We've added a new cookbook: connect a Claude Managed Agent to @vercel's Chat SDK. This gives an agent access to a universal chat layer. github.com/anthropics/cla…
Chat SDK gives you the chat interface: one type-safe `onDirectMessage` handler, 15+ adapters across Slack, Teams, Discord, web and more. Managed Agents runs the agent server-side: harness, session management, and memory. Each conversation is one persistent session.
Claude Code can now draft feedback for you. When something fails, when Claude notices it made a mistake, or when you tell it something went wrong, it writes up the report itself. You can review, modify and approve the feedback to send.
You can disable this or change behavior in /config. More in the docs: code.claude.com/docs/en/tools-…
We've added the Admin API to the SDKs and the `ant` CLI. You can manage members, workspaces, and API keys, and read your org's rate limits. Docs: platform.claude.com/docs/en/manage…
Long answers on Claude on web and desktop now stream ~4x smoother. We rebuilt the streaming renderer to only touch what's still changing, so a long reply stalls 9x less on a slower laptop, its worst freeze is 4.5x shorter, and on a 120Hz MacBook it holds 120fps start to finish.
Enterprise-managed auth for MCP connectors is now generally available. For Claude Team and Enterprise admins, authorization is centralized through your identity provider. For users, tools and data are connected automatically, without the need for individual OAuth.
Supported by Asana, Atlassian, Canva, Datadog, Figma, Granola, Linear, Notion, Slack, and Supabase. Developers can also add enterprise-managed auth to their own third-party MCP connectors in the Claude directory. Blog: claude.com/blog/enterpris… Docs: claude.com/docs/connector…
Last month you told us Remote Control was the thing you'd most like us to fix, so we've been working hard on reliability. Here's what's better today: 🧵
You can now start a Claude Code session directly from your phone. Any machine running claude remote-control shows up as a device card at the top of the Code tab. Tap it, pick a directory, and it starts on that machine.
Computer use, the browser tool, the Skills API, and the Files API are now generally available on the Claude Platform. Automate work in applications that have no API with fewer round trips per task, and build Claude Managed Agents on versioned skills and reusable files.
Claude now takes several actions per turn (click, type, key, screenshot) instead of one per round trip with `computer_toolset_20260801`. Early-access customers saw 20-40% fewer round trips per task, so tasks finish faster and cost less.
Claude Managed Agents can power many different UIs. Our new cookbook pairs Claude Managed Agents with AG-UI, @CopilotKit's open Agent-User Interaction Protocol.
The AG-UI adapter for Claude Managed Agents maps each chat thread to a managed session and streams text, tool calls, and thinking to your UI. Try it here: github.com/anthropics/cla…
You can now set Claude Code's output style to Concise. Claude leads with the result, keeps responses short, and still gives full detail when you ask. Turn it on in /config → Output style, or set "outputStyle": "Concise" in settings.json.
We shipped three updates to Claude Managed Agents. First, we made it easier to use memory with Self-Hosted Sandboxes. Any work done in a Self-Hosted Sandbox can be saved to memory.
Second, we've added domain controls. web_search and web_fetch now take allowed_domains or blocked_domains, so you can control what the agent is allowed to search and read.
Claude Desktop now starts ~2x faster than it did a month ago. When the app started in the background, its timers got throttled and the JS engine dropped into power-saving mode. We now boot at full speed even while the window's still hidden, along with some smaller perf fixes!
We’re extending the 50% increase to weekly Claude Code limits through August 31. We hope to make this a permanent change to our plans, but strong demand for our models means that capacity may be tight over the coming weeks. We’ll keep you posted as things develop.
ClaudeDevs@ClaudeDevs·We're also keeping Claude Code weekly limits 50% higher, now through August 19, for all Pro, Max, Team, and seat-based Enterprise users. x.com/claudeai/statu…
Perf win of the day: Claude Code CLI now uses 2x less CPU at p99. Bun's garbage collector was running on a fixed timer, so it would kick in mid-turn and steal CPU right when Claude Code was busiest. Now it waits until the process is idle.
Claude Code can design now. The new /design skill (research preview) brings Claude Design's artboard workflow into the CLI and Desktop, built on artifacts. Run /design to get editable artboards for your UI — pick one, tweak it, then have Claude implement it.
Available on Pro, Max, Team, and Enterprise. Update Claude Code to try it.
In a new blog post, we share how one customer, ABC Legal, deployed Claude Managed Agents. The fleet of 50+ agents have cut costs by up to 50% for certain legal tasks. The agents also use a feedback loop to improve continuously over time. Read more: claude.com/blog/how-abc-l…
Auto mode is rolling out today as the default permission mode in Claude Code for Pro, Max, and Team. If you've already set a default mode, Claude will ask before changing anything. You can still switch modes any time with Shift+Tab, or pin one with "defaultMode" in settings.
ClaudeDevs@ClaudeDevs·Starting August 14, auto mode will be the default permission mode in Claude Code for Pro, Max, and Team users. Auto mode reviews shell commands and actions with a separate classifier. In testing, it caught 89% of dangerous commands. Manual approval caught 14%.
To configure auto mode for your environment, run /auto-mode-setup. Claude looks through your repo and suggests trusted repos and domains for you to review. The more the classifier knows about your setup, the clearer the line on what's safe to run. code.claude.com/docs/en/auto-m…
Hit your usage limit in Claude Code desktop? There's now an auto-continue checkbox. Turn it on, and it'll automatically continue where you left off once your limit resets.
We recently made auto mode the default in Claude Code, which means you no longer have to approve every action. But what determines if something is safe to run? Watch how it works:
We shipped four updates to Claude Managed Agents this week. First, you can now set a budget for sessions to keep spend predictable. Sessions that hit the limit pause with a budget_reached event, you can raise the budget to resume.
Next, you can now control where inference runs for Claude Managed Agents. Set model.inference_geo to US or global. Pinning to `global` runs wherever there's capacity at the standard rate and `us` keeps it in-region and bills at 1.1x.
New in Claude Code: your sessions can now message each other. Instead of having to re-explain yourself in another session, you can now tell Claude to do it. It sends a summary (not your history or files), and the other session picks it up mid-task.
It goes both ways: you can also ask another session a question and get the answer back in your active session. Claude can also message another session on its own, e.g. when a change it just made affects what that session is working on.
Starting August 14, auto mode will be the default permission mode in Claude Code for Pro, Max, and Team users. Auto mode reviews shell commands and actions with a separate classifier. In testing, it caught 89% of dangerous commands. Manual approval caught 14%.
We’re making this change for two reasons: 1. In our testing, auto mode matched or beat manual permission review on every safety measure we tracked. 2. It makes long-horizon work more viable. Claude runs longer between interruptions, so you can run multi-hour tasks in the background without babysitting permissions.
Two incidents over the last 24 hours resulted in elevated errors or reduced availability on Claude for some users. Multiple separate network failures cut into our capacity to serve Claude, and some requests failed while we rerouted traffic.
We've made progress restoring capacity and things are stable right now, but we're not fully in the clear yet. If anything comes up, we'll post it on status.claude.com.
MCP 2026-07-28 is live and it's the largest update to the protocol since launch. MCP is now stateless, making it easier to deploy and scale remote servers. claude.com/blog/bringing-…
Before, running a remote MCP server meant managing session state, which limited where you could run it. Now that MCP is stateless, you can deploy on serverless and edge infrastructure, or scale horizontally behind any load balancer.
Opus 5 is live in Claude Code and the Claude Platform today. A few things worth knowing: 🧵 x.com/claudeai/statu…
On agentic terminal coding (Frontier-Bench v0.1), Opus 5 is the new state of the art at 43.3%: ahead of Fable 5 (33.7%) and more than double Opus 4.8. On FrontierCode v1.1 it matches Fable 5, at half the price.
We've updated our "zoom tool" cookbook. When large images get downscaled, important detail can be lost. A zoom tool lets Claude request a region and get that crop back from the full-res original.
On the Chartography benchmark (100 questions over dense real-world charts), Fable 5's accuracy goes from 29% to 73% with a zoom tool, and Sonnet 5’s from 13% to 44%. See the cookbook to learn more: github.com/anthropics/cla…
We've just added several new features to Claude Managed Agents. You can now configure effort levels per agent, seed sessions with events, add up to 500 skills per session, use webhooks for environments + memory stores, and stream events for sub-agents.
Effort controls how much each Managed Agent thinks. Lowering effort gives faster responses and lower cost.
Claude Code on desktop now works with the iOS simulator. Build and run your iOS app, and the simulator opens in a panel right next to your conversation. Available today in public beta.
Claude can see the app as it runs, interact with it, and iterate until finished. Tap through the simulator yourself at any time. Available in Claude Code on desktop (macOS only, requires Xcode).
Claude Code now has a screen reader mode. Running `claude --ax-screen-reader` swaps the visual terminal UI for plain, linear text that screen readers (like VoiceOver and NVDA) can follow.
It also adds labeled lines (you:, claude:, tool:), numbered menus you answer with a digit, and a bell when Claude needs you. You can keep it on by adding "axScreenReader": true to ~/.claude/settings.json, or by setting the CLAUDE_AX_SCREEN_READER=1 environment variable.
For the small teams with big plans: Claude Team plans now start at just 2 seats instead of 5. Get shared projects, admin controls, centralized billing, SSO, and enterprise search across all your team's tools, all under one plan.
More on how to get started with the Team plan: support.claude.com/en/articles/92…
We're also keeping Claude Code weekly limits 50% higher, now through August 19, for all Pro, Max, Team, and seat-based Enterprise users. x.com/claudeai/statu…
Over the past 6 months, Claude Platform has added new APIs to help developers quickly build and deploy agents. Platform leads Katelyn Lesse, Angela Jiang, and Jess Yan sat down to talk about what has shipped and the patterns we're seeing in production.
One pattern: let Claude perform long-horizon autonomous work with self-correction. Claude Managed Agents supports this with outcomes: give Claude a rubric for task completion and let Claude loop until the rubric is satisfied.
We've resolved an issue where Fable was not selectable as a model within Claude.ai or Claude Code for a 30 minute period. You may need to restart Claude Code. If Fable is not your default model afterwards, you should reselect it with /model.
If you had extra usage turned on, you may have been overcharged. If you were affected we are refunding your credits, plus granting an additional credit equal to how much you were charged.
Claude Code's /code-review now has effort levels, with the review rewritten at every one. Low effort beats other code review tools on findings at a fraction of the token cost. High effort delivers significantly higher recall when you want to go deeper. You pick the tradeoff.
Previously, /code-review ran one fixed prompt no matter the effort. Now, each level gets a different review strategy. It picks up your session effort setting automatically, or you can pass a level explicitly (e.g. "/code-review high").
We've reset 5-hour and weekly rate limits for all users.
Claude Code artifacts can now call MCP connectors, letting you build dashboards and apps that can fetch information and take actions for each viewer on demand. Available on Pro, Max, Team, and Enterprise plans. Not available on publicly-shared artifacts.
Build an artifact once, then it pulls live data via MCP. Artifacts use the viewers’ own MCP connectors, so creators don’t need to re-run sessions to refresh, and viewers can only see the data they have access to.
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.
Make sure to update to the latest version of the desktop app. Read more in the docs: code.claude.com/docs/en/deskto…
