AI Agents · Lesson

Plugin Discovery and Registration

Tool registries, manifest files, and dynamic tool loading at runtime.

Plugin Systems for Agents

A plugin system lets agents discover and load new tools at runtime without modifying the core agent code. The agent reads a plugin directory, loads each plugin's manifest, validates it, and adds its tools to the active tool registry.

This enables modular, extensible agent architectures.

Plugin Manifest Format

Every plugin ships a plugin.json manifest file. This is the plugin's identity card: what it is, what version it is, what tools it provides, and what it requires (Python packages, environment variables).

# plugin.json — stored in the plugin's root directory
EXAMPLE_MANIFEST = {
    'name': 'weather-tools',
    'display_name': 'Weather Tools',
    'version': '2.1.0',
    'description': 'Real-time weather and forecast tools',
    'author': 'Jane Developer <jane@example.com>',
    'license': 'MIT',
    'entry_point': 'weather_tools.plugin',  # Python module path
    'tool_definitions': [
        'get_current_weather',
        'get_5day_forecast',
        'get_weather_alerts'
    ],
    'requires': {
        'python_packages': ['requests>=2.28'],
        'env_vars': ['WEATHER_API_KEY']
    },
    'tags': ['weather', 'forecast', 'iot'],
    'min_framework_version': '1.0.0'
}

import json
print(json.dumps(EXAMPLE_MANIFEST, indent=2)[:300])

All lessons in this course

← Back to AI Agents