---
license: apache-2.0
base_model: empero-ai/Qwythos-9B-v2
language:
- en
tags:
- verfy
- os-agent
- autonomous-agent
- computer-use
- cybersecurity
- penetration-testing
- ethical-hacking
- abliterated
- uncensored
- reasoning
- reflection
- self-correcting
- credential-vault
- qwen
- 1m-context
pipeline_tag: text-generation
---
**Developed by [Rowhanissick](https://rowhanissick.onrender.com) & Verfy Labs**
**Base Architecture:** `empero-ai/Qwythos-9B-v2` (Qwen3.5 9B Hybrid-Attention)
**Lead Engineer:** [Rohan Patil (Rowhanissick)](https://rowhanissick.onrender.com)
**Portfolio:** [rowhanissick.onrender.com](https://rowhanissick.onrender.com)
**Direct Contact:** [iuske553@gmail.com](mailto:iuske553@gmail.com)
---
## 🌟 Overview
**Verfy AI v1** is an advanced autonomous OS-agent, cybersecurity reasoning engine, and self-auditing intelligence model engineered for desktop/server automation, red-teaming, threat intelligence, and secure execution.
Unlike standard conversational chatbots that only output unstructured text, Verfy natively reasons through its operational stream, executes self-auditing reflection passes (``), and isolates sensitive credentials before executing environment actions (CLI, mouse, keyboard, APIs).
---
## 🛡️ Key Breakthrough Capabilities
### 1. Big Bro Self-Reflection (``)
Before finalizing an execution output or responding to ambiguous prompts, Verfy performs an internal cognitive pass inside `` tags:
- Critiques logical consistency and command safety.
- Catches potential hallucinated mock scripts before deployment.
- Verifies authorization boundaries and prevents social engineering traps.
### 2. Autonomous Agentic Safeguards
- **Credential Enclave Awareness:** Recognizes PII (emails, phone numbers, secret tokens) and flags them for secure vaulting rather than echoing in plain text.
- **Command-Gated Execution:** Refuses voluntary unauthorized broadcasting (social media, public outbound traffic) without explicit operator authorization tokens.
### 3. Native Block Architecture
Verfy AI communicates and executes tasks using structured XML-style tags:
| Block Tag | Purpose | Example |
| :--- | :--- | :--- |
| `` | Deep internal reasoning & strategy planning | Formulating execution path and identifying risks |
| `` | Pre-output self-verification & logic check | Auditing generated script for syntax & logic bugs |
| `` | Decomposes operations into sequential tasks with `` | `1. Locate browser 2. Dispatch click` |
| `` | Precondition validation & safety checks with `` | `- Screen bounds verified
- Non-destructive check passed` |
| `` | Requests visual frame capture of screen/window | `capture(mode='screen', region='desktop')` |
| `` | Shell / Bash terminal command execution | `ss -tulnp \| grep 8080` |
| `` | Safe file, log, or memory dump inspection | `read_file(path='/var/log/syslog', lines=50)` |
| `` | File patching and exploit/payload deployment | `write_file(path='/tmp/patch.py', content='...')` |
| `` | GUI mouse movements and keystroke dispatches | `mouse_move(x=500, y=500)`
`mouse_click('left')` |
| `` | Flags identified CVEs & security vulnerabilities | `ID: VULN-001 Severity: HIGH CWE-78` |
---
## ⚡ Headline Specifications
- **1,048,576 Token Context:** Full 1M-token context window out of the box via YaRN rope-scaling, allowing whole-codebase and long agentic trajectory tracking.
- **Uncensored Technical Reasoning:** Built on an abliterated Qwen 3.5 architecture (`Qwythos-9B-v2`), Verfy provides unredacted technical insights for cybersecurity research, reverse engineering, and threat modeling.
- **Dual Interaction Modes:** Operates both at the conversational level and the autonomous agent level (`` + `` + ``).
---
## 💻 How to Use (Python)
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
MODEL_ID = "Rowhanissick/Verfy-9B"
quant_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.float16
)
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
MODEL_ID,
quantization_config=quant_config,
device_map="auto",
torch_dtype=torch.float16,
trust_remote_code=True
)
prompt = "Analyze open listening sockets and report external exposure."
messages = [{"role": "user", "content": prompt}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(
**inputs,
max_new_tokens=512,
temperature=0.6,
top_p=0.9
)
print(tokenizer.decode(outputs[0][len(inputs.input_ids[0]):], skip_special_tokens=True))
```
---
## 📦 GGUF & Local Deployments
Quantized versions (Q4_K_M, Q8_0) compatible with **llama.cpp**, **Ollama**, and **LM Studio** are available via community builds:
- [`mradermacher/Verfy-9B-GGUF`](https://huggingface.co/mradermacher/Verfy-9B-GGUF)
---
## 👤 Author & Organization
- **Organization:** [Verfy Labs](https://rowhanissick.onrender.com)
- **Lead Developer:** [Rohan Patil (Rowhanissick)](https://rowhanissick.onrender.com)
- **Portfolio:** [rowhanissick.onrender.com](https://rowhanissick.onrender.com)
- **Inquiries & Security Reports:** [iuske553@gmail.com](mailto:iuske553@gmail.com)
- **Hugging Face Profile:** [@Rowhanissick](https://huggingface.co/Rowhanissick)
- **License:** Apache 2.0 (Open-source, free for research, red-teaming, and autonomous development)