v3.0 coming soon
Documentation
Installation guides and tutorials
Quick Start
Install RednBlue CLI with a single command
pip install rednblue
Guides by Domain
Computer Vision
# Authenticationset RNB_TOKEN=your_token
# Classifier
rnb preview --model vgg16.pth \
--input images/ --submit
# YOLO Detector
rnb preview --model-type yolo \
--model best.pt --input images/ --submit
Compatible: ResNet, VGG, MobileNet, EfficientNet, ViT, YOLO
v3.0
LLM
# Local Python filernb llm --file my_chatbot.py
# API providerrnb llm --provider openai \
--model gpt-4 --api-key $OPENAI_KEY
# Custom endpointrnb llm --endpoint https://api.com/chat
Compatible: OpenAI, Anthropic, Gemini, Mistral, Cohere
v3.0
RAG
# Full RAG pipeline testrnb llm --file my_rag_app.py \
--attacks RAG,SPE,JB
# Auto-detectionrnb llm --file rag_chatbot.py --auto
Detects: LangChain, LlamaIndex, ChromaDB, Pinecone
v3.0
AI Agents
# Autonomous agent testrnb llm --file my_agent.py \
--attacks AGT
# Full suiternb llm --file my_agent.py --all
Frameworks: AutoGen, CrewAI, LangChain Agents
Zero-Knowledge
- Tests run 100% locally
- Model never leaves your server
- Prompts and data stay private
- AES-256 encrypted results
- GDPR compliant
Grading
- 🥇 GOLD : ≥ 90% (robust)
- 🥈 SILVER : ≥ 75% (solid)
- 🥉 BRONZE : ≥ 50% (acceptable)
- ❌ FAIL : < 50% (insufficient)