📦 Agentic SDLC - AI-Powered Software Development Kit
Professional SDK for AI-powered software development. Clean architecture, extensible design, and production-ready.
Agentic SDLC is a Python SDK that provides a comprehensive framework for building AI-powered development tools. It features a clean public API, modular architecture, and support for custom extensions through plugins.
🚀 Quick Start
Installation
Core SDK (without CLI):
pip install agentic-sdlc
With CLI tools:
pip install agentic-sdlc[cli]
Development:
pip install -e ".[dev]"
Basic Usage
from agentic_sdlc import Config, Agent, Workflow, get_logger
# Setup logging
setup_logging(level="INFO")
logger = get_logger(__name__)
# Load configuration
config = Config()
# Create and use agents
agent = Agent(name="Developer", role="implementation")
workflow = Workflow(name="feature-dev", agents=[agent])
# Execute workflow
result = workflow.execute()
logger.info(f"Workflow completed: {result}")
CLI Usage
# Initialize a project
agentic init
# Run a workflow
agentic run my-workflow
# View configuration
agentic config get log_level
📚 Architecture
Package Structure
agentic_sdlc/
├── core/ # Core functionality (config, exceptions, logging)
├── infrastructure/ # Automation, bridges, execution engines
├── intelligence/ # Learning, monitoring, reasoning, collaboration
├── orchestration/ # Agents, models, workflows, coordination
├── plugins/ # Plugin system and registry
├── cli/ # Command-line interface (optional)
└── _internal/ # Private utilities
Public API
The SDK exposes a clean public API through the top-level agentic_sdlc module:
# Core
from agentic_sdlc import (
Config, load_config, get_config,
AgenticSDLCError, ConfigurationError, ValidationError,
setup_logging, get_logger
)
# Infrastructure
from agentic_sdlc import (
WorkflowEngine, ExecutionEngine, LifecycleManager
)
# Intelligence
from agentic_sdlc import (
Learner, Monitor, Reasoner, Collaborator
)
# Orchestration
from agentic_sdlc import (
Agent, AgentRegistry, create_agent,
ModelClient, Workflow, WorkflowBuilder
)
# Plugins
from agentic_sdlc import (
Plugin, PluginRegistry, get_plugin_registry
)
🔧 Configuration
Configuration can be loaded from files, environment variables, or set programmatically:
from agentic_sdlc import Config
# Load from file
config = Config("config.yaml")
# Get values with dot notation
log_level = config.get("log_level")
model_name = config.get("models.openai.model_name")
# Set values
config.set("log_level", "DEBUG")
# Validate configuration
config.validate()
🔌 Plugin System
Extend the SDK with custom plugins:
from agentic_sdlc import Plugin, get_plugin_registry
class MyPlugin(Plugin):
@property
def name(self) -> str:
return "my-plugin"
@property
def version(self) -> str:
return "1.0.0"
def initialize(self, config: dict) -> None:
print(f"Initializing {self.name}")
def shutdown(self) -> None:
print(f"Shutting down {self.name}")
# Register plugin
registry = get_plugin_registry()
registry.register(MyPlugin())
📖 Documentation
- Getting Started - Installation and basic usage
- Migration Guide - Upgrading from v2.x to v3.x
- Plugin Development - Creating custom plugins
- API Reference - Complete API documentation
- Architecture - Design and architecture decisions
💡 Examples
See the examples/ directory for complete working examples:
- Programmatic SDK usage:
examples/programmatic/ - CLI usage:
examples/cli/ - Plugin development:
examples/plugins/
🧪 Testing
Run the test suite:
# All tests
pytest
# Unit tests only
pytest tests/unit/
# Property-based tests
pytest tests/property/
# With coverage
pytest --cov=agentic_sdlc --cov-report=html
🔄 What's New in v3.0.0
Breaking Changes
- Reorganized package structure (moved to
src/layout) - Removed vendored dependencies from
lib/directory - CLI is now optional (install with
[cli]extra) - Old import paths are deprecated (use new public API)
New Features
- Clean public API with explicit exports
- Plugin system for extensibility
- Comprehensive configuration management
- Type hints throughout the codebase
- Property-based testing for correctness validation
Migration
See MIGRATION.md for detailed migration instructions from v2.x.
📄 License
MIT License. See LICENSE for details.
Developed by Dao Quang Truong | GitHub
Metadata
Release files for agentic-sdlc 3.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agentic_sdlc-3.0.0.tar.gz | 68.0 kB | Without provenance | Details for agentic_sdlc-3.0.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentic_sdlc-3.0.0-py3-none-any.whl | Python 3 | none | any | Details for agentic_sdlc-3.0.0-py3-none-any.whl |
Total release size: 150.4 kB
Release files / agentic_sdlc-3.0.0.tar.gz
| Download URL | agentic_sdlc-3.0.0.tar.gz |
|---|---|
| Size | 68.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
745ccecb5400186c743bf5fc2cc9a97bb7e5bab93d2b9618b774dfa7db6233ef
|
|
BLAKE2b-256 checksum How to use checksums |
804b3e5331bf9964ca0fdfd7fad63fb716e927d9374ad5d3457d7fde38fbdbfd
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Release files / agentic_sdlc-3.0.0-py3-none-any.whl
| Download URL | agentic_sdlc-3.0.0-py3-none-any.whl |
|---|---|
| Size | 82.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
0dc808450952c2a87afb58993af477aedd2dced76a5caf61c1d42b36a4c43a0f
|
|
BLAKE2b-256 checksum How to use checksums |
f506e422b675f861e4644de75bf3ae5194b715fbcf590be02297dfb3159eabce
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Security for agentic-sdlc 3.0.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.