. Through Claude Code on the web, developers can assign multiple coding tasks to Claude that run on Anthropic-managed cloud infrastructure. Running tasks in the cloud is especially effective for answering questions about how projects work and how repositories are mapped, for routine and well-defined tasks, for bug fixes, and for back-end changes where Claude Code can use test-driven development for change verification, according to Anthropic.

Anthropic brings Claude Code to iOS and the web

At the end of February, Anthropic announced Claude Code. In the eight months since then, the coding agent has arguably become the company's most important product, helping it carve out a niche for itself in the highly competitive AI market. Now, Anthropic is making it easier for developers to use Claude Code in more places with a new web interface for accessing the agent. To get started, you'll need connect Claude to your GitHub repositories. From there, the process of using the agent is the same as if it had direct terminal access. Describe what you need from it, and the agent will take it from there. Claude will provide progress updates while it works, and you can even steer it in real-time with additional prompts. Through the web interface, it's also possible to assign Claude multiple coding tasks to run in parallel. "Every Claude Code task runs in an isolated sandbox environment with network and filesystem restrictions. Git interactions are handled through a secure proxy service that ensures Claude can only access authorized repositories -- helping keep your code and credentials protected throughout the entire workflow," said Anthropic. In addition to making Claude Code available on the web, Anthropic is releasing a preview of the agent inside of its iOS app. The company warns the integration is early, and that it hopes "to quickly refine the mobile experience based on your feedback." Pro and Max users can start using Claude Code on the web today. Anthropic notes any cloud sessions share the same rate limits with all other Claude Code usage.

Anthropic's Claude AI can now code without a command line terminal

The AI coding assistant is offered for subscribers of Anthropic's Pro and Max plans. Anthropic recently launched Claude Code for the web and as an iOS preview, making it easier for developers to use the AI coding assistant without the need for a terminal or command line. Users can connect Claude to their GitHub projects and ask the AI agent to perform coding tasks, follow the work in real time, and provide new instructions during the coding process. Claude Code can handle multiple tasks simultaneously, and each session runs in an isolated sandbox environment with limited network and file system access to protect code and login credentials. Claude Code is offered to subscribers of Anthropic's Pro plan, which costs $20/month (or $17/month if paid annually), and the Max plan, which costs $100+ per month depending on usage.

I tested Claude Code's new web app -- it makes coding as easy as chatting

Anthropic recently launched a web-based interface in limited rollout, making it easier than ever to code directly from your browser. I spent a few days experimenting with this new vibe coding tool, and honestly, it's so intuitive I can't imagine using anything else now. As someone who barely passed computer science in college, let me start by saying this: if I can vibe code, anyone can. The best part? With Claude Code, coding feels more like a conversation. All of the edits and additions are done with natural language, so you don't need to know how to read or write code at all. You just describe what you want to build, and Claude Code takes it from there, no formulas to understand or memorize and no external apps to link. There isn't even any confusing setup; it's so simple I kept waiting for the catch, but there isn't one. Here's how it works and how to get stared. You'll want to start by logging into your Claude account and ensure you have the Pro or Max plan. Claude Pro offers a lot of extra features including more query tokens, that I've recently found are worth the monthly subscription. If you're a vibe coder or thinking about future-proofing your career with this skill, you might want to consider it. Once you've logged in, navigate to the chat box and find "Claude Code." Click on it and you're ready to go. You then choose the coding model (e.g. Haiku 4.5, Sonnet 4.5, Opus 4). I have found Haiku 4.5 to be an excellent choice for vibe coding, but if you're unsure about what you should use, go ahead and ask Claude. Tell the AI want you want to create, and it will suggest the best model for the job. The original Claude Code runs through the terminal and integrates directly with GitHub and IDEs like VS Code. This new web version brings that same logic to a cleaner visual interface. You can type natural-language requests, view the generated code and even manage multiple tasks at once without switching windows. I began by using the prompt: "Build a small React app that lets me track daily writing goals." Within seconds, Claude Code scaffolded the project, wrote the components, and suggested connecting local storage for persistence. I chose a React app -- an app using React, a JavaScript library created by Meta (Facebook) for building user interfaces, especially those that update dynamically as users interact with them. But you can simply say "app" and explain how you want the app to be used (for personal use or public), and Claude will get to work. Again, I can't stress enough how easy it is for anyone with no coding experience to start creating. When I said, "Make the progress bar feel more rewarding," Claude re-designed the animation logic and explained each change. While my app is fairly simple, you can get more elaborate (or simpler) if you prefer. You can also "publish" to make the app public or keep it to yourself. The conversation felt fluid, as Claude responded with exact changes I requested. I could refine the layout, add a save feature or re-name components just by describing what I wanted. The most impressive part isn't how quickly Claude writes code, but how well it collaborates. In other experiments if I pointed out that a section "felt clunky," Claude understood the context and rewrote the code, explaining not only what it did but the trade-offs between clarity and brevity. Claude can also manage several tasks in sequence: debugging, adding comments and optimizing layout performance. Watching it reason through those changes and explain its logic felt like working with a smart programmer who didn't judge me for my minimal coding understanding. Since the browser version of Claude Code is still in limited rollout, there are occasional hiccups . Larger builds sometimes lag, so just stay patient. It's also not meant to replace your local dev environment just yet; think of it as a companion workspace for quick prototypes, bug fixes, and creative experimentation. By shifting coding from syntax to intent, tools like Claude Code are lowering the barrier to entry for beginners while speeding up creative development for experienced coders. Anthropic's broader vision of agentic AI that can plan, debug and execute tasks, is already visible here. And for anyone who's ever wished coding felt less mechanical (and more personal), Claude's conversational flow hits the sweet spot between logic and creativity. Vibe coding is where software creation is headed. Claude Code's new web interface may still be in early stages, but it already turns AI-assisted coding into something incredibly easy for personal or professional use. Whether you're a seasoned developer or just curious about jumping on the vibe coding bandwagon, Claude Code makes it easy to code apps, games and websites right from your browser.

Claude Code comes to the masses - and it's a game-changer for wannabe coding masters

The tool's new accessibility opens up advanced coding capabilities to non-developers and solo creators Anthropic is making its Claude Code programming tool available and usable to just about anyone with a web browser or smartphone. No longer limited to terminals and local environments, you can now delegate multiple coding tasks to Claude Code right from your claude.ai browser tab. Being usable on mobile devices enhances that sense of flexibility. You can use Anthropic's iOS app to get to Claude Code and have a new piece of software outlined in very little time, though not without its share of bugs and flawed mechanics. It's a remarkable shift for a tool like Claude Code, which Anthropic boasts it used internally to write 90% of its own code. The company claims it has contributed to a jump in output of 67% per engineer, even as the engineering team doubled in size. That's partly because Claude Code is so proactive when receiving instructions. Users can submit new requests while previous ones are running, and tweak them before they are done if it looks like Claude hasn't quite understood what it's been asked to do. In one sense, this is the latest chapter in AI's ongoing effort to dissolve barriers between expert tools and casual users. In another, Claude Code on the web allows users to get the programming software to mimic how humans work in the disjointed fits and starts that jump around to different contexts. You just assign the work, Claude handles the execution, and you review the results on your schedule. Claude Code's expansion is a sort of culmination of recent efforts by Anthropic to push a new line of AI models out. Claude Sonnet 4.5 and Claude Haiku 4.5 recently debuted, with agent-based coding a key element of how Anthropic pitches them. The appearance of Claude Code on the web continues Anthropic's push to reshape who gets to benefit from this kind of AI model. That shift in role might feel jarring to some developers who pride themselves on hands-on control. But it's arguably just another level of automating some aspect of programming, going back to physically moving relays in building-sized computers, down to the much more rapid development of high-level languages, then frameworks, then low-code platforms, and, for the average person, the development of the content management systems in use today. Agentic AI just pushes the boundary further by autonomously executing more abstract instructions. It certainly doesn't remove the need for human programmers and designers to make good programs, although making it easier to produce bad ones is arguably a built-in argument against their use. In that light, Claude Code becomes less about replacing developers and more about augmenting them. It handles the glue code, the boilerplate, and the regression tests. The boring bits, in other words. Anthropic says it's a real money-maker too, with Claude Code on its way to making more than half a billion dollars in annualized revenue, with ten times the usage since it became generally available in May 2025. Word of it must be spreading to the likes of solo developers and independent teams who once struggled to keep up with code maintenance. Designers who occasionally dabble in front-end tweaks might finally ship a side project they've played with for years. There are still plenty of limitations. Not every problem can be solved with an agent. Not every user wants to write specs in natural language. But for a growing swath of tasks, Claude Code's accessibility may make all of their programming dreams come true.

Claude Code comes to web and mobile, letting devs launch parallel jobs on Anthropic's managed infra

Vibe coding is evolving and with it are the leading AI-powered coding services and tools, including Anthropic's Claude Code. As of today, the service will be available via the web and, in preview, on the Claude iOS app, giving developers access to additional asynchronous capabilities. Previously, it was available through the terminal on developers' PCs with support for Git, Docker, Kubernetes, npm, pip, AWS CLI, etc., and as an extension for Microsoft's open source VS Code editor and other JetBrains-powered integrated development environments (IDEs) via Claude Agent. "Claude Code on the web lets you kick off coding sessions without opening your terminal," Anthropic said in a blog post. "Connect your GitHub repositories, describe what you need, and Claude handles the implementation. Each session runs in its own isolated environment with real-time progress tracking, and you can actively steer Claude to adjust course as it's working through tasks." This allows users to run coding projects asynchronously, a trend that many enterprises are looking for. The web version of Claude Code, currently in research preview, will be available to Pro and Max users. However, web Claude Code will be subject to the same rate limits as other versions. Anthropic throttled rate limits to Claude and Claude Code after the unexpected popularity of the coding tool in July, which enabled some users to run Claude Code overnight. Anthropic is now ensuring Claude Code comes closer to matching the availability of rival OpenAI's Codex AI coding platform, powered by a variant of GPT-5, which launches on mobile and the web back in mid September 2025. Parallel usage Anthropic said running Claude Code in the cloud means teams can "now run multiple tasks in parallel across different repositories from a single interface and ship faster with automatic PR creation and clear change summaries." One of the big draws of coding agents is giving developers the ability to run multiple coding projects, such as bugfixes, at the same time. Google's two coding agents, Jules and Code Assist, both offer asynchronous code generation and checks. Codex from OpenAI also lets people work in parallel. Anthropic said bringing Claude Code to the web won't disrupt workflows, but noted running tasks in the cloud work best for tasks such as answering questions around projects and how repositories are mapped, bugfixes and for routine, well-defined tasks, and backend changes to verify any adjustments. While most developers will likely prefer to use Claude Code on a desktop, Anthropic said the mobile version could encourage more users to "explore coding with Claude on the go." Isolated environments Anthropic insisted that Claude Code tasks on the cloud will have the same level of security as the earlier version. It runs on an "isolated sandbox environment with network and filesystem restrictions." Interactions go through a secure proxy service, which the company said ensures the model only accesses authorized repositories. Enterprise users can customize which domains Claude Code can connect to. Claude Code is powered by Claude Sonnet 4.5, which Anthropic claims is the best coding model around. The company recently made Claude Haiku 4.5, a smaller version of Claude that also has strong coding capabilities, available to all Claude subscribers, including free users.

Claude Code just came to the web -- and it's about to change how you vibe code

You can now unleash Claude's raw power directly in your terminal I've said it before and it still holds true: Claude is quietly crushing it. Now, Anthropic just made coding way easier. With its latest update, Claude Code on the web users can now write, fix and manage code straight from their browser. No command line, no setup no downloads needed. Currently in research preview for Claude Pro and Max users, this version runs entirely in the cloud, so you can assign tasks, generate pull requests and track updates in real time; all from one place. This updated includes GitHub integration, secure sandbox testing and support for multiple tasks at once, turning Claude Code into a full-on cloud coding workspace. Whether you're fixing bugs, writing tests or updating backend logic, everything happens right inside your browser. With the new web version, you can hand off coding tasks right from your browser. Instead of jumping between GitHub and the command line, just tell Claude what you need, such as: "clean up my CSS" or "add error handling to the login page." Claude will do the rest, generating pull requests, running tests and summarizing the changes automatically. GitHub is still part of the process; Claude needs access to your codebase to make real updates, but setup is a lot easier. The browser interface removes most of the manual steps, so you can focus on shipping code faster. Even better, Claude Code is expected to land in the iOS app soon, bringing mobile workflows into the mix. That means you could assign a few bug fixes while waiting in line for coffee, and come back to completed PRs ready to merge. Claude Code's web version is not only built for convenience, it's built for scale. You can now give Claude a list of tasks instead of one at a time. For example, you could say "fix these 10 bugs" or "update all the backend routes," and it will work on them in parallel. That shift moves Claude closer to agentic AI where the assistant follows instruction while breaking down big goals into smaller jobs and finishes them on its own. This kind of automation could save developers and vibe coders hours of repetitive work. Anthropic hasn't released full documentation yet, but early tests suggest the cloud version removes the single-task limits seen in the older command-line tool. In other words, you can finally let Claude handle multiple coding jobs at once, just as if you had a real timemate doing it. The timing fits Anthropic's rapid release cadence. After launching Claude Sonnet 4.5 in late September -- positioned as "the best model in the world for coding and AI agents" -- the company followed with Haiku 4.5, a lightweight model optimized for reasoning. Claude Code adoption has soared alongside them. Anthropic says the tool has grown 10× since May and now drives hundreds of millions in annualized revenue. Internal teams reportedly generate up to 90% of their code through Claude, signaling just how fast AI-assisted development is scaling. Now, Claude Code on the web marks a major leap in accessibility, bringing advanced AI-assisted coding to everyone; from veteran developers to newcomers who just want to fix a bug or prototype faster. The tool is available now in research preview for Claude Pro and Max tiers at claude.ai/code.

Anthropic brings Claude Code to the web and iOS

The web version lets developers connect GitHub repositories and assign coding tasks through a visual interface. Anthropic has launched a research preview of Claude Code for the web and iOS, now available to its Pro and Max plan subscribers. The update extends an existing command-line tool, enabling developers to delegate coding tasks through new graphical interfaces. This release follows a period over the past year in which developers using large language models for coding have rated Claude as one of the leading options for such tasks. Building on this developer feedback, Anthropic first released Claude Code earlier this year as a command-line utility. This initial version gave programmers the ability to assign coding work directly to the AI from their terminal. The new web-based version expands this functionality, allowing developers to initiate coding sessions without a terminal. According to Anthropic, "Claude Code on the web lets you kick off coding sessions without opening your terminal. Connect your GitHub repositories, describe what you need, and Claude handles the implementation." Each session operates in an isolated environment with real-time progress tracking, and users can actively steer the AI to adjust its course while it works. The web interface supports running multiple tasks in parallel across different repositories from a single dashboard. Anthropic notes the web version is best suited for well-defined assignments, such as bug fixes or routine updates. It can also manage more involved work, including backend changes, and can answer questions about the structure of a repository. For security, Anthropic provides detailed technical documentation that outlines the sandbox architecture it employs for these coding sessions. The accompanying iOS app is also an early research preview. It is designed to offer a quick way for developers to review code, run small tasks, or check the progress of ongoing coding sessions from a mobile device. Anthropic stated it plans to use feedback gathered during the preview to refine the mobile experience.

Anthropic's Claude Code Is Now Available as a Web App

Claude Code was earlier available as a command-line interface (CLI) tool Anthropic is finally expanding the accessibility of its Claude Code product. The artificial intelligence (AI) tool, which was so far available as a command-line interface (CLI) on compatible desktops, can now be accessed via a web app. The web version of the coding tool is currently available as a research preview to the paid subscribers, and it brings several improvements over the coding interface of Claude chatbot. The tool can perform multiple coding tasks in parallel and connect to GitHub repositories. Claude Code Is Now Available on the Web In a newsroom post on Monday, the San Franciso-based AI firm announced the expansion of Claude Code to web. With this, eligible users will no longer need to download the CLI to access the sandboxed coding tool. Instead, the AI system can be given tasks right from the browser, as long as it is connected to the user's GitHub repo. Currently, it is available in beta as a research preview, and those interested in trying it out will require a Claude Pro or Max subscription. Claude Code on the web also brings the AI system from inside the user's terminal to the cloud. There is a trade-off in security and privacy, but those users who are willing to let that go will now get new features due to the extra processing power from the cloud servers. Among them is the ability to run multiple coding tasks in parallel. These tasks can be across different repositories, all manageable via a single interface, and every completed task comes with a pull request (PR) button and change summaries. Additionally, each coding session runs in its own isolated environment where the user can monitor real-time progress. Users can also prompt Claude Code to focus on specific elements and add subtasks while it is actively coding. Anthropic says the AI tool excels in bug fixes, tasks that are well-defined, and making backend changes. Anthropic has also made Claude Code available on smartphones. Currently, the coding tool can be accessed via the Claude for iOS app. However, the company highlights that it is an early preview, and it will refine the mobile experience based on user feedback. While running Claude Code via cloud comes with more security risks than running it from the terminal, the company claims that it has taken measures to ensure that user data remains secure. Each coding task is kept in an isolated environment with network and filesystem restrictions. Additional GitHub interactions are handled via a proxy service to ensure that the AI can only access authorised repositories. Users and admins also have control over choosing the domains Claude Code can connect to via custom network configuration.

Claude Code Web : Redefining AI Coding for the Modern Developer

What if the future of software development wasn't just faster or more efficient, but fundamentally reimagined? Picture a world where coding no longer requires juggling countless tools, where debugging feels less like a chore and more like a seamless collaboration between human creativity and machine intelligence. Enter Claude Code Web, a cloud-based platform that's not just another coding tool, it's a bold step toward transforming how developers work. With its integration of AI-driven workflows, mobile accessibility, and GitHub compatibility, Claude Code Web promises to redefine the very fabric of software engineering. But is it truly the future, or just another fleeting trend in the crowded AI landscape? In this overview, Matt Maher takes you through how Claude Code Web is reshaping the development process, from automating repetitive tasks to allowing parallelized workflows that save time and reduce bottlenecks. You'll discover why its focus on usability and structured outputs sets it apart from competitors like OpenAI's Codex, and how its mobile-first approach enables developers to work from virtually anywhere. Yet, as with any innovation, challenges remain, session context issues and manual interventions still demand attention. By the end, you'll not only understand what makes Claude Code Web a fantastic option but also gain insights into the evolving role of AI in software development. Could this be the platform that finally bridges the gap between efficiency and creativity? Claude Code Web is designed as a cloud-based coding platform, allowing you to work directly from a web browser or mobile device. Its integration with GitHub ensures that repository management, code editing, and debugging can all be performed without the need to switch between multiple tools. The platform's asynchronous workflows reduce the need for constant user interaction, making it particularly effective for distributed teams working across different time zones. Some of its most notable features include: These features collectively make Claude Code Web a powerful and adaptable tool for modern software development, catering to both individual developers and collaborative teams. In a competitive market that includes platforms like OpenAI's Codex, Claude Code Web distinguishes itself through its emphasis on usability and structured outputs. While Codex is known for generating code snippets, Claude Code Web focuses on producing cleaner outputs and more organized pull requests, making it a preferred choice for developers who prioritize clarity and efficiency. Another significant advantage is its mobile compatibility, which allows you to code and test across devices. This feature is particularly valuable for developers managing projects in dynamic or distributed environments. By prioritizing user experience and flexibility, Claude Code Web positions itself as a practical and efficient tool for developers seeking to streamline their workflows. Here are additional guides from our expansive article library that you may find useful on Claude Code. Claude Code Web supports a variety of development workflows, making it suitable for both exploratory coding and iterative processes. Its interactive tools allow you to submit requests, review outputs, and refine code changes in real time, fostering a collaborative and experimental approach to problem-solving. The platform also enables parallelized development, allowing teams to work on multiple components simultaneously. This reduces bottlenecks and accelerates iteration cycles, helping you meet project deadlines more efficiently. Whether addressing complex challenges or exploring unconventional ideas, Claude Code Web provides the tools necessary to optimize your workflow and enhance productivity. User experience is central to Claude Code Web's design. Its intuitive layout simplifies navigation and task management, while its mobile compatibility ensures you can access projects anytime, anywhere. Features like streamlined branching and merging processes further enhance usability, making it easier to manage GitHub repositories and maintain project consistency. By reducing cognitive load, the platform allows you to focus on creative problem-solving. Whether debugging intricate issues or testing new features, Claude Code Web's ergonomic design supports efficient and effective development, making sure that you can dedicate more time to innovation and less to administrative tasks. Despite its many strengths, Claude Code Web is not without its challenges. One notable issue is session context sharing, which can occasionally lead to discrepancies when syncing between cloud and local environments. This may require manual intervention to ensure consistency across development stages. Additionally, while the platform automates several tasks, merging and evaluating changes still require your attention. These limitations highlight areas where further refinement could improve the platform's reliability and user satisfaction. Addressing these challenges will be crucial for making sure that Claude Code Web continues to meet the evolving needs of developers. Claude Code Web represents a significant advancement in cloud-based development. By allowing parallelized tasks and reducing development timelines, it underscores the fantastic potential of AI in software engineering. As AI-driven tools continue to evolve, platforms like Claude Code Web are expected to accelerate innovation and redefine best practices in the industry. The platform's ability to streamline workflows and enhance collaboration positions it as a valuable tool for both early-stage projects and scaling operations. Its ongoing development is likely to influence how developers approach coding, debugging, and project management in the years to come. To fully use the capabilities of Claude Code Web, consider adopting the following strategies: By implementing these practices, you can optimize your workflow and fully use the platform's capabilities, making sure a seamless and productive development experience.

Anthropic Launches Claude Code Web App for AI-Powered Coding Agents

Claude Code Web App Lets Developers Manage AI Coding Agents Directly in Browser Anthropic has released a web application for its AI coding assistant, Claude Code, which allows developers to build and manage multiple AI coding agents from within their browser. The web application is offered to subscribers of the Anthropic Pro and Max plans. It can be accessed through claude.ai or from the Claude iOS app by clicking on the 'Code' tab. This move extends beyond its initial command-line interface (CLI) form, which programmers have historically accessed from a terminal. With a web version, Anthropic wants to enhance the portability of AI coding agents in the coding space.