emcd-agents¶

🤖 AI Agent Configuration Management - Centralized, version-controlled configurations for AI development tools with hybrid distribution architecture. Enables rapid iteration on agent configurations while maintaining consistency across multiple projects through tag-based releases and dynamic content generation.

Key Features ⭐¶

🏗️ Hybrid Distribution Architecture: Combines Copier templates for base configuration with agentsmgr CLI for dynamic content generation from structured data sources.
⚡ Lightning-Fast Iteration: Tag-based releases enable rapid configuration updates without heavyweight project releases.
🔧 Simple CLI Interface: Primary populate command generates agent configurations from any compatible data source with simulation mode support.
📦 Extensible Data Sources: Works with any properly structured agent configuration library, enabling community-driven configuration sharing and reuse.
🔌 Plugin Architecture: Extensible source handlers (git, local) and renderers (Claude, Opencode, Codex, Qwen) with decorator-based registration system.
🎯 Multi-Target Support: Per-user and per-project targeting modes with intelligent symlink management for seamless AI tool integration.

Installation 📦¶

Method: Download Standalone Executable¶

Download the latest standalone executable for your platform from GitHub Releases. These executables have no dependencies and work out of the box.

Method: Install Executable Script¶

Install via the uv tool command:

uv tool install emcd-agents

or, run directly with uvx:

uvx --from emcd-agents agentsmgr

Or, install via pipx:

pipx install emcd-agents

Method: Install Python Package¶

Install via uv pip command:

uv pip install emcd-agents

Or, install via pip:

pip install emcd-agents

Examples 💡¶

CLI Usage¶

Populate Agent Content:

Generate configurations from a git source:

agentsmgr populate --source=github:emcd/agents-common@agents-2

Generate content for per-project mode:

agentsmgr populate --mode=per-project --source=git:path/to/local/repo

Test Configuration Changes:

Preview what would be generated without making changes:

agentsmgr populate --simulate --source=github:emcd/agents-common@agents-2

Copier Template Integration¶

Apply Base Template:

Use as a Copier template for new projects:

copier copy gh:emcd/agents-common path/to/new-project

Update Existing Projects:

Update base configuration templates:

copier update --answers-file .auxiliary/configuration/copier-answers--agents.yaml

Use Cases¶

Project Templates: Distribute consistent AI agent configurations across multiple project templates
Development Teams: Maintain synchronized agent configurations across team members
Configuration Evolution: Rapidly iterate on slash commands and agent definitions
Multi-Tool Support: Support Claude Code, Opencode, Codex, Qwen Code, and future AI development environments

Contribution 🤝¶

Contribution to this project is welcome! However, it must follow the code of conduct for the project.

Please file bug reports and feature requests in the issue tracker or submit pull requests to improve the source code or documentation.

For development guidance and standards, please see the development guide.

Additional Indicia¶

Other Projects by This Author 🌟¶

python-absence (absence on PyPI)

🕳️ A Python library package which provides a sentinel for absent values - a falsey, immutable singleton that represents the absence of a value in contexts where None or False may be valid values.
python-accretive (accretive on PyPI)

🌌 A Python library package which provides accretive data structures - collections which can grow but never shrink.
python-classcore (classcore on PyPI)

🏭 A Python library package which provides foundational class factories and decorators for providing classes with attributes immutability and concealment and other custom behaviors.
python-dynadoc (dynadoc on PyPI)

📝 A Python library package which bridges the gap between rich annotations and automatic documentation generation with configurable renderers and support for reusable fragments.
python-falsifier (falsifier on PyPI)

🎭 A very simple Python library package which provides a base class for falsey objects - objects that evaluate to False in boolean contexts.
python-frigid (frigid on PyPI)

🔒 A Python library package which provides immutable data structures - collections which cannot be modified after creation.
python-icecream-truck (icecream-truck on PyPI)

🍦 Flavorful Debugging - A Python library which enhances the powerful and well-known icecream package with flavored traces, configuration hierarchies, customized outputs, ready-made recipes, and more.
python-mimeogram (mimeogram on PyPI)

📨 A command-line tool for exchanging collections of files with Large Language Models - bundle multiple files into a single clipboard-ready document while preserving directory structure and metadata… good for code reviews, project sharing, and LLM interactions.