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 aipreviewengineer ·
Claude SDKs add support for code execution tool version 20260120
The Python, TypeScript, Go, Java, Ruby, PHP, and C# SDKs now support the `code_execution_20260120` tool version. This update enhances tool usage by enabling REPL state persistence and is the minimum version required for programmatic tool calling. The feature is available on specific Claude model versions and requires setting the tool's type accordingly.
feature - Claude Code Releases sdkaimedia ·
Claude Code v2.1.191: Rewind support, fixes, and performance
This release adds support for resuming conversations with the new `/rewind` command and addresses several bugs affecting agent behavior, UI elements, and command-line interactions. Performance is improved with reduced CPU usage during streaming and better memory management. These updates are primarily for users of Claude Code and its agent functionalities.
patch feature - Anthropic Python SDK Releases sdkaimedia ·
Anthropic SDK Python v0.112.0: System message streaming, memory tool fixes
Anthropic's Python SDK has been updated to v0.112.0, introducing support for streaming system message events and fixing a bug in the memory tool related to directory creation. These updates enhance the SDK's capabilities for developers building with Anthropic's AI models. The release includes a new feature for system message streaming and several minor improvements. This update is available now for all users of the Python SDK.
feature patch - Claude Code Releases sdkaiengineer ·
Claude Code CLI and VS Code Extension Updates
The latest update for Claude Code introduces new security features like credential blocking and organization-wide model restrictions, alongside usability enhancements such as mouse click support for menus and improved handling of structured output. This release also addresses several critical bugs impacting command execution, remote tool calls, and text encoding, benefiting developers using the CLI or VS Code extension.
patch feature - Anthropic News aiengineer ·
Anthropic Introduces Claude Tag for Collaborative AI in Slack
Anthropic has launched Claude Tag, a new feature allowing teams to integrate Claude as a collaborative AI member within Slack channels. This enables users to delegate tasks, leverage connected tools and data, and benefit from Claude's contextual memory and proactive updates, enhancing team productivity. Claude Tag is available today in beta for Claude Enterprise and Team customers, offering a more integrated and asynchronous AI collaboration experience.
feature announcement - Claude Code Releases sdkaiengineermedia ·
Claude Code v2.1.186 CLI Enhancements and Fixes
Claude Code v2.1.186 introduces CLI authentication for MCP servers and new status filtering for workflows, improving developer workflow management. These updates primarily benefit software engineers and architects using the CLI for development and deployment tasks. The release also addresses several bugs, including issues with streaming requests and subagent transcript handling, while adding new features like teammate mode for iTerm2.
feature patch - Anthropic Python SDK Releases sdkaiengineer ·
Anthropic SDK Python adds refusal fallback middleware tagging
Anthropic's Python SDK has been updated to version 0.111.0, introducing a new feature that tags refusal-fallback middleware requests. This change helps developers better understand and manage how the SDK handles situations where model responses are refused, potentially improving error handling and debugging for applications relying on the SDK. The update is available now for users of the Anthropic Python SDK.
feature - Anthropic Python SDK Releases sdkai ·
Anthropic SDK Python v0.110.0 adds code execution tool support
Anthropic's Python SDK has been updated to version 0.110.0, introducing support for the new code_execution_20260120 tool. This update enhances the SDK's capabilities for developers integrating with Anthropic's AI models. Several bug fixes are also included, addressing issues with header merges, stream event types for Bedrock, and header key management. The release is available now for users of the Python SDK.
feature patch - Anthropic News ai ·
Anthropic Opens Seoul Office, Forges New Korean AI Partnerships
Anthropic has opened a new office in Seoul, South Korea, signaling a deeper commitment to the region's burgeoning AI ecosystem. This expansion is accompanied by new partnerships with Korean enterprises, startups, and researchers, aiming to accelerate the deployment and development of AI technologies like Claude. These collaborations span various sectors, from cloud and gaming to energy and IT services, and extend to academic research and non-profit initiatives, highlighting the broad impact and diverse applications of Anthropic's AI models.
announcement feature - Claude Platform Release Notes ai ·
Claude Platform Updates: New Models, Tools, and Cloud Support
Anthropic has released Claude Fable 5 and Claude Opus 4.8, offering enhanced capabilities like 1M token context windows and improved reasoning. New tool versions for code execution and web search, along with expanded support for Claude Platform on AWS, cater to developers and researchers. The release also includes deprecations of older models like Sonnet 4 and Opus 4, signaling a push towards newer, more powerful versions.
feature deprecation announcement - Claude Code Releases sdkaiengineer ·
Claude Code v2.1.176: Improved credential caching, session features, and bug fixes
Claude Code version 2.1.176 introduces several enhancements, including session titles in the conversation's language and improved AWS Bedrock credential caching for longer validity. It also fixes numerous bugs affecting model selection, auto mode fallbacks, hook conditions, sandbox operations, and remote control functionality. These updates benefit developers and organizations using Claude Code by improving stability, usability, and security, particularly for those with specific model allowlists or complex session management needs.
patch feature - Claude Code Releases sdkai ·
Claude Code v2.1.175: Enforce Available Models Setting
A new `enforceAvailableModels` setting is introduced in Claude Code v2.1.175, enhancing security and control. When enabled, this setting ensures that the default model respects the `availableModels` allowlist, preventing fallback to disallowed models. This change primarily impacts organizations and administrators managing model access for their development teams.
patch feature - Anthropic News aiengineerfinance ·
Anthropic and TCS Partner to Bring Claude AI to Regulated Industries
Anthropic and Tata Consultancy Services (TCS) are partnering to bring Claude AI to regulated industries like finance and healthcare. TCS will deploy Claude internally to 50,000 employees and build Claude-powered products for clients, aiming to enhance accuracy and compliance. This collaboration will initially focus on industry-specific offerings such as claims processing and lending advisory, with work already underway in areas like customer experience improvement and software engineering productivity.
announcement feature - Anthropic News ai ·
Anthropic Public Record Survey Reveals Public Views on AI
Anthropic's first Public Record survey of nearly 52,000 Americans highlights significant public hopes for AI in areas like disease cure and support for people with disabilities, alongside widespread fears of job loss and cognitive dependency. The survey also indicates strong support for government regulation of AI, particularly concerning privacy, child safety, and liability. These findings are based on a November-December 2025 survey and aim to inform Anthropic's approach to AI development, building on previous user studies.
announcement - Anthropic News aigovernment ·
Anthropic suspends Fable 5 and Mythos 5 due to US government directive
Anthropic is suspending access to its Fable 5 and Mythos 5 models for all customers in response to a US government export control directive. The government cited national security concerns, believing a method to bypass the model's safeguards has been discovered. This action affects all users, including foreign national Anthropic employees, though other Anthropic models remain unaffected. Anthropic disagrees with the severity of the finding and is working to restore access.
announcement breaking - Claude Platform Release Notes aipreviewengineer ·
Claude Platform Updates: Code Execution and Web Tools Enhanced
Anthropic has updated its code execution, web search, and web fetch tools on the Claude platform. The code execution tool now explicitly states a 90-second time limit to better manage cell execution, while the web tools have added a response inclusion parameter to streamline agentic workflows. These updates aim to improve the predictability and efficiency of Claude's interactions with external tools for developers.
feature - Anthropic News aiengineer ·
Anthropic and DXC Technology form global alliance to integrate Claude
Anthropic is partnering with DXC Technology to integrate its Claude AI model into systems used by major banks, airlines, and other regulated industries. DXC will train thousands of engineers to deploy Claude within customer environments, leveraging the AI for modernization, cybersecurity, and application services. This alliance aims to bring Claude's capabilities to mission-critical systems, with DXC having already integrated Claude into its own operations and AI-native orchestration platform, DXC OASIS.
announcement feature - Anthropic News aiengineer ·
Anthropic Launches Claude Corps AI Fellowship Program
Anthropic is launching Claude Corps, a national fellowship program that will train 1,000 early-career individuals in AI skills and place them at nonprofits for a year. This initiative aims to extend the benefits of AI to underserved communities and provide fellows with valuable career skills, backed by an initial $150 million investment. The program partners with CodePath for fellowship management and Social Finance for evaluation, and will support 400 nonprofits over the next year.
announcement feature - Claude Code Releases sdkaiengineermedia ·
Claude Code v2.1.172: Sub-agents, Bedrock region, and numerous fixes
This patch for Claude Code introduces a significant enhancement allowing sub-agents to spawn their own sub-agents up to five levels deep, expanding agent capabilities. It also improves Amazon Bedrock integration by respecting AWS region configuration and includes fixes for session management, tool usage, and UI rendering. These changes benefit developers and architects using Claude Code for complex agent-based workflows, particularly those integrating with AWS services or encountering specific tool/UI bugs.
patch feature - Claude Platform Release Notes ai ·
Claude Platform Updates: New Models, Tooling, and AWS Integration
Anthropic has released updates to its Claude Platform, including new models like Claude Fable 5 and Claude Opus 4.8, offering enhanced capabilities and larger context windows. The platform also introduces new tool functionalities, improved agent orchestration on AWS, and deprecates older models, requiring users to migrate to newer versions. These changes affect developers and organizations using the Claude API and its associated client SDKs and console.
feature deprecation 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.