graph TD
    A[User Query] --> B[Planning Phase]
    B --> C{Execution Phase}
    C -- Tool Calls --> D[Ghidra/LLM]
    D --> C
    C --> E[Review Phase]
    E -- Agentic Loop --> B
    E --> F[Final Response]

    style E fill:#f9f,stroke:#333,stroke-width:2px
    style B fill:#bbf,stroke:#333,stroke-width:2px

# Clone repository
git clone https://github.com/LLNL/OGhidra.git
cd OGhidra

# Install dependencies (choose one)
uv sync                          # Using UV (recommended)
pip install -r requirements.txt  # Using pip

# Configure environment
cp .env.example .env
# Edit .env with your settings

# For Ollama (local models)
ollama pull gemma3:27b           		# Good balance (20GB RAM)
ollama pull nomic-embed-text     		# Embedding model for RAG

# Alternative models
ollama pull gpt-oss:120b         		# High quality (80GB RAM)
ollama pull devstral-2:123b 			# High quality (80GB RAM)
ollama pull devstral-2:123b-cloud       # Cloud Model

# GUI Mode (recommended)
uv run main.py --ui

# Interactive CLI
uv run main.py --interactive

# In interactive CLI, test connection
health

curl http://localhost:8080/methods

LLM_PROVIDER=ollama
OLLAMA_BASE_URL=http://localhost:11434/
OLLAMA_MODEL=gemma3:27b
OLLAMA_EMBEDDING_MODEL=nomic-embed-text

LLM_PROVIDER=external
EXTERNAL_PROVIDER=google
EXTERNAL_API_KEY=your-api-key-here
EXTERNAL_MODEL=gemini-3.1-flash-lite-preview
EXTERNAL_EMBEDDING_MODEL=gemini-embedding-001

LLM_PROVIDER=custom_api
CUSTOM_API_URL=https://api.example.com/v1/chat/completions
CUSTOM_API_KEY=your-api-key-here
CUSTOM_API_MODEL=your-model-name
CUSTOM_API_EMBEDDING_MODEL=your-embedding-model

# Context budget in tokens (adjust to your model's limit)
CONTEXT_BUDGET=100000              # 100K tokens for mid-size models
                                   # 200K+ for frontier models

# Execution settings
MAX_EXECUTION_STEPS=5              # Steps per planning cycle
MAX_AGENTIC_CYCLES=3               # How many plan-execute-review loops
AGENTIC_LOOP_ENABLED=true          # Enable adaptive replanning

# In GUI: Use "Task Mode" dropdown
# In CLI: set task_mode <mode>

task_mode malware      # Malware analysis with pattern detection
task_mode vuln         # Vulnerability research focus
task_mode general      # General reverse engineering

# Enumerate all functions with AI summaries
# Choose from:
- Rename Only: Only process generic function names
- Smart Enumeration: Focus on security-relevant functions
- Full Enumeration: Analyze every function in the binary

# Save progress
File → Save Session

# Load previous work
File → Load Session

# Auto-save after bulk operations
# Sessions include:
- Analyzed functions with summaries
- RAG vectors for semantic search
- Performance statistics
- UI state

--ghidra-backend={http,pyghidra}

--pyghidra-project=/path/to/project.gpr

--pyghidra-program=<program_name>

uv run main.py --ui --ghidra-backend=pyghidra --pyghidra-project=/path/to/project.gpr --pyghidra-program=<program_name>

--pyghidra-binary=/path/to/binary

# In GUI: Click "Generate Report" button
# Report includes:
- Executive Summary
- Function Inventory (renamed functions with behavior)
- Security Analysis (high-risk functions, patterns)
- Import Analysis
- String Analysis
- Recommendations

# Enable in .env
RESULT_CACHE_ENABLED=true
TIERED_CONTEXT_ENABLED=true

CURRENT_LOOP_MAX_CHARS=2000   # Recent: full detail
PREV_LOOP_MAX_CHARS=400       # Previous: summaries
OLDER_LOOP_MAX_CHARS=100      # Older: references only

LLM_LOGGING_ENABLED=true
LLM_LOG_FILE=logs/llm_interactions.log
LLM_LOG_FORMAT=json

# Verify plugin is loaded
# Open up codebrowser!

# Check server is running
curl http://localhost:8080/methods

# Verify Ollama is running
ollama list

# Check connectivity
curl http://localhost:11434/api/tags

# Restart Ollama service
ollama serve

# Reduce context budget
CONTEXT_BUDGET=50000

# Enable compaction
COMPACTION_ENABLED=true
COMPACTION_THRESHOLD=0.75

┌─────────────────────────────────────────────────────────────┐
│                        OGhidra UI                           │
│                  (GUI / Interactive CLI)                    │
└────────────────────────┬────────────────────────────────────┘
                         │
                         ▼
┌─────────────────────────────────────────────────────────────┐
│                   Bridge (src/bridge.py)                    │
│  ┌────────────────────────────────────────────────────────┐ │
│  │ • Agentic Loop: Plan → Execute → Review → Replan       │ │
│  │ • Tool Router: Ghidra client, LLM client, CAG manager  │ │
│  │ • Context Manager: Budget allocation, compression      │ │
│  └────────────────────────────────────────────────────────┘ │
└───────────┬────────────────────────┬────────────────────────┘
            │                        │
            ▼                        ▼
┌───────────────────────┐  ┌─────────────────────────┐
│   Ghidra Client       │  │   LLM Clients           │
│ • GhidraMCP Plugin    │  │ • Ollama (local)        │
│ • Binary operations   │  │ • External APIs         │
│ • Decompilation       │  │ • Custom endpoints      │
└───────────────────────┘  └─────────────────────────┘
            │                        │
            └────────────┬───────────┘
                         ▼
┌─────────────────────────────────────────────────────────────┐
│               CAG Manager (Knowledge System)                │
│  ┌────────────────────────────────────────────────────────┐ │
│  │ • Vector Store: Semantic search over functions         │ │
│  │ • Pattern Detector: 12+ malware techniques             │ │
│  │ • Metadata Extractor: Structured function analysis     │ │
│  │ • Session Store: Persistent analysis state             │ │
│  └────────────────────────────────────────────────────────┘ │
└─────────────────────────────────────────────────────────────┘

@software{oghidra2025,
  title = {OGhidra: AI-Powered Reverse Engineering with Ghidra},
  author = {Enoch Wang},
  year = {2025},
  url = {https://github.com/LLNL/OGhidra}
}