GitHub 火線榜

GitHub 火線榜 · 倉庫檔案

google-gemini/gemini-managed-agents-templates

This repository contains a collection of templates for building and deploying Gemini Managed Agents using the Gemini API. (簡介來自倉庫自身文件。)

資料截至 October 23google-gemini

最好成績

#175

被忽視榜 · 活躍卻無人問津

100

累計 Star

38

Fork 總數

2

近 30 天在榜天數

專案文件

Gemini Managed Agents Templates

This repository contains a collection of templates for building and deploying Gemini Managed Agents using the Gemini API. These templates demonstrate the power of the Gemini API sandbox, including code execution, filesystem operations, and web search.

Available Templates

  • Data Analyst: Upload a CSV and get full data analysis with charts and insights.
  • AI Radio: Turn today's top Hacker News stories into a radio program (podcast briefing).
  • Repo Maintainer: Provide a GitHub repo URL, find top issues, fix them, and send Pull Requests.
  • Document Processor: A template for processing and analyzing documents.
  • News Curator: Personalized daily briefings on a Trigger schedule — sweeps Google News, Hacker News, and Medium for your topics, learns your taste across runs via the persistent environment.
  • SEO Auditor: Audit published web apps for loading speed, Core Web Vitals, mobile usability, and search readiness using Lighthouse and Google Search.

Getting Started

To use these templates, you can reference them in your Gemini API calls or use the Gemini API CLI to scaffold new agents based on these templates.

Running Probers

Each template directory contains a probers.sh script that can be used to test the agent template by sending a "Hello" prompt to the Gemini API. These probers read the template information (like AGENTS.md and skills) dynamically from disk.

To run a prober:

  1. Set your GEMINI_API_KEY environment variable:

    export GEMINI_API_KEY="your_api_key_here"
  2. Navigate to the template directory you want to test (e.g., data-analyst):

    cd data-analyst
  3. Run the prober script:

    ./probers.sh

The script will call ../generate_payload.py to construct the payload dynamically and then use curl to make the API request.

Licensing & Disclaimer

Copyright 2026 Google LLC

All software is licensed under the Apache License, Version 2.0 (Apache 2.0); you may not use this file except in compliance with the Apache 2.0 license. You may obtain a copy of the Apache 2.0 license at: https://www.apache.org/licenses/LICENSE-2.0

All other materials are licensed under the Creative Commons Attribution 4.0 International License (CC-BY). You may obtain a copy of the CC-BY license at: https://creativecommons.org/licenses/by/4.0/legalcode

Unless required by applicable law or agreed to in writing, all software and materials distributed here under the Apache 2.0 or CC-BY licenses are distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the licenses for the specific language governing permissions and limitations under those licenses.

This is not an official Google product.

當前上榜

  • 175

    被忽視榜 · 活躍卻無人問津

    100 星 · 38 fork · 累計星星(升冪)

    被忽視 →

近 30 天勢頭

累計 Star 走勢

名次走勢

同榜競速 · 名次近鄰

← 回到榜單