{"id":48216449,"url":"https://github.com/vitalcheffe/aegis","last_synced_at":"2026-04-04T19:00:30.435Z","repository":{"id":343371602,"uuid":"967450664","full_name":"Vitalcheffe/Aegis","owner":"Vitalcheffe","description":"Autonomous kinetic interceptor swarm. 50Hz hard-real-time logic, UKF state estimation, and BFT sensor fusion. Inverting the air defense cost-curve.","archived":false,"fork":false,"pushed_at":"2026-03-28T14:53:33.000Z","size":559,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-03-28T17:16:43.086Z","etag":null,"topics":["aerospace","autonomous-drones","defense","embedded-systems","kalman-filter","osint","robotics","swarm-intelligence","systems-engineering"],"latest_commit_sha":null,"homepage":"https://vitalcheffe.github.io/Aegis/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Vitalcheffe.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-04-16T13:25:57.000Z","updated_at":"2026-03-28T14:53:37.000Z","dependencies_parsed_at":null,"dependency_job_id":"80978156-61b2-4d83-bba1-c63a1cf0d6ba","html_url":"https://github.com/Vitalcheffe/Aegis","commit_stats":null,"previous_names":["vitalcheffe/aegis"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Vitalcheffe/Aegis","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vitalcheffe%2FAegis","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vitalcheffe%2FAegis/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vitalcheffe%2FAegis/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vitalcheffe%2FAegis/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Vitalcheffe","download_url":"https://codeload.github.com/Vitalcheffe/Aegis/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vitalcheffe%2FAegis/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31409471,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-04T10:20:44.708Z","status":"ssl_error","status_checked_at":"2026-04-04T10:20:06.846Z","response_time":60,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["aerospace","autonomous-drones","defense","embedded-systems","kalman-filter","osint","robotics","swarm-intelligence","systems-engineering"],"created_at":"2026-04-04T19:00:17.727Z","updated_at":"2026-04-04T19:00:30.411Z","avatar_url":"https://github.com/Vitalcheffe.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n# 🛡️ AEGIS\n\n### _Autonomous Kinetic Interceptor Swarm._\n\n**500 drones. $4,200 each. Against $4M missiles.**\n\n\u003cp\u003e\n  \u003ca href=\"https://github.com/Vitalcheffe/Aegis/stargazers\"\u003e\u003cimg src=\"https://img.shields.io/github/stars/Vitalcheffe/Aegis?style=for-the-badge\u0026logo=github\u0026label=Stars\u0026color=FFD700\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/Vitalcheffe/Aegis/network/members\"\u003e\u003cimg src=\"https://img.shields.io/github/forks/Vitalcheffe/Aegis?style=for-the-badge\u0026logo=github\u0026label=Forks\u0026color=blue\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/Vitalcheffe/Aegis/issues\"\u003e\u003cimg src=\"https://img.shields.io/github/issues/Vitalcheffe/Aegis?style=for-the-badge\u0026logo=github\u0026color=green\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/Vitalcheffe/Aegis/blob/main/LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/License-MIT-blue?style=for-the-badge\u0026logo=opensourceinitiative\" /\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp\u003e\n  \u003cimg src=\"https://img.shields.io/badge/Python-3.11+-blue?style=for-the-badge\u0026logo=python\u0026logoColor=white\" /\u003e\n  \u003cimg src=\"https://img.shields.io/badge/NumPy-1.26+-013243?style=for-the-badge\u0026logo=numpy\u0026logoColor=white\" /\u003e\n  \u003cimg src=\"https://img.shields.io/badge/SciPy-1.12+-0054a6?style=for-the-badge\u0026logo=scipy\u0026logoColor=white\" /\u003e\n  \u003cimg src=\"https://img.shields.io/badge/Real--Time-50Hz-green?style=for-the-badge\" /\u003e\n\u003c/p\u003e\n\n\u003cp\u003e\n  \u003cimg src=\"https://img.shields.io/badge/Swarm-500_Drones-FF6B35?style=for-the-badge\" /\u003e\n  \u003cimg src=\"https://img.shields.io/badge/UKF-9--State-purple?style=for-the-badge\" /\u003e\n  \u003cimg src=\"https://img.shields.io/badge/BFT-Sensor_Fusion-red?style=for-the-badge\" /\u003e\n  \u003cimg src=\"https://img.shields.io/badge/Jetson-Orin_NX-76B900?style=for-the-badge\u0026logo=nvidia\u0026logoColor=white\" /\u003e\n\u003c/p\u003e\n\n\u003cp\u003e\n  \u003ca href=\"https://github.com/Vitalcheffe\"\u003e\u003cimg src=\"https://img.shields.io/badge/GitHub-Vitalcheffe-181717?style=for-the-badge\u0026logo=github\u0026logoColor=white\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://t.me/amnox271\"\u003e\u003cimg src=\"https://img.shields.io/badge/Telegram-Contact-blue?style=for-the-badge\u0026logo=telegram\u0026logoColor=white\" /\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cimg src=\"https://raw.githubusercontent.com/Trilokia/Trilokia/refs/heads/main/bottom_header.svg\" width=\"100%\"/\u003e\n\n\u003c/div\u003e\n\n---\n\n\u003e [!IMPORTANT]\n\u003e **A $4,200 drone vs a $4,000,000 missile. That is the entire point.**\n\u003e\n\u003e Armies spend millions to shoot down things that cost thousands. The math doesn't work.\n\u003e **AEGIS flips it.**\n\n---\n\n## 🚀 The Problem\n\nA Shahed-136 costs **$20,000**. The missile used to intercept it costs **$2,000,000**. That's a 100:1 cost ratio — and the attacker always wins the economics.\n\nCurrent air defense was designed for expensive threats: fighter jets, cruise missiles, ballistic missiles. Against cheap, mass-produced drones and loitering munitions, it collapses. You can't afford to shoot a Patriot at every $20K drone.\n\n**AEGIS inverts the cost curve.** A swarm of autonomous interceptor drones at **$4,200 per unit** — with distributed sensor fusion, autonomous target assignment, and energy-aware routing.\n\n---\n\n## 💰 The Economics\n\n\u003cdiv align=\"center\"\u003e\n\n| Threat | Cost | Current Intercept | Intercept Cost | Ratio | **AEGIS Cost** | **AEGIS Ratio** |\n|:-------|-----:|:------------------|---------------:|------:|---------------:|----------------:|\n| Shahed-136 | $20,000 | Patriot PAC-3 | $2,000,000 | 1:100 | **$4,200** | **1:0.2** |\n| Lancet-3 | $35,000 | IRIS-T SLM | $450,000 | 1:13 | **$4,200** | **1:0.1** |\n| Cruise Missile | $1,500,000 | SM-6 | $4,000,000 | 1:2.7 | **$12,600** (3x) | **1:0.008** |\n| Mixed Wave (10×) | $200,000 | Layered Defense | $8,000,000+ | 1:40 | **$42,000** | **1:0.2** |\n\n\u003c/div\u003e\n\n---\n\n## 🎯 What It Does\n\n500 drones patrol at **300m altitude**. When a threat appears, the system detects it, classifies it, tracks it, and sends the best-positioned drone to intercept.\n\n- ⚡ **50 Hz real-time tick rate** — full 500-drone cycle in ~6ms on a laptop\n- 🧑‍✈️ **Human veto at any point** — weapons locked by default, always\n- 🎯 **3 interception waves tested** — Shahed-136, Lancet-3, mixed with decoys\n- 🔒 **Byzantine fault-tolerant** — bad sensor data gets rejected automatically\n- 🔋 **Energy-aware routing** — drones go home before they fall out of the sky\n\n---\n\n## 🔧 Modules\n\n\u003cdiv align=\"center\"\u003e\n\n```mermaid\nflowchart TB\n    subgraph SENSORS[\"📡 Sensor Layer\"]\n        EO[EO/IR Camera\u003cbr/\u003eSony IMX678 + FLIR Lepton]\n        RADAR[24GHz Radar\u003cbr/\u003eInxpect LBK-24]\n        GPS[RTK GPS\u003cbr/\u003eHere3+]\n        IMU[Redundant IMU\u003cbr/\u003eICM-42688-P ×2]\n    end\n\n    subgraph M1[\"M1 — Sensor Fusion\"]\n        BFT[Byzantine Fault-Tolerant\u003cbr/\u003eMAD Filter]\n    end\n\n    subgraph M2[\"M2 — UKF Tracker\"]\n        UKF[9-State Unscented\u003cbr/\u003eKalman Filter]\n    end\n\n    subgraph M3[\"M3 — Elastic Net\"]\n        FORM[Formation Control\u003cbr/\u003e6 Nearest Neighbors\u003cbr/\u003eO(6N)]\n    end\n\n    subgraph M4[\"M4 — Energy Budget\"]\n        ENERGY[3-Reserve Model\u003cbr/\u003eChute · RTB · Combat]\n    end\n\n    subgraph SAFETY[\"🔒 Safety Layer\"]\n        LOCK[ProximityLock\u003cbr/\u003eWeapon Safe by Default]\n        HUMAN[HumanLoopGate\u003cbr/\u003eFinal Authorization]\n        ADSB[ADS-B Spoof\u003cbr/\u003eDetector]\n    end\n\n    SENSORS --\u003e M1\n    M1 --\u003e M2\n    M2 --\u003e M3\n    M3 --\u003e M4\n    M4 --\u003e SAFETY\n\n    style SENSORS fill:#1a1a2e,stroke:#e94560,color:#fff\n    style M1 fill:#16213e,stroke:#0f3460,color:#fff\n    style M2 fill:#0f3460,stroke:#533483,color:#fff\n    style M3 fill:#1a1a2e,stroke:#e94560,color:#fff\n    style M4 fill:#16213e,stroke:#0f3460,color:#fff\n    style SAFETY fill:#2d0a0a,stroke:#ff4444,color:#fff\n```\n\n\u003c/div\u003e\n\n| Module | What It Does |\n|:-------|:-------------|\n| **M1 — Spectral Fusion** | Byzantine fault-tolerant data fusion (MAD filter). Drones report what they see — bad data gets rejected automatically. No single compromised sensor can corrupt the picture. |\n| **M2 — UKF Tracker** | 9-state Unscented Kalman Filter. Tracks position, velocity, and acceleration of high-speed maneuvering targets. Handles evasive threats. |\n| **M3 — Elastic Net** | Formation control via 6 nearest neighbors. **O(6N)** instead of O(N²) — 83× faster than full mesh at N=500. |\n| **M4 — Energy Budget** | Three inviolable reserves per drone: chute (10Wh), RTB (40Wh), combat (60Wh). If the math doesn't clear, the drone goes home. No exceptions. |\n| **Safety — ProximityLock** | Weapons locked by default. Requires active proof of safety every tick to unlock. Fail-safe: if anything goes wrong, weapons lock. |\n| **Safety — HumanLoopGate** | Final human authorization. No engagement without human approval. Always. |\n| **Safety — ADS-B Spoof Detector** | Detects spoofed ADS-B transponder signals to prevent friendly-fire. |\n\n---\n\n## ✈️ The Airframe — Tessera MK.II\n\nDelta-canard CFRP, built for speed and endurance.\n\n\u003cdiv align=\"center\"\u003e\n\n```\n                        ┌──────────┐\n                        │  EO/IR   │\n                        │  Sensor  │\n                    ┌───┴──────────┴───┐\n                   ╱    CANARD L  CANARD  ╲\n                  ╱  ┌─────┐    ┌─────┐    ╲\n                 │   │     │    │     │     │\n    SPRINT ◄─────│   │  ████████████  │     │─────► PATROL\n   320 km/h      │   │  █ JETSON  █  │     │     180 km/h\n                 │   │  █ ORIN NX █  │     │\n                  ╲  │  ████████████  │    ╱\n                   ╲ │     MAIN WING │   ╱\n                    ╲│  940mm span   │  ╱\n                     └───────┬───────┘\n                             │\n                        ┌────┴────┐\n                        │  MOTOR  │\n                        │ U10+    │\n                        │ 700W    │\n                        └─────────┘\n```\n\n\u003c/div\u003e\n\n| Spec | Value |\n|:-----|:------|\n| **Wingspan** | 940 mm |\n| **MTOW** | 7.2 kg |\n| **Configuration** | Delta-canard |\n| **Material** | T800H/3900-2 CFRP prepreg |\n| **EO Sensor** | Sony IMX678 (4K 60fps, 0.1 lux) |\n| **Thermal** | FLIR Lepton 3.5 (LWIR 8–14 μm) |\n| **Radar** | Inxpect 24 GHz Doppler (±50 m/s) |\n| **Compute** | Jetson Orin NX (70 TOPS) + Hailo H15 (40 TOPS) |\n| **Mesh Network** | 60 GHz phased array (500 Mbps) |\n| **Sprint Speed** | 320 km/h (Cesaroni Pro54 booster) |\n| **Patrol Speed** | 180 km/h |\n| **Endurance** | ~45 min patrol / ~8 min sprint |\n\nFull BOM with part numbers and prices: [`docs/BOM.md`](docs/BOM.md)\n\n---\n\n## 📊 Does It Work?\n\n\u003cdiv align=\"center\"\u003e\n\n| Test | Status | Details |\n|:-----|:------:|:--------|\n| Unit Tests | ✅ | All modules tested individually |\n| Fusion (M1) | ✅ | Byzantine rejection validated |\n| UKF (M2) | ✅ | 9-state tracking converges |\n| Elastic Net (M3) | ✅ | 500-drone formation stable |\n| Energy (M4) | ✅ | Reserve model enforced |\n| Safety | ✅ | ProximityLock + HumanLoopGate |\n| Wave 1 — Shahed-136 | ✅ | Single target intercept |\n| Wave 2 — Lancet-3 | ⚠️ | 3× targets, convergence in progress |\n| Wave 3 — Mixed + Decoys | ✅ | Decoy rejection working |\n| Hardware | ❌ | Simulation only — no physical drone built yet |\n\n\u003c/div\u003e\n\n\u003e [!NOTE]\n\u003e **Honesty corner:** The code runs. Tests pass. The simulation is real (ISA atmosphere, real drag coefficients, real motor specs). But nobody's built the drone yet. Wave 2 isn't fully converged. That's life — this is a research project, not a product.\n\n---\n\n## ⚡ Performance\n\n\u003cdiv align=\"center\"\u003e\n\n```\n┌─────────────────────────────────────────────────┐\n│              50 Hz PIPELINE BENCHMARK            │\n├─────────────────────────────────────────────────┤\n│                                                 │\n│  Sensor Fusion (M1)     ████░░░░░░░░░░  0.8ms  │\n│  UKF Tracking (M2)      █████░░░░░░░░░  1.2ms  │\n│  Elastic Net (M3)       ██████░░░░░░░░  1.5ms  │\n│  Energy Budget (M4)     ██░░░░░░░░░░░░  0.4ms  │\n│  Safety Checks          ██░░░░░░░░░░░░  0.3ms  │\n│  Command Dispatch       █░░░░░░░░░░░░░  0.2ms  │\n│  ──────────────────────────────────────────     │\n│  TOTAL                  ████████████░░  ~4.4ms  │\n│  TICK BUDGET (50Hz)     ████████████████ 20ms   │\n│  HEADROOM               ██████████░░░░  15.6ms  │\n│                                                 │\n│  ✅ 500 drones @ 50Hz on laptop (i7-12700H)     │\n└─────────────────────────────────────────────────┘\n```\n\n\u003c/div\u003e\n\n---\n\n## 🚀 Quick Start\n\n### Install\n\n```bash\ngit clone https://github.com/Vitalcheffe/Aegis.git\ncd Aegis\npip install -r requirements.txt\n```\n\n### Run Tests\n\n```bash\n# All tests\npython tests/test_all.py\n\n# Individual modules\npython tests/test_fusion.py\npython tests/test_ukf.py\npython tests/test_energy.py\npython tests/test_safety.py\n```\n\n### Run Simulation\n\n```bash\n# Nevada scenario — 3 waves\npython simulations/nevada_scenario.py\n\n# Benchmark pipeline\npython scripts/simulate.py\n```\n\n### Prerequisites\n\n| Requirement | Version |\n|:------------|:--------|\n| **Python** | 3.11+ |\n| **NumPy** | 1.26+ |\n| **SciPy** | 1.12+ |\n\nNo exotic dependencies. No GPU required for simulation.\n\n---\n\n## 📁 Project Structure\n\n\u003cdiv align=\"center\"\u003e\n\n```\nAegis/\n├── 📂 src/aegis/\n│   ├── 🐍 origin_core.py         # 50Hz orchestrator — ZERO business logic\n│   ├── 🐍 core.py                # Main entry point\n│   ├── 🐍 oc_types.py            # Shared types + physical constants\n│   │\n│   ├── 📂 fusion/\n│   │   └── 🐍 spectral_fusion.py # M1 — Byzantine fault-tolerant sensor fusion\n│   │\n│   ├── 📂 ukf/\n│   │   └── 🐍 intercept_ukf.py   # M2 — 9-state Unscented Kalman Filter\n│   │\n│   ├── 📂 swarm/\n│   │   └── 🐍 elastic_net.py     # M3 — Formation control, O(6N)\n│   │\n│   ├── 📂 energy/\n│   │   └── 🐍 budget_manager.py  # M4 — 3-reserve energy model\n│   │\n│   └── 📂 safety/\n│       └── 🐍 proximity_lock.py  # ProximityLock + HumanLoopGate + ADS-B\n│\n├── 📂 simulations/\n│   └── 🐍 nevada_scenario.py     # 3-wave intercept simulation\n│\n├── 📂 tests/\n│   ├── 🧪 test_all.py            # Run all tests\n│   ├── 🧪 test_fusion.py\n│   ├── 🧪 test_ukf.py\n│   ├── 🧪 test_energy.py\n│   ├── 🧪 test_safety.py\n│   └── 🧪 test_oc_types.py\n│\n├── 📂 docs/\n│   ├── 📋 BOM.md                 # Full bill of materials ($4,200/unit)\n│   ├── 🏗️ architecture.md        # Design decisions\n│   └── 📂 figures/\n│\n├── 📂 scripts/\n│   └── 🐍 simulate.py            # Pipeline benchmark\n│\n├── ⚙️ pyproject.toml\n├── 📋 requirements.txt\n└── 📄 LICENSE                    # MIT\n```\n\n\u003c/div\u003e\n\n---\n\n## 🔒 Safety Philosophy\n\n\u003e [!CAUTION]\n\u003e **Weapons are locked by default. Always.**\n\nAEGIS implements a **defense-in-depth safety model**:\n\n1. **ProximityLock** — Every drone's weapon system starts LOCKED. To unlock, the drone must provide active proof of safety every single tick (20ms). If anything goes wrong — communication lost, sensor failure, unexpected behavior — weapons lock immediately.\n\n2. **HumanLoopGate** — No engagement without human authorization. Period. The system can track, classify, and recommend — but the final \"go\" requires a human.\n\n3. **ADS-B Spoof Detection** — Detects spoofed transponder signals to prevent friendly-fire against civilian or allied aircraft.\n\n4. **3-Reserve Energy Model** — No drone can spend its RTB or chute reserves. If the math doesn't clear for a safe return, the drone doesn't engage. No exceptions, no overrides.\n\n5. **Byzantine Fusion** — Compromised or malfunctioning sensors are automatically rejected. No single bad sensor can corrupt the tactical picture.\n\n---\n\n## 🌐 System Architecture\n\n\u003cdiv align=\"center\"\u003e\n\n```\n                    ┌─────────────────────┐\n                    │    COMMAND CENTER    │\n                    │  (Human Operator)    │\n                    └──────────┬──────────┘\n                               │ Auth + Veto\n                               ▼\n┌──────────────────────────────────────────────────────┐\n│                   AEGIS CORE (50Hz)                   │\n│  ┌─────────┐  ┌──────┐  ┌──────┐  ┌──────┐  ┌─────┐ │\n│  │ Fusion  │→→│ UKF  │→→│ Net  │→→│Energy│→→│Safe │ │\n│  │  M1     │  │  M2  │  │  M3  │  │  M4  │  │Lock │ │\n│  └─────────┘  └──────┘  └──────┘  └──────┘  └─────┘ │\n└──────────────────────────┬───────────────────────────┘\n                           │ DroneCommands\n              ┌────────────┼────────────┐\n              ▼            ▼            ▼\n         ┌────────┐  ┌────────┐  ┌────────┐\n         │Drone 001│ │Drone 002│ │Drone 500│  × 500\n         │ EO/IR  │  │ EO/IR  │  │ EO/IR  │\n         │ Radar  │  │ Radar  │  │ Radar  │\n         │ Mesh   │  │ Mesh   │  │ Mesh   │\n         └────────┘  └────────┘  └────────┘\n              │            │            │\n              └────────────┼────────────┘\n                           │ 60GHz Mesh\n                      ┌────┴────┐\n                      │ SWARM   │\n                      │ O(6N)   │\n                      └─────────┘\n```\n\n\u003c/div\u003e\n\n---\n\n## 🤝 Contributing\n\n**This is a research project. Contributions are welcome — especially from people who know aerospace, control theory, or embedded systems.**\n\n1. **Fork** the Project\n2. **Create** your Feature Branch\n   ```bash\n   git checkout -b feature/AmazingFeature\n   ```\n3. **Commit** your Changes\n   ```bash\n   git commit -m 'feat: add AmazingFeature'\n   ```\n4. **Push** to the Branch\n   ```bash\n   git push origin feature/AmazingFeature\n   ```\n5. **Open** a Pull Request\n\n**Areas that need help:**\n- 🎯 Wave 2 convergence (3× Lancet-3 intercept)\n- 🔬 Hardware-in-the-loop testing\n- 📡 Real sensor integration\n- 🧪 Monte Carlo validation\n- 📖 Documentation and diagrams\n\n---\n\n## 📚 References \u0026 Inspiration\n\n- **Estimation and Tracking** — Bar-Shalom, Li, Kirubarajan (2001)\n- **Swarm Intelligence** — Bonabeau, Dorigo, Theraulaz (1999)\n- **Byzantine Fault Tolerance** — Lamport, Shostak, Pease (1982)\n- **Unscented Kalman Filter** — Julier, Uhlmann (1997)\n- **Elastic Net Formation** — Kaiser, Görner, Schmickl, Crailsheim (2012)\n\n---\n\n## 📊 Stats\n\n\u003cdiv align=\"center\"\u003e\n\n![GitHub Stars](https://img.shields.io/github/stars/Vitalcheffe/Aegis?style=social)\n![GitHub Forks](https://img.shields.io/github/forks/Vitalcheffe/Aegis?style=social)\n![GitHub Watchers](https://img.shields.io/github/watchers/Vitalcheffe/Aegis?style=social)\n\n[![Star History Chart](https://api.star-history.com/svg?repos=Vitalcheffe/Aegis\u0026type=date)](https://www.star-history.com/#Vitalcheffe/Aegis\u0026type=date)\n\n\u003c/div\u003e\n\n---\n\n## 📄 License\n\nDistributed under the **MIT License**. See [`LICENSE`](LICENSE) for more information.\n\nBuild on it. Improve it. Make the math work.\n\n---\n\n\u003cdiv align=\"center\"\u003e\n\n### Made with ❤️, 🎯, and 🔬 by [Amine Harch el Korane](https://github.com/Vitalcheffe)\n\n_Inverting the air defense cost curve._\n\n\u003cimg src=\"https://raw.githubusercontent.com/Trilokia/Trilokia/refs/heads/main/bottom_header.svg\" width=\"100%\"/\u003e\n\n![AEGIS](https://socialify.git.ci/Vitalcheffe/Aegis/image?description=1\u0026font=Raleway\u0026forks=1\u0026issues=1\u0026language=1\u0026name=1\u0026owner=1\u0026pattern=Circuit+Board\u0026pulls=1\u0026stargazers=1\u0026theme=Dark)\n\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvitalcheffe%2Faegis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvitalcheffe%2Faegis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvitalcheffe%2Faegis/lists"}