PhantomDev

An all-in-one, completely offline AI development HUD powered by local inference.

PhantomDev bundles an interactive developer interface, local socket inspection, and an embedded offline LLM into a single portable binary. No cloud API keys, no installation wizard, and no internet connection required.

---

Quick Start

1. Go to the Releases section on the right.
2. Download PhantomDev-v1.X.X-Portable.zip
3. Double-click the .exe to launch.

Note: The entire AI model and engine are bundled directly inside the binary. Initial startup takes ~5–10 seconds while the application unpacks the local inference environment into memory.

---

Features

• 100% Local & Air-Gapped: Zero external network telemetry or API dependency.
• Embedded AI Engine: Powered by llama.cpp and Qwen 2.5 Coder 1.5B.
• Developer HUD: Real-time port scanner, service killer, and AI copilot in a dark aesthetic.
• Zero Dependencies: No Python, CUDA setups, or system runtimes required on the host machine.

---

System Requirements

• OS: Windows 10 / Windows 11 (64-bit)
• RAM: 4 GB minimum (requires ~2 GB free RAM for model execution)
• Storage: ~2 GB free disk space

---

License

Distributed under the terms in the LICENSE file.