Editions
Pay once. Private for life.
There is no tier that "unlocks" your own privacy — enforcement is identical everywhere. Higher editions add capability, never surveillance.
Core
The complete private local AI.
- Full local chat + agent tools on your GPU
- Privacy Fortress & live console
- Metatron's Cube emotional avatar
- Local voice + image & video generation
- One-shot Windows installer
Sentinel
Core, plus a four-agent defensive array that stands guard whenever ABSOL touches the internet.
- Everything in Core
- VANGUARD — network traffic anomaly detection
- AEGIS — PII & exfiltration scanning on every response
- CIPHER — prompt-injection correlation across chats
- ORACLE — tamper-evident audit log integrity
Workshop
For tinkerers who want to make ABSOL theirs.
- Everything in Sentinel
- LoRA fine-tuning kit + starter dataset
- Custom voice training walkthrough (RVC)
- Avatar & persona customization guide
- Early builds
All editions run 100% offline. Pay once, own it forever — no subscription, no account, no per-token billing.
A typical cloud AI subscription costs $240+ every year. ABSOL never bills you again.
Requirements
Runs on real hardware, not a data center.
Built and tested around a single mid-range GPU. If your machine can game, it can run ABSOL.
| OS | Windows 10/11 (INSTALL.bat) · macOS / Linux (install.py) |
| GPU | NVIDIA, 8 GB VRAM minimum — 12 GB recommended (RTX 3060-class) for voice + media generation |
| RAM | 16 GB recommended |
| Disk | ~10 GB for the app + your chosen model file |
| Model | Any .gguf — ABSOL recommends one for your GPU (Qwen3-14B on 12 GB+, Hermes-3-8B default); download links in the app |
| Internet | Only for the initial download. After that: optional, and blockable. |
Bring your AI home.
Two steps on Windows: run INSTALL.bat, then click the fox on your desktop.
Secure checkout · Your download link and license are delivered instantly after payment.