AI posts
AI release notes
Official updates from Anthropic, OpenAI, Google, xAI, Mistral, DeepSeek and Meta, newest first. Open any update for a short AI summary and the full notes.
Compiled by the Toolstash team · Updated
Google · Antigravity
Agent Skills
Introducing agent skills to Antigravity for enhanced customizability, alongside tab model updates and new conversation settings.
Anthropic · Claude Code
Claude Code 2.1.5
1 newAdded CLAUDE_CODE_TMPDIR environment variable to override the temp directory used for internal temp files, useful for environments with custom temp directory requirements.
Anthropic · Claude API
console.anthropic.com now redirects to platform.claude.com
The Claude Console has moved to its new home as part of our Claude brand consolidation. Existing bookmarks and links will continue working through an automatic redirect.
Anthropic · Claude apps
Cowork research preview on Claude Desktop (macOS only) for Max plans, plus 4 more changes
Cowork brings Claude Code's agentic capabilities to the Claude desktop app for knowledge work beyond coding. It runs locally on your computer in an isolated VM, enabling direct access to local files and MCP integrations. Refer to this article to learn more: Getting started with Cowork.
Google · Gemini API
Launched model lifecycle feature. Some models will now specify the lifecycle stage and deprecation timeline.…
Launched model lifecycle feature. Some models will now specify the lifecycle stage and deprecation timeline.
Anthropic · Claude Code
Claude Code 2.1.4
1 new1 fixAdded CLAUDE_CODE_DISABLE_BACKGROUND_TASKS environment variable to disable all background task functionality including auto-backgrounding and the Ctrl+B shortcut.
Anthropic · Claude Code
Claude Code 2.1.3
3 new6 fixes4 otherAdded release channel (stable or latest) toggle to /config. Added detection and warnings for unreachable permission rules, with warnings in /doctor and after saving rules that include the source of each rule and actionable fix guidance.
Anthropic · Claude Code
Claude Code 2.1.2
6 new8 fixes8 otherAdded source path metadata to images dragged onto the terminal, helping Claude understand where images originated. Added clickable hyperlinks for file paths in tool output in terminals that support OSC 8 (like iTerm).
Google · Gemini API
Launched support for Cloud Storage buckets and any public and private DB pre-signed URL as data input source…
Launched support for Cloud Storage buckets and any public and private DB pre-signed URL as data input source for the Gemini API. The file size limit has also increased from 20MB to 100MB. For details, see File input methods guide.
Anthropic · Claude Code
Claude Code 2.1.1
Anthropic · Claude Code
Claude Code 2.0.76
1 fixFixed issue with macOS code-sign warning when using Claude in Chrome integration.
Google · Gemini CLI
Gemini CLI 0.23.0
14 new17 fixes36 otherintroduce remote agent infrastructure and rename local executor. Add /auth logout command to clear credentials and auth state.
Anthropic · Claude API
We’ve retired the Claude Opus 3 model
All requests to this model will now return an error. We recommend upgrading to Claude Opus 4.5, which offers significantly improved intelligence at a third of the cost. Researchers can request ongoing access to Claude Opus 3 on the API through the External Researcher Access Program.
Google · Antigravity
Initial release of Antigravity CLI
Initial public release of the Antigravity CLI.
Google · Antigravity
Sandbox auto-approvals, plugin discovery, and clipboard fixes
Added proceed-in-sandbox auto-approvals, automated plugin skill discovery, and clipboard image reading.
Google · Antigravity
Account hiding flag, subagent timeouts, and TUI fixes
Added AGY_CLI_HIDE_ACCOUNT_INFO flag, subagent-specific interaction timeouts, and TUI fixes.
Google · Antigravity
G1 AI credits support, /credits panel, and input prompt fixes
G1 AI credits support when standard quotas run out, in-CLI /credits panel, and prompt input fixes.
xAI · Grok API
Batch API is released
Batch API is available for all customers. It enables efficient batch processing of multiple requests, providing a better experience for users who need to submit large volumes of requests at once.
xAI · Grok API
Video Generation & Next-Gen Image Generation
Video Generation and a revamped Image Generation are now available.
Google · Gemini CLI
Gemini CLI 0.22.5
1 fixcherry-pick 07e597d to release/v0.22.4-pr-15684 [CONFLICTS].
Google · Gemini CLI
Gemini CLI 0.22.4
1 fixcherry-pick 37be162 to release/v0.22.3-pr-15601 to patch version v0.22.3 and create version 0.22.4.
Google · Gemini CLI
Gemini CLI 0.22.3
1 fixcherry-pick 9cdb267 to release/v0.22.2-pr-15494 to patch version v0.22.2 and create version 0.22.3.
Google · Gemini CLI
Gemini CLI 0.22.2
Google · Gemini CLI
Gemini CLI 0.22.1
Google · Gemini CLI
Gemini CLI 0.22.0
12 new13 fixes32 otherfallback to GEMINI_CLI_IDE_AUTH_TOKEN env var. display quota stats for unused models in /stats.
Anthropic · Claude Code
Claude Code 2.0.74
6 new6 fixes1 otherAdded LSP (Language Server Protocol) tool for code intelligence features like go-to-definition, find references, and hover documentation. Added /terminal-setup support for Kitty, Alacritty, Zed, and Warp terminals.
Google · Gemini CLI
Gemini CLI 0.21.3
1 fixcherry-pick 9e6914d to release/v0.21.2-pr-15288 to patch version v0.21.2 and create version 0.21.3.
Anthropic · Claude Code
Claude Code 2.0.73
5 new1 fix3 otherAdded clickable [Image #N] links that open attached images in the default viewer. Added alt-y yank-pop to cycle through kill ring history after ctrl-y yank.
Anthropic · Claude API
We announced the deprecation of the Claude Haiku 3.5 model
Read more in Model deprecations.
OpenAI · Codex app
Agent skills in Codex
Codex now supports agent skills: reusable bundles of instructions (plus optional scripts and resources) that help Codex reliably complete specific tasks. Skills are available in both the Codex CLI and IDE extensions. You can invoke a skill explicitly by typing $skill-name (for example, $skill-installer or the experimental $create-plan skill after installing it), or let Codex select a skill automatically based on your prompt. Learn more in the skills documentation... Folder-based standard (agentskills.io). Following the open agent skills specification, a skill is a folder with a required SKILL.md and optional supporting files: text my-skill/ SKILL.md # Required: instructions + metadata scripts/ # Optional: executable code references/ # Optional: documentation assets/ # Optional: templates, resources. Install skills per-user or per-repo. You can install skills for just yourself in ~/.codex/skills, or for everyone on a project by checking them into.codex/skills in the repository. Codex also ships with a few built-in system skills to get started, including $skill-creator and $skill-installer. The $create-plan skill is experimental and needs to be installed (for example: $skill-installer install the create-plan skill from the.experimental folder). Codex ships with a small curated set of skills inspired by popular workflows at OpenAI. Install them with $skill-installer, and expect more over time.