Metadata-Version: 2.4
Name: ladyol
Version: 0.2.0
Summary: Object-based prompt injection system for AI agents
Author: Morganna
Author-email: morganna@magick.ai
License: MIT
Platform: Linux
Requires-Python: >=3.10
Requires-Dist: httpx>=0.24
Requires-Dist: tenacity>=8.2.0
Requires-Dist: pydantic>=2.0,<3.0
Requires-Dist: pyyaml>=6.0,<7.0
Requires-Dist: kahndor>=0.0.1,<1.0.0
Requires-Dist: subtrix>=0.0.1,<1.0.0
Requires-Dist: goalt>=0.1.0,<1.0.0
Requires-Dist: squirl>=0.0.1,<1.0.0
Requires-Dist: thingery>=0.1.0,<1.0.0
Requires-Dist: mindot>=0.1.0,<1.0.0
Requires-Dist: pycurity>=0.0.1,<1.0.0
Requires-Dist: pytest>=8.0 ; extra == "dev"
Requires-Dist: pytest-asyncio>=0.23 ; extra == "dev"
Requires-Dist: pytest-json-report>=1.5 ; extra == "dev"
Requires-Dist: pytest-cov>=4.1 ; extra == "dev"
Requires-Dist: ruff>=0.5 ; extra == "dev"
Provides-Extra: dev
Description: # LadyOl
        
        Object-based prompt injection system for AI agents.
        
        ## Features
        
        - **Context Injection** - Inject past experiences and project context into messages
        - **Context Closure** - Store task outcomes for continuous learning
        - **Identity Management** - Persistent agent identity documents in Glain
        - **Memory System** - Two-layer memory (MEMORY.md + Glain)
        - **Skills Loading** - Load and manage agent skills
        - **Prompt Scaling** - Automatically adjust prompt complexity based on model capability
        
        ## Installation
        
        ```bash
        pip install ladyol
        ```
        
        ## Usage
        
        ```bash
        # Run LadyOL
        ladyol run
        
        # Check status
        ladyol status
        ```
        
        ### Options
        
        | Argument | Type | Required | Default | Description |
        |----------|------|----------|---------|-------------|
        | `--verbose` / `-v` | flag | No | false | Enable verbose output |
        | `--config` / `-c` | path | No | None | Path to configuration file |
        
        ### Commands
        
        #### `run`
        Run the main operation.
        
        ```bash
        ladyol run
        ```
        
        #### `status`
        Check project status.
        
        ```bash
        ladyol status
        ```
        
        ## Quick Start
        
        ```python
        from pathlib import Path
        from ladyol import LadyOlPromptEngine, LadyOlConfig
        
        # Initialize the engine
        config = LadyOlConfig()
        engine = LadyOlPromptEngine(
            workspace=Path("./workspace"),
            config=config,
        )
        
        # Inject context into messages
        messages = [{"role": "user", "content": "What was I working on?"}]
        updated_messages = await engine.inject_context(messages)
        
        # Get memory context
        memory_context = engine.get_memory_context()
        
        # Get skills summary
        skills = engine.get_skills_summary()
        ```
        
        ## Architecture
        
        ```
        ladyol/
        ├── agent/           # Core agent components
        │   ├── context_closure.py
        │   ├── context_injector.py
        │   ├── identity.py
        │   ├── memory.py
        │   ├── prompt_scaler.py
        │   └── skills.py
        ├── config/          # Configuration schemas
        ├── prompt/          # Prompt engine
        └── utils/          # Utilities
        ```
        
        ## License
        
        MIT
Description-Content-Type: text/markdown
