by eli-labz
A production-grade OSINT platform that provides situational awareness across multiple intelligence domains.
# Add to your Claude Code skills
git clone https://github.com/eli-labz/Third-EyeLast scanned: 6/14/2026
{
"issues": [
{
"type": "npm-audit",
"message": "@vercel/analytics: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "@vitest/mocker: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "esbuild: esbuild: Missing binary integrity verification in Deno module enables remote code execution via NPM_CONFIG_REGISTRY",
"severity": "high"
},
{
"type": "npm-audit",
"message": "next: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "postcss: PostCSS has XSS via Unescaped </style> in its CSS Stringify Output",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "vite: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "vite-node: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "vitest: Vulnerability found",
"severity": "high"
}
],
"status": "WARNING",
"scannedAt": "2026-06-14T08:16:29.806Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}Third-Eye is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by eli-labz. A production-grade OSINT platform that provides situational awareness across multiple intelligence domains. It has 938 GitHub stars.
Third-Eye returned warnings in SkillsLLM's automated security scan. It has no critical vulnerabilities, but review the flagged issues in the Security Report section before adding it to your workflow.
Clone the repository with "git clone https://github.com/eli-labz/Third-Eye" and add it to your Claude Code skills directory (see the Installation section above).
Third-Eye is primarily written in TypeScript. It is open-source under eli-labz on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh Third-Eye against similar tools.
No comments yet. Be the first to share your thoughts!
Requires a passing catalog security scan. Resolve the flagged issues and resubmit to enable featuring.
A real-time global intelligence dashboard that aggregates live flight tracking, CCTV networks, earthquake monitoring, conflict zone mapping, and 24/7 news feeds into a single GPU-accelerated interface.
🌐 Live Demo · 🐛 Report Bug · ✨ Request Feature · ⭐ Star This Repo
If Third Eye is useful to you, please consider giving it a ⭐ — it helps the project grow and reach more people!
Third Eye is a production-grade OSINT platform that provides real-time situational awareness across 13+ intelligence domains — all in one GPU-accelerated interface. Built with Next.js 16 and MapLibre GL, every data point is rendered via WebGL for 60fps performance even with thousands of concurrent entities on-screen.
No API keys required to get started. Clone, run, and you're live in under 2 minutes.
| Domain | Data Points | Sources |
|---|---|---|
| ✈️ Aviation | Commercial, Private, Military, Jets | OpenSky Network |
| 🚢 Maritime | 39 Global Ports, 10 Chokepoints | Static Naval Intel |
| 📷 CCTV | 2,000+ Cameras | TfL, WSDOT, Caltrans, NYC DOT, VicRoads + more |
| 🌋 Seismic | Real-time M2.5+ | USGS Earthquake API |
| 🔥 Fires | Active Hotspots | NASA FIRMS |
| 📺 News | 24/7 Live Streams | 25+ Global Broadcasters |
| 🌪️ Weather | Severe Events | NASA EONET |
| 🛰️ Space | Solar Weather, Satellites | NOAA SWPC, N2YO |
| 🛡️ Cyber | CVE Threats, Vulnerability Scanning | NVD, Custom Scanner |
| ⚔️ Conflict | 13 Active Zones | Static OSINT Intel |
| 💰 Crypto | BTC + ETH Wallet Tracing, OFAC SDN Match | blockstream.info, Blockscout, OpenSanctions |
| 🚫 Sanctions | Person / Org / Vessel SDN Search | OpenSanctions (US OFAC SDN mirror) |
| 📱 Telegram OSINT | Geoparsed Posts from Public Channels | t.me/s/ web preview |
git clone https://github.com/eli-labz/Third-Eye.git
cd Third-Eye
npm install
npm run dev
Open http://localhost:3000 — done. No API keys needed.
git clone https://github.com/eli-labz/Third-Eye.git
cd Third-Eye
cp .env.template .env # optional — configure keys / port
docker compose up -d
docker pull ghcr.io/aiacos/third-eye:latest
docker run -d -p 3000:3000 --env-file .env ghcr.io/aiacos/third-eye:latest
💡 Custom port: Set
THIRDEYE_PORTin.envto change the published host port without editing the compose file.
Third Eye works without any API keys — all core layers use public, keyless sources. Copy .env.template to .env and configure only what you need:
# Published host port (container always listens on 3000). Default: 3000
THIRDEYE_PORT=3000
# RECON scanner backend — generate key with: openssl rand -hex 32
SCANNER_URL=
SCANNER_KEY=
# Optional — for higher rate limits
FIRMS_API_KEY= # NASA FIRMS
OPENSKY_CLIENT_ID= # OpenSky OAuth2
OPENSKY_CLIENT_SECRET=
N2YO_API_KEY= # N2YO satellites
AIS_API_KEY= # aisstream.io maritime
Without
SCANNER_URL/SCANNER_KEYthe RECON toolkit returns503; every other layer works out of the box.
THIRDEYE_TELEGRAM_CHANNELS| Layer | Technology |
|---|---|
| Framework | Next.js 16 (App Router, Turbopack) |
| Language | TypeScript 5 |
| Map Engine | MapLibre GL JS (WebGL) |
| Animations | Framer Motion |
| Icons | Lucide React |
| Styling | Custom CSS Design System |
| Deployment | Vercel Edge Network |
| Key | Action |
|---|---|
F |
Toggle flight layers |
E |
Toggle earthquakes |
S |
Toggle satellites |
D |
Toggle day/night cycle |
Escape |
Close panels |
An optional, feature-flagged, human-in-the-loop data-fusion module that layers an analyst workflow over the platform's existing live feeds:
Ingestion → Ontology → Advisory AI models → Human review → Audit
It is decision-support only — nothing autonomous, kinetic, or real-world. It ingests the platform's real feeds (flights, maritime, satellites, earthquakes, GDELT, news), normalizes them into canonical entities, runs explainable advisory models (object-detection summary, track-anomaly detection, report summarization, course-of-action generation, risk scoring), and routes every recommendation into a human approve / reject / request-changes queue with a full audit trail.
Completely invisible unless enabled:
ENABLE_MSS_SMART_SYSTEM_MODULE=true # adds a "Smart System" panel + /api/smart-system/*
SMART_SYSTEM_RUN_KEY=<random-secret> # (recommended) guards the heavy /run endpoint
KV_REST_API_URL=... # (optional) Vercel KV / Upstash → state persists
KV_REST_API_TOKEN=... # across serverless requests
When off, the GUI, routes and workflows are unchanged. Full architecture,
API reference, and safety notes: docs/SMART_SYSTEM.md.
Run its test suite with npm test.
Contribution