[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-81134":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":17,"stars30d":17,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":18,"rankGlobal":10,"rankLanguage":10,"license":19,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":22,"hasPages":20,"topics":23,"createdAt":10,"pushedAt":10,"updatedAt":28,"readmeContent":29,"aiSummary":30,"trendingCount":16,"starSnapshotCount":16,"syncStatus":13,"lastSyncTime":31,"discoverSource":32},81134,"GeoCode-Release","zzhonglei\u002FGeoCode-Release","zzhonglei","A desktop AI assistant for geoscience data processing","",null,"JavaScript",33,2,32,4,0,1,42.03,"MIT License",false,"main",true,[24,25,26,27],"agent","googleearthengine","qgis","qgis-processing","2026-06-12 04:01:32","\u003Cp align=\"center\">\n  \u003Cimg src=\"assets\u002Flogo.svg\" width=\"500\" alt=\"GeoCode\">\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\u003Cstrong>A desktop AI assistant for geoscience data processing\u003C\u002Fstrong>\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  English  ·  \u003Ca href=\"README.zh-CN.md\">简体中文\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FQGIS-589632?style=flat-square&logo=qgis&logoColor=white\" alt=\"QGIS\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FGDAL-5CAE58?style=flat-square&logo=osgeo&logoColor=white\" alt=\"GDAL\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FGEE-4285F4?style=flat-square&logo=googleearth&logoColor=white\" alt=\"Google Earth Engine\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FmacOS-arm64-blue?style=flat-square&logo=apple&logoColor=white\" alt=\"macOS arm64\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FWindows-x64-blue?style=flat-square&logo=windows&logoColor=white\" alt=\"Windows x64\">\n  \u003Ca href=\"LICENSE\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-yellow?style=flat-square\" alt=\"MIT License\">\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fzzhonglei\u002FGeoCode-Release\u002Freleases\">🚀 Download\u003C\u002Fa>\n  ·\n  \u003Ca href=\"contributions\u002F\">✨ Skill Bazaar\u003C\u002Fa>\n  ·\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fsst\u002Fopencode\">🌳 Upstream OpenCode\u003C\u002Fa>\n\u003C\u002Fp>\n\n---\n\n## What GeoCode Can Do\n\nTackle complex geoscience data processing through conversation — empowering anyone to analyze the planet 🌏...\n\n| Capability                  | Scope                                                          | Examples                                                          |\n| --------------------------- | -------------------------------------------------------------- | ----------------------------------------------------------------- |\n| 🗺️ **QGIS**                 | **All hundreds of algorithms** in QGIS Processing              | Spatial analysis, vector\u002Fraster batch processing, format conversion, accessibility analysis... |\n| 🛰️ **Google Earth Engine** | **Full GEE Python API** — any remote sensing task you can express | Temporal compositing, classification, change detection, land surface temperature, image download... |\n| 🐍 **Python**              | Run **arbitrary Python scripts** in an isolated env, full scientific computing stack | Geospatial processing, thematic mapping, deep learning... |\n| ✨ **Skill**                | On-demand capability packs that **let GeoCode grow as you need** | Pull community-built packs anytime, build the geoscience ecosystem together... |\n\n## How to Use\n\n### 1. What environment do you need?\n\nNo complex setup required. Before installing GeoCode, only two things need to be on your machine:\n\n- **[QGIS](https:\u002F\u002Fqgis.org\u002Fdownload\u002F)** — desktop GIS app, GeoCode calls its algorithms\n- **A Python environment manager** (recommend [Miniconda](https:\u002F\u002Fdocs.anaconda.com\u002Fminiconda\u002F)) — isolates Python dependencies so GeoCode's scripts don't interfere with each other\n\n> [!TIP]\n> Give GeoCode's agent a **dedicated Python environment** (create a fresh one with Conda \u002F Mamba). The agent will install, uninstall, and upgrade Python packages on its own as it works — a dedicated env keeps your other projects clean and helps the agent run more reliably.\n\n### 2. GeoCode Versions\n\nGeoCode is currently in public preview as the 0.9.x series. Grab the latest build from [Releases](https:\u002F\u002Fgithub.com\u002Fzzhonglei\u002FGeoCode-Release\u002Freleases). Early adopters and feedback are welcome.\n\n| Version | Released | Changes |\n| :--- | :--- | :--- |\n| [**v0.9.2**](https:\u002F\u002Fgithub.com\u002Fzzhonglei\u002FGeoCode-Release\u002Freleases\u002Ftag\u002Fv0.9.2) `Latest` | 2026-05-07 | `Fixed` Compatibility issues with certain QGIS versions\u003Cbr>`Fixed` Settings window stutter on certain Windows machines |\n| [**v0.9.1**](https:\u002F\u002Fgithub.com\u002Fzzhonglei\u002FGeoCode-Release\u002Freleases\u002Ftag\u002Fv0.9.1) | 2026-05-05 | `Fixed` Google Earth Engine display issue on Windows |\n| [**v0.9.0**](https:\u002F\u002Fgithub.com\u002Fzzhonglei\u002FGeoCode-Release\u002Freleases\u002Ftag\u002Fv0.9.0) | 2026-05-04 | `Initial` First public preview |\n\n> [!TIP]\n> This repo primarily hosts GeoCode's **Skill** store; each version's source code is published alongside its release packages.\n\n### 3. How to configure\n\nAfter installing QGIS and your environment manager, launch GeoCode and type `\u002Fset` in the input box to enter the setup wizard. Just follow the prompts to the end.\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"assets\u002Fsetup-wizard.png\" width=\"700\" alt=\"Type \u002Fset in GeoCode to launch the setup wizard\">\n\u003C\u002Fp>\n\n> [!TIP]\n> The free models bundled with OpenCode are limited in capability and not recommended for real work. For a noticeably better experience, plug in your own [**DeepSeek v4**](https:\u002F\u002Fplatform.deepseek.com\u002Fsign_in) API key, or sign in with a **ChatGPT Plus** subscription.\n\n## Skill Bazaar\n\nSkills are a key piece of how smoothly the agent works. GeoCode ships a built-in management UI for them — browse, install, enable, disable, all click-driven, no manual file shuffling.\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"assets\u002Fskill-bazaar.png\" width=\"700\" alt=\"GeoCode Settings → Skill Bazaar\">\n\u003C\u002Fp>\n\n> [!TIP]\n> The Skill catalog is small in both quantity and polish in these early days. As more users and contributors join, the bazaar will fill up with higher-quality skills.\n\n### How to contribute your own Skill\n\nAll GeoCode Skills live under [`contributions\u002F`](contributions\u002F) — anyone can open a Pull Request to add a new one. The standard layout of a Skill package:\n\n```\ncontributions\u002F\u003Cyour-skill-id>\u002F\n├── manifest\u002F\n│   ├── README.md       # Human-facing description of the Skill\n│   └── meta.json       # Metadata: version \u002F description \u002F author \u002F tags ...\n└── skill\u002F\n    ├── SKILL.md        # Required, the core prompt (LLM-facing, with frontmatter)\n    └── \u003Cdir>\u002F          # Optional, any name and any nesting — references, templates, scripts, etc.\n```\n\nSubmission flow:\n\n1. Fork this repo and create your Skill directory under `contributions\u002F`\n2. Fill in `manifest\u002F` and `skill\u002F` following the layout above\n3. Open a Pull Request — CI auto-validates schema, version, and structure\n4. Once reviewed, the maintainer merges and publishes\n\n> [!TIP]\n> Skills are loaded into the agent's prompt and directly affect its behavior. Every PR is reviewed manually before merging to screen for malicious instructions or unsafe operations.\n\n## Acknowledgements\n\nGeoCode benefited from guidance on design and technical decisions from the following research groups:\n\n- China University of Geosciences (Wuhan) · [**UrbanComp Lab**](https:\u002F\u002Furbancomp.net\u002F)\n- LIESMARS, Wuhan University · [**Urban Spatial Intelligence Research Group**](https:\u002F\u002Fgithub.com\u002FWHU-USI3DV)\n\n## License\n\nMIT — see [LICENSE](LICENSE) and [NOTICE](NOTICE).\n","GeoCode-Release 是一个用于地球科学数据处理的桌面AI助手。它集成了QGIS的所有数百种算法、完整的Google Earth Engine Python API以及任意Python脚本的执行能力，支持空间分析、遥感任务、地理空间处理等多种功能。此外，用户还可以根据需求下载社区构建的能力包来扩展GeoCode的功能。该项目适用于需要进行复杂地理数据分析和处理的研究人员及专业人士，无需复杂的环境配置即可上手使用。","2026-06-11 04:03:38","CREATED_QUERY"]