31 agents available in the Gemini directory
A self-extending AI agent built with Google ADK & Gemini 2.0 Flash that dynamically creates, stores, and reuses its own skills at runtime — growing smarter with every task.
AI storyteller that turns screen time into active adventure. Puck — a live Gemini agent — narrates interactive fairytales, generates watercolor scenes, and only continues the story when the child completes a real physical challenge. Built with Gemini Live 2.5, Google ADK, Veo 3.1, React 19.
This MCP server that brings Gemini's Deep Research Agent to the AI coding assistants. This provides ai assistant with very high quality deep web research. Ai coding assisstant when doing deep research on their own easily fill up their context size, but gemini makes it very very efficient. the only negative is time and pricing here.
Autonomous multi-agent framework for self-correcting image synthesis using 'Think → Generate → Critique → Refine' cycles with Gemini 3.1 and SDXL.
基于 Gemini 的可视化多智能体深度推理引擎 | A visual multi-agent deep reasoning engine powered by Gemini, featuring dynamic planning, chain-of-thought visualization, and multi-session management. Built with React 19 + TypeScript + Vite 6.
🤖 The Ultimate AI Form Filler. Automate complex web forms & PDFs with Voice, generic LLMs (Gemini/Phi-2), and Playwright. The best open-source autonomous form filling agent.
EVO OS: The next-gen autonomous agent IDE. It executes the full development cycle: Plan, Code, Verify (AST/QA), Test (Docker Sandbox), and Self-Heal. Features BudgetGuard™ for real-time cost control and loop-preventing Healer logic for unmatched robustness. A safe, economical, and self-expanding platform, ready for production use.
AgentStack is a production-grade multi-agent framework built on Mastra, delivering 50+ enterprise tools, 25+ specialized agents, and A2A/MCP orchestration for scalable AI systems. Focuses on financial intelligence, RAG pipelines, observability, and secure governance. ACP Openclaw, Gemini CLI, Opencode
A minimal browser automation agent using Google's Gemini 2.5 Computer Use Preview model and Playwright for web browser control.
Autonomous AI Agent for the JVM: shell, files, google search, runs any LLM generated java code on the jvm itself. JIT compilation and a child-first classloader with ANY classpath. Comes wit a swing GUI , can be "dropped in" into any existing java application. Easy tools easy pojos. IoT devices. Run it standalone for a pure-java AI assistant.
A real-time voice AI agent powered by LiveKit and Google's Gemini Realtime API, enabling natural conversational interactions through browser-based voice interface.
A NetBeans plugin that allows Google Gemini to do all your work on the worlds best Java IDE. Get a wireless headset, lay on your bed and tell the model to turn on your tv and stream NetBeans onto it while you approve and deny diffs on the diff viewer. Try not to drink too much alcohol if the model goes way faster than your thoughts.
Minovative Mind is an AI-Agent, VS Code extension using Google Gemini 2.5 models to boost developer productivity with intelligent code assistance, automated code planning/execution, context-aware chat, and secure, efficient workflows for all developers
AI Technical Interviewer with Google ADK, Gemini and A2UI. Multi-agent system for adaptive interviews, guided learning, and code analysis with beautiful web UI.
Agent is built with the help of Firecrawl for MCP tools, Gemini for LLM's.
A state-of-the-art multi-agent travel planning system built with LangGraph, Google Gemini Flash-2.0, and DuckDuckGo Search. The system offers three different planning approaches, from traditional single-agent to cutting-edge multi-agent collaboration using modern industry frameworks.
A web search agent that enables you to search, visualize, and listen to information.
This is a library for implementing an Agent2Agent (A2A) server using Google Apps Script. This enables AI agent communication and secure service access for AI-powered workflows.
An open-source AI agent that brings the power of Gemini directly into your terminal.
Multi-Agent SEO Blog Generator automates SEO-friendly blog creation by researching trending topics, generating structured content using AI, and optimizing it for search engines. It integrates Google News, Bing News (SerpAPI), and Gemini AI to produce high-quality blogs in multiple formats, including Markdown, TXT, HTML, and PDF.
Professional Gemini API integration for Claude and all MCP-compatible hosts with intelligent model selection and advanced file handling | Smithery.ai verified
MCP Deep Research Server using Gemini creating a Research AI Agent
This is an AI-powered email agent built using Node.js and Google Gemini (or Gmail API). It allows you to send emails automatically by providing a prompt. You can use this agent to send emails based on the instructions provided.
HighlighAI - An AI Agentic System for Video Summarizing🎥🚀 Powered by Gemini 2.0 Flash Exp, this tool enables users to upload video files and receive detailed, user-friendly analysis.