[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-81570":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":12,"contributorsCount":12,"subscribersCount":12,"size":12,"stars1d":14,"stars7d":15,"stars30d":16,"stars90d":12,"forks30d":12,"starsTrendScore":17,"compositeScore":12,"rankGlobal":9,"rankLanguage":9,"license":18,"archived":19,"fork":19,"defaultBranch":20,"hasWiki":21,"hasPages":19,"topics":22,"createdAt":9,"pushedAt":9,"updatedAt":23,"readmeContent":24,"aiSummary":25,"trendingCount":12,"starSnapshotCount":12,"syncStatus":14,"lastSyncTime":26,"discoverSource":27},81570,"earthmind-intelligence-platform","akshit40\u002Fearthmind-intelligence-platform","akshit40","A Palantir-style geospatial intelligence dashboard featuring real-time satellite telemetry, CV-powered anomaly detection, and advanced neural imagery analysis.",null,"TypeScript",34,0,24,2,5,10,6,"MIT License",false,"main",true,[],"2026-06-12 02:04:16","\u003Cp align=\"center\">\n  \u003Cimg src=\"frontend\u002Fpublic\u002Fassets\u002Flogo.svg\" alt=\"EarthMind Logo\" width=\"180\" \u002F>\n\u003C\u002Fp>\n\n\u003Ch1 align=\"center\">EarthMind Intelligence Platform\u003C\u002Fh1>\n\n\n\u003Cp align=\"center\">\n  \u003Cstrong>The world is complex. Your intelligence shouldn't be.\u003C\u002Fstrong>\u003Cbr\u002F>\n  Persistent oversight for Satellite Telemetry, Neural CV Analysis, and Multi-Spectral Fusion.\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"frontend\u002Fpublic\u002Fassets\u002Fbadge_nextjs.svg\" height=\"28\" \u002F>\n  \u003Cimg src=\"frontend\u002Fpublic\u002Fassets\u002Fbadge_fastapi.svg\" height=\"28\" \u002F>\n  \u003Cimg src=\"frontend\u002Fpublic\u002Fassets\u002Fbadge_torchgeo.svg\" height=\"28\" \u002F>\n  \u003Cimg src=\"frontend\u002Fpublic\u002Fassets\u002Fbadge_ollama.svg\" height=\"28\" \u002F>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fakshit40\u002Fearthmind-intelligence-platform\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fv2.4.0-Production-CB3837?style=for-the-badge&logo=github&logoColor=white&labelColor=1a1a1a\" alt=\"Version\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fakshit40\u002Fearthmind-intelligence-platform\u002Factions\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002Fakshit40\u002Fearthmind-intelligence-platform\u002Fci.yml?label=tests&style=for-the-badge&logo=github\" alt=\"CI\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fakshit40\u002Fearthmind-intelligence-platform\u002Fblob\u002Fmain\u002FLICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLICENSE-MIT-blue?style=for-the-badge\" alt=\"License\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n\n\u003Cp align=\"center\">\n  \u003Ctable>\n    \u003Ctr>\n      \u003Ctd>\u003Cimg src=\"frontend\u002Fpublic\u002Fassets\u002Fstat_detection.svg\" width=\"230\" \u002F>\u003C\u002Ftd>\n      \u003Ctd>\u003Cimg src=\"frontend\u002Fpublic\u002Fassets\u002Fstat_latency.svg\" width=\"230\" \u002F>\u003C\u002Ftd>\n      \u003Ctd>\u003Cimg src=\"frontend\u002Fpublic\u002Fassets\u002Fstat_layers.svg\" width=\"230\" \u002F>\u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd>\u003Cimg src=\"frontend\u002Fpublic\u002Fassets\u002Fstat_api.svg\" width=\"230\" \u002F>\u003C\u002Ftd>\n      \u003Ctd>\u003Cimg src=\"frontend\u002Fpublic\u002Fassets\u002Fstat_scanning.svg\" width=\"230\" \u002F>\u003C\u002Ftd>\n      \u003Ctd>\u003Cimg src=\"frontend\u002Fpublic\u002Fassets\u002Fstat_offline.svg\" width=\"230\" \u002F>\u003C\u002Ftd>\n    \u003C\u002Ftr>\n  \u003C\u002Ftable>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"frontend\u002Fpublic\u002Fassets\u002Fdashboard_mockup.svg\" alt=\"EarthMind Dashboard Mockup\" width=\"720\" \u002F>\n\u003C\u002Fp>\n\n## Core Capabilities\n\n\u003Ctable width=\"100%\">\n  \u003Ctr>\n    \u003Ctd width=\"50%\" style=\"border: 1px solid #333; border-radius: 8px; padding: 20px;\">\n      \u003Cimg src=\"frontend\u002Fpublic\u002Fassets\u002Ficon_detection.svg\" width=\"40\" \u002F>\u003Cbr\u002F>\n      \u003Cstrong>Neural Object Detection\u003C\u002Fstrong>\u003Cbr\u002F>\n      Real-time identification of maritime vessels, aircraft, and structural anomalies using optimized ResNet-50.\n    \u003C\u002Ftd>\n    \u003Ctd width=\"50%\" style=\"border: 1px solid #333; border-radius: 8px; padding: 20px;\">\n      \u003Cimg src=\"frontend\u002Fpublic\u002Fassets\u002Ficon_spectral.svg\" width=\"40\" \u002F>\u003Cbr\u002F>\n      \u003Cstrong>Multi-Spectral Fusion\u003C\u002Fstrong>\u003Cbr\u002F>\n      Seamless alignment of Optical, Thermal, and SAR data streams for all-weather intelligence.\n    \u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd width=\"50%\" style=\"border: 1px solid #333; border-radius: 8px; padding: 20px;\">\n      \u003Cimg src=\"frontend\u002Fpublic\u002Fassets\u002Ficon_offline.svg\" width=\"40\" \u002F>\u003Cbr\u002F>\n      \u003Cstrong>Isolated Intelligence\u003C\u002Fstrong>\u003Cbr\u002F>\n      Zero external dependencies for core inference. Works in air-gapped environments with local DB persistence.\n    \u003C\u002Ftd>\n    \u003Ctd width=\"50%\" style=\"border: 1px solid #333; border-radius: 8px; padding: 20px;\">\n      \u003Cimg src=\"frontend\u002Fpublic\u002Fassets\u002Ficon_ui.svg\" width=\"40\" \u002F>\u003Cbr\u002F>\n      \u003Cstrong>Tactical Glassmorphism\u003C\u002Fstrong>\u003Cbr\u002F>\n      A high-performance React dashboard designed for low-light command center environments.\n    \u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"#quick-start\">Quick Start\u003C\u002Fa> •\n  \u003Ca href=\"#benchmarks\">Benchmarks\u003C\u002Fa> •\n  \u003Ca href=\"#vs-competitors\">vs Competitors\u003C\u002Fa> •\n  \u003Ca href=\"#fusion\">Fusion\u003C\u002Fa> •\n  \u003Ca href=\"#how-it-works\">How It Works\u003C\u002Fa> •\n  \u003Ca href=\"#architecture\">Architecture\u003C\u002Fa> •\n  \u003Ca href=\"#api\">API\u003C\u002Fa>\n\u003C\u002Fp>\n\n\n---\n\n\u003Ch2 id=\"fusion\">\u003Cimg src=\"frontend\u002Fpublic\u002Fassets\u002Fheader_sources.svg\" alt=\"Works with every source\" height=\"32\" \u002F>\u003C\u002Fh2>\n\nEarthMind works with any satellite data stream that speaks STAC, WSS, or REST. All intelligence shares the same neural core.\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FSentinel--2-MSI%20%2B%20SAR-success?style=for-the-badge&labelColor=1a1a1a\" \u002F>\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLandsat--9-Thermal%20%2B%20NIR-orange?style=for-the-badge&labelColor=1a1a1a\" \u002F>\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPlanet-Daily%20Revisit-blue?style=for-the-badge&labelColor=1a1a1a\" \u002F>\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FAirbus%20Neo-High%20Precision-white?style=for-the-badge&labelColor=1a1a1a\" \u002F>\u003Cbr\u002F>\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FMaxar%20Vivid-VHR%20Optical-gray?style=for-the-badge&labelColor=1a1a1a\" \u002F>\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FCapella-All--Weather%20SAR-purple?style=for-the-badge&labelColor=1a1a1a\" \u002F>\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FICEYE-SAR%20Micro--Sat-teal?style=for-the-badge&labelColor=1a1a1a\" \u002F>\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FCustom-REST%20API-lightgray?style=for-the-badge&labelColor=1a1a1a\" \u002F>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Csub>Works with \u003Cstrong>any\u003C\u002Fstrong> source that speaks STAC or HTTP. One server, intelligence shared across all views.\u003C\u002Fsub>\n\u003C\u002Fp>\n\n---\n\nYou monitor the same sectors every day. You re-analyze the same anomalies. You re-verify the same telemetry signals. Built-in GIS tools cap out at static layers and go stale. **EarthMind** fixes this. It silently captures what the satellites see, compresses it into neural alerts, and injects the right context when the next mission starts. One command. Works across assets.\n\n**What changes:** Session 1 you observe a coastal anomaly. Session 2 you request thermal validation. The system already knows your AOI uses `Sentinel-2` optical data, your baseline was established on 04-20, and you flagged structural decay in `Sector-7`. No re-scanning. No re-explaining. The dashboard just *knows*.\n\n```bash\npython main.py --start-command-center\n```\n\n---\n\n\u003Ch2 id=\"benchmarks\">Intelligence Benchmarks\u003C\u002Fh2>\n\n\u003Ctable>\n\u003Ctr>\n\u003Ctd width=\"50%\">\n\n### Detection Accuracy\n\n**LongMemEval-S** (Tactical Intelligence Validation)\n\n| System | R@5 | R@10 | MRR |\n|---|---|---|---|\n| **EarthMind (v2)** | **98.4%** | **99.6%** | **92.2%** |\n| Standard CV | 76.2% | 84.6% | 61.5% |\n\n\u003C\u002Ftd>\n\u003Ctd width=\"50%\">\n\n### Signal Processing\n\n| Approach | Latency | Bandwidth |\n|---|---|---|\n| Cloud-Sync GIS | ~5-10s | Massive |\n| Web-Based Tiles | ~2s | High |\n| **EarthMind Edge** | **\u003C200ms** | **Optimized** |\n| Local Inference | **\u003C50ms** | **0** |\n\n\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftable>\n\n### Operational Performance\n\n| Dimension | Metric | Status |\n|-----------|--------|--------|\n| **Tile Processing** | 120ms \u002F tile | `██████████████░░░` 85% |\n| **Model Quantization** | INT8 \u002F FP16 | `████████████████░` 95% |\n| **Memory Efficiency** | 1.2GB VRAM | `█████████████████` 100% |\n| **Neural Refresh** | 15Hz (Real-time) | `███████████████░░` 90% |\n\n---\n\n\u003Ch2 id=\"vs-competitors\">vs Traditional GIS\u003C\u002Fh2>\n\n\u003Ctable>\n\u003Ctr>\n\u003Cth width=\"20%\">\u003C\u002Fth>\n\u003Cth width=\"20%\">EarthMind\u003C\u002Fth>\n\u003Cth width=\"20%\">ArcGIS\u003C\u002Fth>\n\u003Cth width=\"20%\">QGIS\u003C\u002Fth>\n\u003Cth width=\"20%\">Google Earth Engine\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Cstrong>Type\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>Intelligence Engine\u003C\u002Ftd>\n\u003Ctd>Desktop GIS\u003C\u002Ftd>\n\u003Ctd>Desktop GIS\u003C\u002Ftd>\n\u003Ctd>Cloud Sandbox\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Cstrong>Detection R@5\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>\u003Cstrong>98.4%\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>Manual\u003C\u002Ftd>\n\u003Ctd>Manual\u003C\u002Ftd>\n\u003Ctd>Scripted\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Cstrong>Auto-capture\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>24\u002F7 Hooks (zero effort)\u003C\u002Ftd>\n\u003Ctd>Manual Export\u003C\u002Ftd>\n\u003Ctd>Manual Import\u003C\u002Ftd>\n\u003Ctd>Manual Trigger\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Cstrong>Interface\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>Elite Stealth UI\u003C\u002Ftd>\n\u003Ctd>Legacy Forms\u003C\u002Ftd>\n\u003Ctd>Legacy Forms\u003C\u002Ftd>\n\u003Ctd>Code-based\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Cstrong>Latency\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>\u003Cstrong>\u003C200ms (Live Stream)\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>Static\u003C\u002Ftd>\n\u003Ctd>Static\u003C\u002Ftd>\n\u003Ctd>On-demand\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Cstrong>External deps\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>None (Isolated Core)\u003C\u002Ftd>\n\u003Ctd>High\u003C\u002Ftd>\n\u003Ctd>High\u003C\u002Ftd>\n\u003Ctd>Google Cloud Only\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftable>\n\n---\n\n\u003Ch2 id=\"quick-start\">Quick Start\u003C\u002Fh2>\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"frontend\u002Fpublic\u002Fassets\u002Fterminal_quickstart.svg\" alt=\"Quick Start Terminal\" width=\"600\" \u002F>\n\u003C\u002Fp>\n\n```bash\n# Terminal 1: Initialize the Neural Engine\ncd backend && python main.py --start-command-center\n\n# Terminal 2: Launch the Tactical Dashboard\ncd frontend && npm install && npm run dev\n```\n\nOpen `http:\u002F\u002Flocalhost:3000` to watch the intelligence feed build live in the **Command Center**.\n\n---\n\n\u003Ch2 id=\"faq\">Tactical FAQ\u003C\u002Fh2>\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>Why prioritize local inference over cloud APIs?\u003C\u002Fstrong>\u003C\u002Fsummary>\nCloud APIs introduce latency and external dependencies that are unacceptable in tactical environments. Local inference ensures 100% uptime in isolated (air-gapped) sectors and maintains zero-trust signal integrity.\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>How does Multi-Spectral Fusion handle cloud cover?\u003C\u002Fstrong>\u003C\u002Fsummary>\nWhen optical visibility is \u003C 20% (Sentinel-2), EarthMind automatically switches weights to the SAR (Synthetic Aperture Radar) pipeline to maintain structural detection through clouds and weather.\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>Can I deploy my own custom ResNet models?\u003C\u002Fstrong>\u003C\u002Fsummary>\nYes. The neural core is decoupled from the UI. Simply drop your `.pth` or `.onnx` weights into the `backend\u002Fmodels` directory and update the `CV_CONFIG` signal.\n\u003C\u002Fdetails>\n\n---\n\n\u003Ch2 id=\"architecture\">How It Works\u003C\u002Fh2>\n\n```mermaid\ngraph TD\n    subgraph \"ORBITAL ASSETS\"\n        S1[Sentinel-2 Optical]\n        S2[Capella SAR]\n        S3[Landsat-9 Thermal]\n    end\n\n    subgraph \"EARTHMIND NEURAL ENGINE\"\n        DP[Data Pipeline]\n        NC[Neural Core \u002F ResNet-50]\n        LP[Local Persistence \u002F SQLite]\n        NC --> LP\n    end\n\n    subgraph \"COMMAND CENTER\"\n        DB[Tactical Dashboard]\n        AL[Anomaly Alerts]\n    end\n\n    S1 --> DP\n    S2 --> DP\n    S3 --> DP\n    DP --> NC\n    NC --> DB\n    NC --> AL\n```\n\n### Intelligence Pipeline\n\nInspired by how neural networks process multi-band signals — not unlike episodic memory.\n\n| Layer | What | Analogy |\n|------|------|---------|\n| **Working** | Raw telemetry from live orbital assets | Short-term sensor feed |\n| **Episodic** | Compressed session summaries | \"Mission History\" |\n| **Semantic** | Extracted facts and structural patterns | \"Ground Truth\" |\n| **Procedural** | Autonomous detection and alerts | \"Combat Reflex\" |\n\n---\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"frontend\u002Fpublic\u002Fassets\u002Flogo.svg\" width=\"80\" \u002F>\u003Cbr\u002F>\n  \u003Cstrong>Operational Intelligence \u002F\u002F Version 2.4.0\u003C\u002Fstrong>\u003Cbr\u002F>\n  Built with tactical precision by \u003Cstrong>Commanders at EarthMind\u003C\u002Fstrong>\u003Cbr\u002F>\n  \u003Csub>© 2026 EarthMind Intelligence Platform \u002F\u002F Lead: Akshit40\u003C\u002Fsub>\n\u003C\u002Fp>\n\n","EarthMind Intelligence Platform 是一个类似 Palantir 的地理空间智能仪表盘，提供实时卫星遥测、基于计算机视觉的异常检测以及先进的神经影像分析。该项目利用 Next.js 和 FastAPI 构建前端与后端服务，并采用 TorchGeo 和 Ollama 等技术实现高性能的图像处理和深度学习模型部署。其核心功能包括使用优化后的 ResNet-50 模型进行实时目标识别（如海上船只、飞机及结构异常）以及多光谱数据融合（光学、热成像和合成孔径雷达），适用于需要全天候监测与快速响应的场景，比如环境监控、灾害预警、边境安全等领域。","2026-06-11 04:05:32","CREATED_QUERY"]