Best of Google Gemini — 2025

  1. 1
    Article
    Avatar of googledevsGoogle Developers·32w

    Say hello to a new level of interactivity in Gemini CLI

    Gemini CLI v0.9.0 introduces pseudo-terminal (PTY) support, enabling interactive commands like vim, top, and git rebase -i to run directly within the CLI context. The update uses node-pty to spawn processes in a virtual terminal, streaming real-time snapshots of terminal state including text, colors, and cursor position. This architecture supports two-way communication with keyboard input and window resizing, eliminating the need to switch to separate terminals while maintaining full context awareness.

  2. 2
    Video
    Avatar of youtubeYouTube·49w

    Full Stack AI Agent course with inngest and Gemini

    A comprehensive tutorial on building a full-stack AI agent application using Inngest for background workers and Gemini for AI processing. The application features a smart ticketing system with role-based access control, automated ticket assignment based on user skills, and AI-powered ticket analysis. Key components include user authentication with JWT, MongoDB for data storage, email notifications via background workers, and AI agents that automatically categorize tickets, set priorities, generate helpful notes, and assign them to appropriate moderators based on their skills.

  3. 3
    Video
    Avatar of t3dotggTheo - t3․gg·27w

    Google just dropped their Cursor killer (FREE Gemini 3 Pro???)

    Google released Anti-gravity, a free AI-powered IDE built on VS Code that integrates Gemini 3 Pro. The editor features an innovative agent manager workflow that operates as a separate window, browser control capabilities through Chrome integration, and automatic asset generation. While the tool shows promise with successful one-shot project creation and unique UX patterns for managing multiple tasks, it suffers from numerous bugs including broken extensions, inconsistent performance, and UI glitches. The editor appears to be based on Windsurf code from Google's recent acquisition, offering generous free usage limits during its preview period.

  4. 4
    Article
    Avatar of tcTechCrunch·23w

    Google's vibe-coding tool Opal comes to Gemini

    Google is integrating Opal, its vibe-coding tool for building AI-powered mini apps, directly into the Gemini web interface. Users can now create custom apps (called Gems) using natural language descriptions, with a visual editor that arranges steps without writing code. The tool includes a new view that converts written prompts into step-by-step workflows, and advanced users can access more customization options at opal.google.com. This move positions Google alongside other AI-powered app-building tools like Lovable, Cursor, and offerings from Anthropic and OpenAI.

  5. 5
    Article
    Avatar of googledevsGoogle Developers·27w

    Announcing the Genkit Extension for Gemini CLI

    Google launched the Genkit Extension for Gemini CLI, enabling developers to build and debug AI applications directly from the terminal. The extension provides context-aware assistance through tools like flow execution, documentation lookup, and OpenTelemetry trace analysis. It integrates Genkit's MCP server with specialized context files to give Gemini CLI comprehensive understanding of Genkit's architecture and best practices. Developers can install it via a single command and immediately access language-specific guidance, run flows for debugging, and receive tailored code suggestions that follow Genkit patterns.

  6. 6
    Article
    Avatar of androiddevAndroid Developers Blog·23w

    Build smarter apps with Gemini 3 Flash

    Gemini 3 Flash is now available through Firebase AI Logic, offering frontier AI intelligence optimized for speed and cost-effectiveness. The model excels at reasoning, tool use, and multimodal capabilities including video analysis and visual Q&A. Integration is straightforward using Firebase AI Logic SDK for Android apps, with features like AI monitoring dashboards for tracking latency and costs, and server-side prompt templates for secure prompt management. Gemini 3 Flash is also available in Android Studio for development assistance at no cost, with higher rate limits accessible through AI Studio API keys or Gemini Code Assist licenses.

  7. 7
    Article
    Avatar of logrocketLogRocket·52w

    Gemini 2.5 and the future of AI reasoning for frontend devs

    Google's Gemini 2.5 Pro introduces advanced reasoning capabilities for frontend development, featuring a 1 million token context window and multimodal processing. The model leads current AI leaderboards for web development tasks and offers competitive pricing compared to GPT-4o and Claude. Key advantages include native step-by-step reasoning, ability to process entire codebases, and integration with Google's custom TPU hardware for faster, cheaper inference. Practical demonstrations show the model can generate complete web applications, 3D games, and recreate popular social media interfaces from single prompts.

  8. 8
    Article
    Avatar of googledevsGoogle Developers·23w

    Introducing Agent Development Kit for TypeScript: Build AI Agents with the Power of a Code-First Approach

    Google released Agent Development Kit (ADK) for TypeScript, an open-source framework for building AI agents and multi-agent systems. The code-first approach lets developers define agent logic, tools, and orchestration directly in TypeScript, applying traditional software development practices like version control and CI/CD. While optimized for Gemini and Vertex AI, ADK is model-agnostic and supports third-party tools. It includes native integration with MCP Toolbox for database connections and supports the latest Gemini 3 models.

  9. 9
    Article
    Avatar of googledevsGoogle Developers·41w

    Gemini CLI + VS Code: Native diffing and context-aware workflows

    Google's Gemini CLI now offers deep VS Code integration through a companion extension, enabling context-aware AI suggestions and native diffing directly within the editor's integrated terminal. The setup involves installing the extension with `/ide install` and managing it with simple enable/disable commands.

  10. 10
    Article
    Avatar of googledevsGoogle Developers·42w

    The Google Developer Program is evolving

    Google Developer Program introduces new monthly subscription tier at $24.99/month, launches centralized forums at discuss.google.dev, and expands AI tool access. The program now offers flexible pricing, unified community platform with migrated existing forums, and enhanced benefits including Google Cloud credits, Gemini Code Assist Standard, and Firebase Studio Workspaces. A new Google Cloud & NVIDIA Community provides specialized learning pathways for AI inference tasks.

  11. 11
    Article
    Avatar of googledevsGoogle Developers·27w

    Making the terminal beautiful one pixel at a time

    Gemini CLI v0.15.0 introduces a major UI overhaul with a new rendering foundation that eliminates screen flicker, bouncing prompts, and visual artifacts. Key improvements include mouse support for navigation, persistent header lines for context, stable input positioning at the bottom, and clean terminal resizing. The update maintains full chat history accessibility while delivering a graphical-interface-level polish in the terminal. Users can upgrade via npm and provide feedback on GitHub.

  12. 12
    Article
    Avatar of googledevsGoogle Developers·1y

    Building agents with Google Gemini and open source frameworks

    Google Gemini models offer advanced AI agent-building capabilities through multimodality and function calling. Coupled with open-source frameworks like LangGraph, CrewAI, LlamaIndex, and Composio, developers can create sophisticated agents for various applications. Each framework provides unique features to enhance agent development, from complex workflows to knowledge retrieval and tool integrations.

  13. 13
    Article
    Avatar of firebase-developersFirebase Developers·30w

    Building Arc: An AI Messenger Powered by Firebase, Flutter, and Vertex AI

    Arc is a privacy-focused messaging app built with Flutter for cross-platform development, Firebase for real-time messaging and authentication, Cloud Run for scalable microservices, and Vertex AI with Gemini models for AI-powered conversational companions. The architecture emphasizes four pillars: stability, speed, lightweight design, and high security. Key features include ephemeral messaging, mesh networking for offline resilience, and RAG-based AI characters grounded in Vertex AI Search to prevent hallucinations. The team achieves rapid iteration with 144 updates in 34 months through rigorous Flutter optimization using static analysis and dynamic profiling.

  14. 14
    Article
    Avatar of thevergeThe Verge·37w

    Google finally details Gemini usage limits

    Google has clarified usage limits for its Gemini AI service across different subscription tiers. Free accounts get 5 daily prompts with Gemini 2.5 Pro, 5 Deep Research reports, and 100 generated images. AI Pro subscribers receive 100 daily prompts and 1,000 images, while AI Ultra offers unlimited access. This replaces previous vague descriptions with specific numerical limits.

  15. 15
    Video
    Avatar of youtubeYouTube·23w

    4-Step Gemini 3.0 Pro System For Beautiful UI Designs

    A four-step workflow for generating UI designs using Gemini 3.0 Pro before building functionality. The process starts with creating a product requirements document (PRD), extracting core features and UX considerations, building a design system based on visual inspiration, and finally generating screen-by-screen designs with all states. The approach emphasizes designing upfront rather than treating UI as an afterthought, using structured prompts to guide the AI through creating a complete design system with colors, typography, and component specifications that can be implemented in React with Tailwind CSS.

  16. 16
    Article
    Avatar of collectionsCollections·33w

    Introducing the Genkit Extension and Ecosystem for Gemini CLI

    Google launched an extension ecosystem for Gemini CLI, including the Genkit Extension for AI-powered development assistance. The platform supports third-party integrations from partners like Figma, Stripe, and Dynatrace through an open-source model on GitHub. With over 1 million users and 22+ extensions at launch, developers can install and chain extensions via single commands to build customized toolchains with framework-aware code generation, debugging, and documentation access.

  17. 17
    Video
    Avatar of fireshipFireship·26w

    Did Google just kill OpenAI?

    Google released Gemini 3 Pro, which topped major AI benchmarks and prompted companies like Anthropic to switch from Claude. The release boosted Google's stock by 6% to an all-time high. Google also unveiled anti-gravity, an agentic coding platform built on technology from the acquired Windsurf team, competing with other AI-powered development tools like Cursor and their own idx/Firebase Studio.

  18. 18
    Video
    Avatar of fireshipFireship·38w

    Google’s nano banana is bananas… let’s run it

    Google released Gemini Flash 2.5 image (nicknamed 'Nano Banana'), a new AI image editing model that enables photo alterations through text prompts while maintaining character consistency. The model costs 3.9 cents per image via API, excels at blending multiple images, and can generate realistic photos based on locations or sketches. However, it has limitations including text rendering issues, prompt adherence problems, and heavy content censorship.

  19. 19
    Article
    Avatar of medium_jsMedium·42w

    Google Gemini 2.5 Deep Think : The best ever AI is here

    Google released Gemini 2.5 Deep Think, an AI model that prioritizes reasoning over speed by taking more time to think through problems. Available to Ultra subscribers, it achieved bronze-level performance at the International Math Olympiad and leads benchmarks in coding and mathematical reasoning. Unlike traditional chatbots that respond instantly, Deep Think uses parallel reasoning and reinforcement learning to test ideas and revise answers, making it ideal for complex problems in mathematics, coding, and design. The model is more cautious and less prone to hallucination but may refuse some harmless requests.

  20. 20
    Article
    Avatar of lightbendLightbend·1y

    Building a real-time video AI service with Google Gemini

    Learn how an agentic AI service was built to process real-time video, utilizing the Google Gemini Multimodal Live API. The project, implemented using Akka's SDK, overcame challenges with the synchronous Python client provided by Google by creating a custom reactive client. The service was scaled to thousands of TPS and deployed within a Google VPC.

  21. 21
    Article
    Avatar of elevateElevate·31w

    Gemini CLI Tips & Tricks

    Comprehensive guide covering 30+ advanced techniques for using Gemini CLI, Google's open-source AI terminal assistant. Covers persistent context with GEMINI.md files, custom slash commands, MCP server extensions, memory management, checkpointing for rollbacks, file and image referencing with @ syntax, on-the-fly tool creation, system troubleshooting, YOLO mode for auto-approval, headless scripting, and session management. Includes setup instructions, authentication options (free Google account or API key), and practical examples for coding tasks, debugging, content generation, and workflow automation.

  22. 22
    Article
    Avatar of googledevsGoogle Developers·22w

    Conductor: Introducing context-driven development for Gemini CLI

    Conductor is a new extension for Gemini CLI that introduces context-driven development by formalizing project specs and plans in persistent Markdown files. Instead of relying on chat logs, it helps developers create structured documentation that lives alongside code, enabling better planning, team collaboration, and AI agent control. The workflow involves setting up project context, creating tracks for features with spec and plan documents, and implementing changes while maintaining state across sessions. This approach keeps developers in control while allowing AI to work with deep project awareness.

  23. 23
    Article
    Avatar of googledevsGoogle Developers·27w

    Introducing the Jules extension for Gemini CLI

    Google launched the Jules extension for Gemini CLI, an autonomous coding assistant that handles tasks asynchronously in a background virtual machine. While Gemini CLI serves as an interactive terminal collaborator for active tasks, Jules works independently to clone code, install dependencies, and modify files. Developers can delegate tasks using the /jules command and check progress without interrupting their workflow. The extension requires Gemini CLI v0.4.0 or newer and can be installed with auto-update capabilities.

  24. 24
    Video
    Avatar of youtubeYouTube·42w

    n8n Tutorial for Beginners - Build Your First Free AI Agent

    A comprehensive tutorial showing how to build AI agents using n8n workflow automation tool completely for free. Covers setting up n8n with Docker, integrating with Google Gemini AI model, connecting to QuickBooks for invoice data, and creating automated payment reminder emails with human approval workflows through Discord. Demonstrates building an agent that can reason, use tools, and maintain memory to handle overdue invoice management automatically.

  25. 25
    Video
    Avatar of fireshipFireship·47w

    Google’s new CLI tool hits different…

    Google released a new CLI tool that integrates Gemini AI for automated coding tasks. Unlike competitors like Claude Code, it's completely open-source and offers 1,000 free model requests daily. While the tool can write code, create files, and execute commands automatically, the user experience is rougher compared to established alternatives. The author tested it by building a Svelte application and found it capable but struggled with build tool configuration issues.

See all Google Gemini archives