AI posts
AI release notes
Google's official release notes. Antigravity: Google's AI coding app. Gemini CLI: Gemini in a terminal window. Gemini app: the website and phone app. Gemini API: what developers build with.
Compiled by the Toolstash team · Updated
Gemini CLI
Gemini CLI 0.39.1
Gemini CLI
Gemini CLI 0.39.0
24 new35 fixes47 otheradd memory usage integration test harness. add /memory inbox command for reviewing extracted skills.
Gemini API
Released gemini-embedding-2 as generally available. To learn more, see the Embeddings page
Released gemini-embedding-2 as generally available (GA). To learn more, see the Embeddings page.
Gemini API
Released new versions of the Deep Research agent with collaborative planning, visualization support, MCP…
Released new versions of the Deep Research agent with collaborative planning, visualization support, MCP server integration, and File Search: deep-research-preview-04-2026: Designed for speed and efficiency, ideal to be streamed back to a client UI. deep-research-max-preview-04-2026: Maximum comprehensiveness for automated context gathering and synthesis.
Gemini CLI
Gemini CLI 0.38.2
1 fixcherry-pick 14b2f35 to release/v0.38.1-pr-24974 to patch version v0.38.1 and create version 0.38.2.
Antigravity
Bug Fixes
Fixed bug that prevented MCP servers from loading and bug that prevented accessing workspace-specific settings.
Gemini CLI
Gemini CLI 0.38.1
1 fixcherry-pick 050c303 to release/v0.38.0-pr-25317 to patch version v0.38.0 and create version 0.38.1.
Gemini API
Launched Gemini 3.1 Flash TTS Preview, our cost-efficient, expressive, and steerable text to speech model.…
Launched Gemini 3.1 Flash TTS Preview, our cost-efficient, expressive, and steerable text to speech model. Read the Text-to-Speech docs to learn more.
Gemini app
Meet your new desktop assistant: Gemini for Mac
What: We’re introducing the Gemini app for Mac, a native desktop experience built to help you get more done without disrupting your flow. With a simple keyboard shortcut (Option + Space), you can bring up Gemini alongside any application you're using. You can also seamlessly share your window, allowing Gemini to understand your context and assist with exactly what’s on your screen. The new desktop app is available to users on macOS versions 15 and up, globally, for free. Download the app directly at gemini.google/desktop. Why: By bringing a native app to Mac, we're cutting down on context switching and giving you a faster, more integrated way to use Gemini alongside the tools you use every day.
Gemini CLI
Gemini CLI 0.38.0
25 new38 fixes47 otherexplicitly allow web_fetch in plan mode with ask_user. add experimental.adk.agentSessionNoninteractiveEnabled setting.
Gemini API
Released gemini-robotics-er-1.6-preview, our updated robotics model. It now has new capabilities like…
Released gemini-robotics-er-1.6-preview, our updated robotics model. It now has new capabilities like instrument reading, improved spatial and physical reasoning capabilities. To learn more, see Gemini Robotics ER page and the blog. Deprecation announcement: The gemini-robotics-er-1.5-preview model will be shut down on April 30, 2026 at 9AM PST.
Gemini CLI
Gemini CLI 0.37.2
1 fixcherry-pick 9d741ab to release/v0.37.1-pr-24565 to patch version v0.37.1 and create version 0.37.2.
Gemini CLI
Gemini CLI 0.37.1
Gemini CLI
Gemini CLI 0.37.0
42 new64 fixes75 othercentralize test agents into test-utils for reuse. add maxActionsPerTask for browser agent setting.
Antigravity
Agent Permissions
New unified permissions system to control agent actions.
Gemini API
Released gemma-4-26b-a4b-it and gemma-4-31b-it, available on AI Studio and through the Gemini API, as part…
Released gemma-4-26b-a4b-it and gemma-4-31b-it, available on AI Studio and through the Gemini API, as part of the Gemma 4 launch.
Gemini CLI
Gemini CLI 0.36.0
40 new50 fixes69 othermulti-registry architecture and tool filtering for subagents. integrate task tracker protocol into core system prompt.
Gemini API
Introduced the new Flex and Priority inference tiers, offering more options for optimizing cost or latency
Introduced the new Flex and Priority inference tiers, offering more options for optimizing cost or latency.
Gemini API
Launched Veo 3.1 Lite Preview, veo-3.1-lite-generate-preview, our most cost-efficient video generation…
Launched Veo 3.1 Lite Preview, veo-3.1-lite-generate-preview, our most cost-efficient video generation model, designed for rapid iteration and building high-volume applications. The gemini-2.5-flash-lite-preview-09-2025 model has been shut down. Use gemini-3.1-flash-lite-preview instead.
Antigravity
Onboarding Fix
Fixed bug that prevented new users from completing onboarding.
Gemini CLI
Gemini CLI 0.35.3
1 fixcherry-pick 765fb67 to release/v0.35.2-pr-24055 [CONFLICTS].
Gemini CLI
Gemini CLI 0.35.2
Gemini CLI
Gemini CLI 0.35.1
Gemini API
Released gemini-3.1-flash-live-preview, the latest audio-to-audio model designed for real-time dialogue and…
Released gemini-3.1-flash-live-preview, the latest audio-to-audio (A2A) model designed for real-time dialogue and voice-first AI applications. Read the Live API docs to get started.
Gemini app
Make the switch: Seamlessly bring your AI memories and chat history to Gemini
What: Starting today, we are rolling out new switching tools to your Settings page for all consumer accounts. You can now easily import your personal context, preferences, and full chat history from other AI apps directly into Gemini. To bring over your memories, simply select the import option in Settings, paste the suggested prompt into your other AI app, and copy its generated summary back into Gemini. You can also seamlessly pick up where you left off by uploading a ZIP file of your chat history from other providers. Additionally, we are renaming the "past chats" feature to "memories," which will roll out in the app over the next few weeks. Why: The most helpful AI assistant is one that understands your preferences and past conversations. Starting over with a new assistant can feel daunting, so we created these tools to let you quickly get Gemini up to speed on what matters most to you without starting from scratch. By bringing over your key facts and past conversation threads, you can pick up right where you left off and continue building on your ideas right inside Gemini.
Gemini API
Launched Lyria 3 music generation models: lyria-3-clip-preview and lyria-3-pro-preview. Both models accept…
Launched Lyria 3 music generation models: lyria-3-clip-preview (30-second clips) and lyria-3-pro-preview (full-length songs). Both models accept text and image inputs and generate high-quality, 48kHz stereo audio.
Antigravity
Linux Sandboxing and MCP Improvements
Linux support for sandboxing, improved MCP authentication, and deprecations in Manager.
Gemini CLI
Gemini CLI 0.35.0
42 new52 fixes68 othercustomizable keyboard shortcuts. Thread AgentLoopContext through core.
Gemini API
Rolled out Prepay and Postpay billing plans in AI Studio. Existing accounts may be affected; read the…
Rolled out Prepay and Postpay billing plans in AI Studio. Existing accounts may be affected; read the Billing documentation for more information.
Gemini API
Released the new Built-in Tools and Function Calling Combination feature, making it possible to use Gemini's…
Released the new Built-in Tools and Function Calling Combination feature, making it possible to use Gemini's built-in tools alongside custom function calling tools in a single API call. Grounding with Google Maps is now supported for Gemini 3 models going forward.