πŸš€ -> Project on GitHub <-

πŸ“ Project Structure

πŸ“š Navigation: 🏠 Home πŸ“– Docs πŸ”„ Release Process βœ… Pre-Release Check 🀝 Contributing

Root Directory (Organized)

Crawllama/
β”œβ”€β”€ πŸ“„ README.md                    # Main documentation - START HERE!
β”œβ”€β”€ πŸ“œ LICENSE                      # MIT License
β”œβ”€β”€ 🀝 CONTRIBUTING.md              # Contribution guidelines
β”œβ”€β”€ πŸ‘₯ CODE_OF_CONDUCT.md           # Community code of conduct
β”œβ”€β”€ πŸ”’ SECURITY.md                  # Security policy
β”œβ”€β”€ πŸ“ CHANGELOG.md                 # Release history
β”‚
β”œβ”€β”€ βš™οΈ config.json                   # Main configuration
β”œβ”€β”€ πŸ“¦ requirements.txt             # Python dependencies
β”œβ”€β”€ πŸ” .env.example                 # Environment variables example
β”œβ”€β”€ 🚫 .gitignore                   # Git ignore rules
β”œβ”€β”€ πŸ§ͺ pytest.ini                   # Test configuration
β”‚
β”œβ”€β”€ 🐍 main.py                      # CLI entry point
β”œβ”€β”€ 🌐 app.py                       # FastAPI server
β”œβ”€β”€ πŸ₯ health-dashboard.py          # Health monitoring dashboard
β”‚
β”œβ”€β”€ πŸ“‚ docs/                        # ALL documentation (see below)
β”œβ”€β”€ πŸ“‚ core/                        # Core logic (Agent, LLM, Cache, etc.)
β”œβ”€β”€ πŸ“‚ tools/                       # Tools (Search, RAG, OSINT, etc.)
β”œβ”€β”€ πŸ“‚ utils/                       # Utilities (Logger, Validators, etc.)
β”œβ”€β”€ πŸ“‚ plugins/                     # Plugin system
β”œβ”€β”€ πŸ“‚ tests/                       # Test suite
β”œβ”€β”€ πŸ“‚ data/                        # Data & cache
β”œβ”€β”€ πŸ“‚ logs/                        # Log files
β”œβ”€β”€ πŸ“‚ scripts/                     # Utility scripts
β”œβ”€β”€ πŸ“‚ config/                      # Additional configs
└── πŸ“‚ .github/                     # GitHub templates & workflows

πŸ“š docs/ - Documentation Directory

docs/
β”œβ”€β”€ πŸ“– README.md                    # Documentation overview (Navigation)
β”‚
β”œβ”€β”€ πŸš€ Quick Start & Installation
β”‚   β”œβ”€β”€ QUICKSTART.md               # 5-minute quick start
β”‚   └── INSTALLATION.md             # Detailed installation
β”‚
β”œβ”€β”€ πŸ€– Adaptive Agent System (NEW v1.4.4)
β”‚   β”œβ”€β”€ ADAPTIVE_HOPS.md            # πŸ†• Complete adaptive system documentation
β”‚   └── ADAPTIVE_HOPS_QUICKSTART.md # πŸ†• 3-step integration guide
β”‚
β”œβ”€β”€ πŸ“˜ Feature Guides
β”‚   β”œβ”€β”€ API_USAGE.md                # REST API documentation
β”‚   β”œβ”€β”€ LANGGRAPH_GUIDE.md          # Multi-hop reasoning
β”‚   β”œβ”€β”€ OSINT_USAGE.md              # OSINT features
β”‚   β”œβ”€β”€ OSINT_CONTEXT_USAGE.md      # OSINT context usage
β”‚   β”œβ”€β”€ SOCIAL_INTELLIGENCE.md      # Social intelligence
β”‚   β”œβ”€β”€ PLUGIN_TUTORIAL.md          # Plugin development
β”‚   β”œβ”€β”€ HALLUCINATION_DETECTION.md  # Hallucination detection
β”‚   └── SEARCH_LIMITATIONS.md       # Search limitations
β”‚
β”œβ”€β”€ πŸ₯ Health Monitoring
β”‚   β”œβ”€β”€ HEALTH_MONITORING.md        # Health system
β”‚   β”œβ”€β”€ HEALTH_DASHBOARD.md         # Dashboard usage
β”‚   β”œβ”€β”€ HEALTH_FEATURES.md          # Available features
β”‚   └── DASHBOARD_STARTER.md        # Dashboard starter
β”‚
└── πŸ”§ Development & Security
    β”œβ”€β”€ development/
    β”‚   └── PROJECT_STRUCTURE.md    # This document
    └── security/
        β”œβ”€β”€ SECRET_LEAK_RESPONSE.md # Secret leak emergency plan
        └── CODEQL_SECURITY_ANALYSIS.md # Security analysis

πŸ—οΈ Code Structure

core/ - Core Modules

core/
β”œβ”€β”€ agent.py                        # Standard agent
β”œβ”€β”€ adaptive_hops.py                # πŸ†• v1.4.4: Adaptive complexity detection & agent selection
β”œβ”€β”€ adaptive_integration.py         # πŸ†• v1.4.4: AdaptiveQueryProcessor integration layer
β”œβ”€β”€ langgraph_agent.py              # Multi-hop agent
β”œβ”€β”€ llm_client.py                   # Ollama client
β”œβ”€β”€ context_manager.py              # Token management
β”œβ”€β”€ cache.py                        # Smart cache
β”œβ”€β”€ session_manager.py              # Multi-user sessions
β”œβ”€β”€ plugin_manager.py               # Plugin system
β”œβ”€β”€ fallback_manager.py             # Fallback logic
β”œβ”€β”€ registry.py                     # Tool registry
β”œβ”€β”€ robustness.py                   # Robustness features
β”œβ”€β”€ hallu_detect.py                 # Hallucination detection
β”œβ”€β”€ lazy_loader.py                  # Lazy loading
β”œβ”€β”€ unified_loader.py               # Unified loader
β”‚
β”œβ”€β”€ health/                         # Health monitoring
β”‚   β”œβ”€β”€ system_monitor.py           # System metrics
β”‚   β”œβ”€β”€ component_checker.py        # Component health
β”‚   β”œβ”€β”€ performance_tracker.py      # Performance tracking
β”‚   β”œβ”€β”€ alert_system.py             # Alert system
β”‚   β”œβ”€β”€ dashboard.py                # Dashboard logic
β”‚   β”œβ”€β”€ rich_dashboard.py           # Rich terminal UI
β”‚   └── ...
β”‚
└── osint/                          # OSINT modules
    β”œβ”€β”€ query_parser.py             # Advanced search operators
    β”œβ”€β”€ email_intel.py              # Email intelligence
    β”œβ”€β”€ phone_intel.py              # Phone intelligence
    β”œβ”€β”€ query_enhancer.py           # AI query enhancement
    └── compliance.py               # Compliance & rate limiting

tools/ - Modular Tools

tools/
β”œβ”€β”€ web_search.py                   # Multi-source web search
β”œβ”€β”€ wiki_lookup.py                  # Wikipedia integration
β”œβ”€β”€ page_reader.py                  # HTML parser
β”œβ”€β”€ rag.py                          # RAG system (ChromaDB)
β”œβ”€β”€ osint_tool.py                   # OSINT tool integration
└── tool_registry.py                # Tool management

utils/ - Utility Functions

utils/
β”œβ”€β”€ logger.py                       # Structured logging
β”œβ”€β”€ validators.py                   # Input validation
β”œβ”€β”€ retry.py                        # Retry logic (tenacity)
β”œβ”€β”€ safe_fetch.py                   # Safe HTTP
β”œβ”€β”€ rate_limiter.py                 # Rate limiting
β”œβ”€β”€ domain_blacklist.py             # Domain filter
β”œβ”€β”€ async_utils.py                  # Async operations
β”œβ”€β”€ parallel_search.py              # Parallelization
β”œβ”€β”€ resource_monitor.py             # RAM/performance
β”œβ”€β”€ cli_helper.py                   # Enhanced CLI
β”œβ”€β”€ text_cleaner.py                 # Text cleaning
└── secure_config.py                # Encrypted config

tests/ - Test Suite

tests/
β”œβ”€β”€ unit/
β”‚   β”œβ”€β”€ test_adaptive_hops.py       # πŸ†• v1.4.4: Adaptive system unit tests (30 tests)
β”‚   β”œβ”€β”€ test_cache.py               # Cache tests
β”‚   β”œβ”€β”€ test_llm_client.py          # LLM client tests
β”‚   └── test_memory_store.py        # Memory store tests
β”œβ”€β”€ integration/
β”‚   β”œβ”€β”€ test_adaptive_integration.py # πŸ†• v1.4.4: End-to-end adaptive tests (16 tests)
β”‚   └── test_integration.py         # General integration tests
β”œβ”€β”€ osint/                          # OSINT-specific tests
β”œβ”€β”€ security/                       # Security tests
β”œβ”€β”€ multihop/                       # Multi-hop reasoning tests
β”œβ”€β”€ robustness/                     # Robustness tests
β”œβ”€β”€ quality/                        # Quality tests
└── other/                          # Other specialized tests

πŸ“¦ data/ - Data Directory

data/
β”œβ”€β”€ blacklist.txt                   # Domain blacklist
β”œβ”€β”€ cache/                          # Web cache (TTL-based)
β”œβ”€β”€ embeddings/                     # ChromaDB embeddings
β”œβ”€β”€ test_embeddings/                # Test embeddings
β”œβ”€β”€ history/                        # Session history
β”œβ”€β”€ models/                         # Model files
└── osint_logs/                     # OSINT audit logs

πŸ”§ .github/ - GitHub Configuration

.github/
β”œβ”€β”€ ISSUE_TEMPLATE/                 # Issue templates
β”‚   β”œβ”€β”€ bug_report.yml              # Bug report
β”‚   β”œβ”€β”€ feature_request.yml         # Feature request
β”‚   └── documentation.yml           # Documentation issue
β”œβ”€β”€ pull_request_template.md        # PR template
└── CODEOWNERS                      # Code ownership

πŸš€ Scripts - Setup & Execution

β”œβ”€β”€ setup.bat / setup.sh            # Automatic installation
β”œβ”€β”€ run.bat / run.sh                # Start agent
β”œβ”€β”€ health-dashboard.bat/.sh        # Start health dashboard
└── scripts/
    β”œβ”€β”€ debug_ddgs.py               # DuckDuckGo debug
    β”œβ”€β”€ extract_all_functions.py    # Function extractor
    └── ...

πŸ†• New in v1.4.4: Adaptive Agent Hopping System

Key Additions:

Features:

πŸ“Š Metrics

Category Count Description
Core Modules 17+ Core functionality (incl. adaptive system)
Tools 6+ Modular tools
Utils 12+ Utility functions
Tests 143+ Test cases (97 existing + 46 adaptive)
Docs 22+ Documentation files (incl. adaptive docs)
LOC ~16,000+ Lines of code (incl. adaptive system)

πŸ—ΊοΈ Navigation

Back to Main Page Documentation Overview