Quick start¶
Get HYDRA × PDX running in 15 minutes.
Prerequisites¶
- Python 3.10+
- A Groq API key (free tier works)
- A VPS with a public IP (for HYDRA) or localhost for testing
- GPU with 8GB+ VRAM (optional, for fine-tuning only)
1. Clone the repository¶
2. Install dependencies¶
3. Configure HYDRA¶
Edit .env:
4. Generate SSH keys¶
This generates RSA and Ed25519 host keys in the keys/ directory.
5. Start HYDRA¶
You should see:
[HYDRA] SSH honeypot listening on 0.0.0.0:2222
[HYDRA] Groq API connected (llama-3.3-70b)
[HYDRA] 3 personas loaded: fintech_trading, crypto_validator, corp_ad
[HYDRA] PromptGuard active (warn=0.5, block=0.8)
6. Test it¶
From another terminal:
Try some commands:
uname -a # Returns realistic kernel info
ls /root # Shows persona-specific files
cat /root/.aws/credentials # Shows decoy AWS keys (fintech persona)
7. Process data with PDX¶
After capturing sessions:
cd ../pdx
# Split events into defensive + offensive
python -m pdx.training.data_router split
# Generate training datasets
python -m pdx.training.data_router generate --all
# Check results
python -m pdx.training.data_router status
8. Fine-tune (optional)¶
python training/finetune_pdx.py \
--dataset training_output/data_router/offensive/sft_attack_chains.jsonl \
--model qwen \
--epochs 3 \
--rank 16
See Fine-tuning guide for detailed options.
What's next¶
- Deploy on a VPS for real-world capture
- Connect Burp Suite for web pentest data
- Understand the data flow in detail