Anthropic Releases
Anthropic news, Claude releases and SDK updates. New features, breaking changes, security advisories and deprecations - each summarised in plain English and updated continuously.
Tracking 218 Anthropic releases · Updated
- Claude Platform Release Notes aigaengineer ·
Claude Platform Updates: New Sonnet 5, API Key Expiration, Agent Memory
Anthropic has released Claude Sonnet 5 with a 1M token context window and updated pricing, introducing significant behavioral changes and a new tokenizer for Sonnet 5. The Claude Platform now supports API key expiration in the Console, enhancing security for administrators. Additionally, updates to agent memory handling and SDKs improve developer experience and tool integration across various models.
feature patch deprecation - Claude Code Releases sdkaigaengineer ·
Claude Code v2.1.206: Enhanced Commands and Agent Upgrades
Claude Code v2.1.206 introduces directory path suggestions for `/cd`, a `/doctor` check to trim `CLAUDE.md` files, and improved `/commit-push-pr` functionality. These updates enhance developer workflow and agent management, with background agents now upgrading seamlessly post-Claude Code updates. The release also addresses numerous bugs, including login failures and input responsiveness issues across various commands and server configurations.
patch - Claude Platform Release Notes aipreviewengineer ·
Claude API Update: Agent Memory Listing Changes
Anthropic is introducing a new beta header, `agent-memory-2026-07-22`, for the List Memories endpoint, altering response ordering and parameter behavior. This change impacts how developers retrieve memory data and requires updates to SDK usage and explicit beta header configurations. The new header will eventually replace `managed-agents-2026-04-01` on July 22, 2026, and developers are advised to restart pagination when adopting it.
feature breaking announcement - Anthropic News aiengineer ·
UST partners with Anthropic to embed Claude AI in physical product development
UST is integrating Anthropic's Claude AI into its engineering and manufacturing processes to improve physical AI applications. This partnership aims to catch design flaws earlier, speed up validation cycles, and enhance operational efficiency across various industries. UST is also training 20,000 of its engineers on Claude to facilitate AI adoption and deployment within its client solutions.
announcement feature - Claude Platform Release Notes aigaengineer ·
Claude Platform Updates: API Keys, New Models, and Tooling Enhancements
Anthropic has released updates to the Claude Platform, including new model versions like Claude Sonnet 5, Fable 5, and Mythos 5, and enhanced tooling for API keys and managed agents. These changes offer improved context windows, adaptive thinking, and more granular control over agent behavior and security. The updates affect developers building applications with Claude models, providing new capabilities and requiring some migration steps for certain features.
feature patch deprecation announcement - Anthropic News ai ·
Anthropic Seeks Public's Hardest AI Questions for Transparency Initiative
Anthropic is launching an initiative to gather the public's most challenging questions about artificial intelligence, aiming to transparently address societal hopes and concerns. This effort includes large-scale surveys, focus groups, and a public commitment to report on actions taken to mitigate AI risks and maximize benefits. The company, a Public Benefit Corporation, seeks to align AI development with public interest and invites direct input via a dedicated website.
announcement - Anthropic News aigovernancefinance ·
Ben Bernanke Appointed to Anthropic's Long-Term Benefit Trust
Anthropic's Long-Term Benefit Trust (LTBT) has appointed former Federal Reserve Chair Ben Bernanke as a new member to oversee the responsible development of advanced AI for humanity's long-term benefit. His expertise in economics and navigating financial crises will inform Anthropic's approach to AI's economic impacts. Bernanke joins an independent body tasked with ensuring AI development aligns with societal good.
announcement - Claude Release Notes aipreviewengineer ·
Claude Adds Monthly Usage Recap and Focus Tools
Anthropic introduced a new 'Monthly Recap' feature in Claude, providing insights into user activity and work patterns with the AI model. This feature aims to enhance user awareness and productivity by offering data on topics, active days, and peak hours. It is currently in beta for Free, Pro, and Max plan users on web and desktop versions, requiring memory to be enabled, and is complemented by new time management tools.
feature announcement - Anthropic News aipreviewengineer ·
Anthropic Beta: Claude Usage Reflection Dashboard
Anthropic has launched a beta feature allowing users to track and analyze their interaction patterns with Claude, aiming to improve AI integration into daily life. This reflection dashboard visualizes usage across key topics and task types, offering insights and interactive prompts to refine AI collaboration. It is available to Free, Pro, and Max users with Memory enabled, with specific privacy measures for sensitive conversations.
feature announcement - Claude Code Releases sdkaipreviewengineer ·
Claude Code v2.1.205: Bug fixes and usability improvements
This release of Claude Code, version 2.1.205, addresses numerous bugs and introduces several usability enhancements for its AI coding assistant. Key fixes include preventing silent data loss during agent interactions, resolving issues with file handling on Windows, and improving the reliability of background agent operations. The update also enhances the agent view with clearer status indicators and adds a diagnostic tool. These changes benefit developers and architects using Claude Code for coding assistance, aiming for a more stable and informative user experience.
patch - Claude Code Releases sdkaiengineermedia ·
Claude-Code v2.1.204: Fixes hook event streaming in headless sessions
Version 2.1.204 of Claude-Code resolves an issue where hook events failed to stream during SessionStart in headless sessions. This prevented remote workers from being prematurely idled. The fix ensures proper event propagation for headless operation.
patch - Claude Release Notes aipreviewengineer ·
Claude Cowork available on web and mobile
Claude Cowork is expanding to web and mobile platforms, complementing its existing desktop availability. This feature allows sessions and files to be saved to a user's Claude account, enabling access across devices and ensuring scheduled tasks run even when a device is offline. The rollout begins with the Max plan over the coming weeks, and all chat and Cowork features are now consolidated in a single location.
feature announcement - Claude Release Notes aiengineer ·
Claude's Microsoft 365 connector gains write capabilities
The Microsoft 365 connector for Claude now supports write operations, allowing it to draft and send emails, manage calendar events, update mailbox settings, and create/update files in OneDrive and SharePoint. This significantly expands its utility beyond search for users interacting with Microsoft 365 data. Administrators must enable these new write permissions, and users can find setup details in the provided documentation.
feature - Claude Code Releases sdkaipreviewengineer ·
Claude Code v2.1.203: Session Recovery and UI Improvements
This update to Claude Code addresses numerous bugs related to background session stability and responsiveness, particularly on macOS and Windows. It improves the user experience by adding warnings for expiring logins, clearer visibility of active modes, and better recovery from session staleness. The release affects developers using Claude Code for coding assistance, especially those working with background agents or on macOS.
patch feature - Claude Code Releases sdkai ·
Claude-Code v2.1.202: Dynamic workflows, OpenTelemetry, and bug fixes
This update introduces a "Dynamic workflow size" setting to control agent count and adds OpenTelemetry attributes for better workflow tracing. Several bugs affecting session management, remote control, workflow parsing, and voice dictation have been fixed. These changes benefit users working with complex workflows, distributed tracing, and those encountering specific session or input issues.
patch - Anthropic News aiengineergovernment ·
Alberta Government Uses Claude to Enhance Cybersecurity
The Government of Alberta has successfully leveraged Claude Code with Opus and Sonnet models to review, identify, and fix cybersecurity vulnerabilities across millions of lines of government code. This initiative significantly accelerated the process of securing systems, which would have traditionally taken years. The program involved scanning 466 million lines of code in just 20 hours, remediating security gaps, and developing new tools to bolster system safety, showcasing a large-scale application of AI in government cybersecurity.
announcement feature - Claude Code Releases sdkaiengineer ·
Claude Sonnet 5 system role change for harness reminders
Claude Sonnet 5 sessions will no longer use the mid-conversation system role for harness reminders. This change impacts users who rely on this specific system role for reminder functionality. The update ensures cleaner and more direct communication within the API.
patch - Claude Code Releases sdkai ·
Claude Code v2.1.200: Dialogs, permissions, and background agent fixes
Claude Code v2.1.200 updates `AskUserQuestion` dialogs to require explicit opt-in for auto-continuation and changes the default permission mode to "Manual" across all interfaces for enhanced control. Several critical bugs affecting background session stability, agent startup, and data corruption have been resolved, ensuring more reliable agent operation. Additionally, improvements to UI rendering, accessibility, and the installation process are included for a smoother user experience.
patch - Anthropic News aisecurityengineer ·
Anthropic Details Fable 5 Cybersecurity Safeguards and Jailbreak Framework
Anthropic has redeployed Fable 5 globally, providing new details on its cybersecurity safeguards, specifically safety classifiers designed to detect and block dangerous uses. The company also introduced a draft AI jailbreak severity framework developed with Glasswing partners, aiming to standardize risk communication. These updates are relevant to all users, security researchers, and AI developers interested in responsible AI deployment and risk mitigation.
feature announcement - Claude Code Releases sdkaimedia ·
Claude Code v2.1.199: Improved error handling and agent stability
This release addresses several stability and error handling issues within Claude Code, particularly concerning background agents and subagent interactions. It improves how stacked skill invocations are handled and ensures partial responses are preserved during server errors. These fixes benefit developers using Claude Code, especially those running complex agent workflows or experiencing transient API issues.
patch
About Anthropic release tracking on ReleaseBytes
Anthropic ships Claude model releases, API updates and SDK versions on a rapid cadence. ReleaseBytes tracks the official Anthropic announcement channels and SDK changelogs, summarising each release and flagging model deprecations and breaking changes so teams building on Claude stay ahead of them.
Frequently asked questions
How often are Anthropic release notes updated on ReleaseBytes? ›
Continuously. ReleaseBytes monitors the official Anthropic release channels around the clock and publishes a plain-English summary of each announcement shortly after it lands.
What kinds of Anthropic changes does ReleaseBytes track? ›
New features, enhancements, bug fixes, security advisories, breaking changes, deprecations and end-of-life announcements. Every item is tagged by type so you can filter to just the changes that need action.
How can I get alerts for new Anthropic releases? ›
Set up a free email or Slack alert filtered to Anthropic, subscribe to the weekly digest, or follow the RSS feed. Teams can also install the ReleaseBytes GitHub App or connect via MCP.
Where does the Anthropic release data come from? ›
From the official sources: Anthropic news, Claude releases and SDK updates. Every item links back to the original vendor announcement.