Crucix

Normal

GitHub JavaScript AGPL-3.0

Description

Crucix is a personal intelligence agent that watches the world from multiple data sources and pings you when something changes, helping you stay on top of information in real time.

Key Features

Aggregates 27 OSINT sources: satellite fire data, flight tracking, radiation monitoring, and more
Jarvis-style 3D WebGL dashboard with globe, flat map, and animated flight corridors
LLM integration for two-way intelligence assistant with Telegram and Discord alerts
Auto-refreshes every 15 minutes with sweep delta showing new signals and escalations
Cross-source correlation across satellite, economic, conflict, and social domains
Zero cloud, zero telemetry — fully self-hosted with just Express as dependency

Use Cases

💡 Monitor global geopolitical events and conflict zones in real-time

💡 Track satellite fire detections and natural disaster activity

💡 Analyze economic indicators, market data, and supply chain risks

💡 Receive automated intelligence briefings via Telegram or Discord

💡 Conduct OSINT research with correlated cross-domain data feeds

Strengths & Limitations

✅ Strengths

• High community interest (11.4k stars)
• Responsive to issues, low backlog

⚠️ Limitations

• Restrictive license (AGPL-3.0)

Quick Start

git clone https://github.com/calesthio/Crucix.git → cd Crucix → npm install → cp .env.example .env (add API keys) → npm run dev → open http://localhost:3117

Visit GitHub Visit Website

Related Projects

AI Agents From Scratch

4.5k · JavaScript

Active A

Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.

javascriptagentevaluation +2

· 12-step progressive learning path from raw LLM calls to ReAct agents
· Runs entirely on local LLMs via node-llama-cpp, no API keys needed
· Covers function calling, memory, Tree of Thought, and error handling

View on GitHub

DeepCamera

3.0k · JavaScript

Normal A

Open-Source AI Camera Skills Platform, AI NVR & CCTV Surveillance. LLM-powered agentic security camera agent with pluggable AI skills. Runs on Mac Mini & AI PC.

javascriptagenttools +3

· VLM scene analysis and object detection running locally with Qwen, DeepSeek, SmolVLM
· 19+ pluggable AI skills across detection, segmentation, annotation, and training
· Auto-detection of GPU/NPU/CPU hardware with TensorRT, CoreML, OpenVINO acceleration

View on GitHub

OpenShell

8.2k · Rust

Active A

OpenShell is the safe, private runtime for autonomous AI agents, developed by NVIDIA. Provides controlled execution environments and resource management.

rustagentframework +2

· Sandboxed execution environments protecting data, credentials, and infrastructure with declarative YAML policies
· Four defense-in-depth layers: filesystem, network, process, and inference policy enforcement
· Hot-reloadable network and inference policies via `openshell policy set` without restarting sandboxes

View full details → View on GitHub

Agents Towards Production

21.3k · Jupyter Notebook

Active A+

End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.

agentframeworkevaluation +2

· 28 production-grade tutorials — Covering stateful workflows, vector memory, web search APIs and more
· End-to-end coverage — From Docker deployment, FastAPI endpoints to security guardrails and GPU scaling
· Multi-agent coordination — Teaching multi-Agent collaboration architecture design and implementation