AIAny
AI Agent2026
Icon for item

ShadowBroker

Aggregates 60+ real-time OSINT feeds into a self-hosted geospatial dashboard and exposes an HMAC-signed agentic AI command channel so LLM-driven agents can query and act on live telemetry; privacy is experimental.

Introduction

Why this matters

Public telemetry—ADS‑B, AIS, sat TLEs, seismic sensors, CCTV and open radio—already exists but is siloed. ShadowBroker brings those signals into a single, self-hosted map interface and adds a signed, tiered agent channel so an LLM-based analyst can inspect feeds, place investigation pins, run proximity scans, and trigger map actions in real time. That combination turns fragmented public data into an actionable intelligence surface without relying on a central vendor.

What Sets It Apart
  • Unified multi-domain feed set: 60+ live layers (aircraft, ships, satellites, SAR ground-change, CCTV, SDR nodes, environmental sensors, GDELT conflict events) rendered on one MapLibre map with viewport culling and efficient update tiers. This reduces context‑switching when correlating events across domains.
  • Agentic AI channel: a bidirectional HMAC‑SHA256 signed API (tier‑gated) that lets compatible agents (OpenClaw reference) read telemetry, place pins, control map view, and batch commands concurrently. Designed for auditable, programmatic analyst workflows rather than embedding a model.
  • Time Machine & SAR: hourly snapshot playback for forensic review and SAR-based ground-change anomaly alerts (Mode A: ASF catalog; Mode B: OPERA/EGMS with opt‑in credentials).
  • Decentralized testnet: InfoNet mesh (obfuscated gate personas, dead-drop mailboxes, governance primitives). The mesh enables peer messaging and experimental governance but is explicitly labeled as a testnet.
Who it's for — and tradeoffs

Great fit if you are an OSINT analyst, researcher, radio operator, or lab operator who needs to correlate multi-domain public telemetry in near real time and wants an agent-enabled workflow you can host yourself. It is useful for situational awareness, rapid correlation, and creating reproducible snapshot timelines.

Look elsewhere or proceed cautiously if you require provable end‑to‑end privacy or a production‑grade secure messaging system today: InfoNet lanes are obfuscated but not fully E2E encrypted, and several privacy primitives are scaffolded but not yet fully wired. Some features (global flight coverage, AIS, Sentinel imagery) require operator-supplied API keys, and running the backend at scale needs adequate RAM and sensible operational controls.

Where it fits

Think of ShadowBroker as an OSINT map + agent bridge rather than a hosted SaaS: it sits between single-domain trackers (ADS‑B sites, AIS dashboards, SatNOGS) and heavyweight commercial intel suites. Its main value is fast cross-layer correlation and agentic automation on a self-hosted surface that you can audit and extend.

Information

  • Websitegithub.com
  • AuthorsBigBodyCobain
  • Published date2026/03/05

Categories

More Items

Hugging Face
AI Model2026

Open-weights LLM fine-tuned for phone-based voice agents that prioritizes low latency and reliable tool/function calling. Based on NVIDIA Nemotron 3 Nano (30B total, 3.5B active), supports very long contexts (262,144 tokens) and recommends temperature=0 with thinking disabled for deployment.

GitHub
AI Agent2026

A curated collection of production-ready Agent Skills that turn tasks—presentation production, image generation, local KB retrieval, article assembly, and web-design—into agent-loadable skill folders. Uses a SKILL.md contract, supports multiple agent runtimes (Claude Code, Cursor, Codex), and offers modular install paths with pinned release zips.

GitHub
AI Agent2026

Provides a ruleset and skills that make AI coding agents prefer the simplest correct implementation: reuse existing code, prefer stdlib/native features, and only write minimal new code. Cuts generated LOC, tokens, cost and time while preserving validation and safety.