Artifacts now support public sharing and multiplayer editing in Claude Code, and can be created with Claude Tag.
You can now publish an artifact to the public, so anyone with the link can view it. Prototype a tool and you can now ship it beyond your company.
Claude Code on desktop now has an in-app browser. Claude can pull up docs, designs, or any other site. It can read, click through, and interact the same way it does with your local dev servers. It's sandboxed and configurable: you choose whether sessions persist.
Make sure to update to the latest version of the desktop app. Read more in the docs: code.claude.com/docs/en/deskto…
We've reset 5-hour and weekly rate limits for all users.
A few patterns we frequently use with Fable 5: Use Fable 5 as an "advisor." An executor (Sonnet 5) calls Fable 5 for guidance. Most tokens are billed at the lower executor rate.
On SWE-bench Pro, Sonnet 5 + a Fable 5 advisor tool gets ~92% of Fable 5's score at ~63% of the price. Fable 5 is called rarely (~once) per task to steer while Sonnet 5 executors the majority of the work. See our docs to learn more: platform.claude.com/docs/en/agents…
6 months of Claude Max 20x, on us. We're expanding Claude for Open Source to more of the community. If you're a maintainer, a core contributor, someone landing PRs across the ecosystem, or someone keeping a critical package alive, apply today!
Apply here: claude.com/contact-sales/…
/radio 🍓☀️
We've raised Claude Platform API rate limits for all users and simplified the tiers, which are no longer based on API spend. The latest Sonnet and Haiku models now provide 5x higher rate limits at the highest tier.
Each rate limit tier offers the same requests per minute and token throughput across the latest Opus, Sonnet, and Haiku models. This lets you choose the right model for the task, instead of making trade-offs for rate limiting.
Artifacts in Claude Code are now also available on Pro and Max plans. Ask for an artifact, Claude writes the code, publishes it live to claude.ai, and updates it in real time while it keeps working. Pages are private to your account and fully self-contained. x.com/claudeai/statu…
Read more in the docs: code.claude.com/docs/en/artifa…
Now that Fable 5 is ready to build (again), we've reset everyone's 5-hour and weekly rate limits.
We’ve added a few updates to Claude Managed Agents: Streaming session event deltas, per-session agent overrides, new webhook event types, reverse pagination, and credential injection scoping.
Agent Overrides let you start a session from a stored agent and override parts of its config for that one session: swap out the model, system prompt, tools, mcp_servers, or skills.
Claude Sonnet 5 is here. Top-tier performance on coding and tool use at Sonnet pricing, with a 1M context window. It's the new default in Claude Code for Pro users, and available everywhere on the Claude Platform, including the API and Managed Agents. x.com/claudeai/statu…
Sonnet 5 provides big gains over 4.6 across reasoning, tool use, coding, and knowledge work. It's built for real engineering work. Navigating large codebases, landing multi-file changes, and carrying long debugging or refactor tasks through to completion.
Claude Desktop is now available on Linux (Ubuntu and Debian) in beta. Alongside the browser and terminal, you now get a first-class desktop experience with Claude Code, Claude Cowork, and chat on all paid plans.
Computer Use isn’t included in this release, more coming soon. Read more in the docs: code.claude.com/docs/en/deskto…
You can now run Claude models in Microsoft Foundry, hosted on Azure. Claude Opus 4.8 and Claude Haiku 4.5 are available through the Messages API with capabilities like prompt caching, thinking, and more. x.com/claudeai/statu…
Claude runs in your Azure environment using your Azure identity, networking, billing, and governance controls. Check out the docs here: platform.claude.com/docs/en/build-…
Boris sat down with Spotify VP of Engineering Niklas Gustavsson. Spotify ships 4,500 production deploys a day, and 73% of PRs are now AI-assisted.
Niklas keeps 5 to 10 Claude sessions running in tmux, one per git worktree, agents working in the background. All of it inside a 20M+ line monorepo. He expected agents to struggle at that size, but it's worked well.
Claude Tag is the next evolution of agents. It's a proactive, multiplayer agent with memory and identity, built on top of Claude Code. Learn more about how Claude Tag works and best practices for using it in this deep dive.
When Claude is working in a channel with four people, whose credentials does it use? The answer: its own. When tagging Claude, Claude gets provisioned like any other teammate, with its own credentials. We call this access model "agent identity". Here's how it works: 🧵
Acting as the user works fine for a single personal assistant, but Claude Tag can be multiplayer. When three people are in one thread, there's no "right" set of permissions to borrow. So in channels, Claude acts as itself. In DMs, where it's just you, Claude acts as you.
The Claude Code team has been shipping with Claude Tag internally all year. It now writes 65% of our product team's code, including most of what built Claude Tag itself. Here are a few ways we use it every day: 🧵 x.com/claudeai/statu…
Incident response Tag Claude in the incident thread when the page lands. It pulls graphs, diffs the deploy, comes back with root cause and the author tagged. Your team approves in-thread. Claude opens the fix, lands it, watches the metric recover, and resolves the page.
The Japan Claude Community Ambassador program is here! 🇯🇵 Ambassadors have hosted 290+ meetups in 107 cities across 37 countries, with 40,000+ attendees building together. Now open from Hokkaido to Okinawa. 日本の皆さん、ぜひご応募ください！ claude.com/ja/community/a…
Update: we've gone ahead and reset 5-hour and weekly usage limits for everyone, across all plans. Enjoy your weekend! x.com/ClaudeDevs/sta…
Earlier today, ~3% of Claude Code Max and Pro users hit a bug that showed an incorrect weekly usage limit, and in some cases blocked them from sending messages. This is fixed, and we're resetting 5-hour and weekly limits for everyone affected. Apologies for the disruption.
Artifacts are now live in Claude Code. Ask Claude to turn what it's working on into a page and send the link to your team. The page updates as the session keeps working. Available today on Team and Enterprise plans. x.com/claudeai/statu…
We've added support for the Enterprise-Managed Auth extension to MCP. Admins can centrally authorize MCP connectors for their organization, so all the tools and data users need are connected on their first login.
It centralizes authorization through your identity provider: no per-app OAuth or setup for users, and tighter, more efficient control for admins.
Claude Code and Claude Design now sync both ways. Run /design-sync to pull your design system into your repo and build against your real components, or push what you've built back into Claude Design and keep editing on the canvas. x.com/claudeai/statu…
Thanks for building with us at Claude Build Day! 300 builders spent their Saturday with us in SF, and we're blown away by what you made in a single day. Here are all the winning demos: 🧵
🥇 1st Place: Tekton Holly Tang & Austin Burgess built an evidence-driven 3D reconstruction platform that brings Tang Dynasty architecture back to life, with every component traceable to its historical source
How do teams get agents into production? New blog post from our Applied AI team on Claude Managed Agents and the challenges it solves (credentials, sandboxing, observability, & more) ...
The blog shares common reasons teams have chosen to build on Claude Managed Agents, several case-studies, and practical tips for getting started: claude.com/blog/building-…
We've reset 5-hour and weekly rate limits for all users.
As a result of a US government directive, we are suspending access to Claude Fable 5 for all users. You can continue to use all other Claude models. Here’s what this means for you: Across Claude products, new sessions will run on your selected default model or Opus 4.8, and x.com/AnthropicAI/st…
Claude Managed Agents can operate in a sandbox you control, on your own infrastructure or with any provider you choose. Today we added new guides for @blaxelAI, @e2b, @googlecloud, @namespacelabs, and @superserve_ai, so you can choose the best fit for your use case.
Learn more about self-hosted code sandboxes with these and other providers in the Claude Managed Agents docs: platform.claude.com/docs/en/manage…
/goooooal ⚽
We've just added two new Claude Managed Agents features: 1. Scheduled deployments - run tasks on a schedule 2. Environment variables - expose vault credentials for CLIs as environment variables
Each deployment is an agent, an environment, an initial message, and a schedule. When a deployment runs, it starts a fresh session. No scheduler to build or host.
We’re rolling out changes to make Fable 5’s safeguards for frontier LLM development visible. Starting this week, flagged requests will visibly fall back to Opus 4.8—the same as our safeguards for cyber and bio. You will see this every time it happens. On the API, any flagged
New for Apple developers: Foundation Models support for Claude lets developers use Apple's Foundation Models framework to call Claude for multi-step reasoning, code generation, and longer context.
Typed outputs from Apple's Foundation Models framework drop straight into your Claude request, so you're sending structured data rather than raw user text. Responses stream back into the same SwiftUI view. Read more in the docs: platform.claude.com/docs/en/cli-sd…
We've reset 5-hour and weekly rate limits for all users. Enjoy Fable 5!
We're hosting Claude Fable 5 Build Day in San Francisco on June 13. Point Fable 5 at a problem worth solving and build a solution with Claude Code. The Anthropic team will be in the room, with a chance to win from a prize pool of $150K in Claude credits across 3 finalists.
Spots are limited. Apply by June 12: cerebralvalley.ai/e/claude-start…
Tomorrow’s Build Day event is still on, we're building on Opus 4.8 instead. Thank you, we can’t wait to build with you tomorrow!
Claude Fable 5 is our first generally available Mythos-class model. It ships with new safety classifiers that may flag certain prompts in dual-use domains like cyber and bio. We've added fallbacks: a refused request retries on Claude Opus 4.8 instead of dead-ending.
When a classifier declines, the API re-runs the request on your fallback model in the same round trip. Rate limits and server errors are returned from the API as usual.
If you’re having trouble accessing Claude Fable 5, try running /model claude-fable-5. In the Claude Code CLI, make sure to upgrade to 2.1.170. If you’re on the Claude Desktop app, update the latest version.
Claude Fable 5 changed how we work on the Claude Code team day to day. We used to verify that Claude did the work right. Now we verify that it's doing the right work. Here’s the 3 biggest changes:
With multi-agent orchestration in Claude Managed Agents, you can use Fable to delegate work to dedicated agents using smaller models.
Cybersecurity and biosecurity requests may auto-reroute to Opus 4.8 (shown in the UI, billed at Opus prices). Docs + prompting guide: platform.claude.com/docs/en/build-…
