Command-line interface for the Amplifier AI-powered modular development platform.
Note: This is a reference implementation of an Amplifier CLI. It works with amplifier-core and demonstrates how to build a CLI around the kernel. You can use this as-is, fork it, or build your own CLI using the core.
# Try without installing
uvx --from git+https://github.com/microsoft/amplifier@next amplifier
# Install globally
uv tool install git+https://github.com/microsoft/amplifier@next# First-time setup (auto-runs if no config)
amplifier init
# Install shell completion (optional, one-time setup)
amplifier --install-completion
# Single command
amplifier run "Create a Python function to calculate fibonacci numbers"
# Interactive chat mode
amplifier
# Use specific profile
amplifier run --profile dev "Your prompt"# Provider management
amplifier provider use <name> [--local|--project|--global]
amplifier provider current
amplifier provider list
amplifier provider reset [--scope]
# Profile management
amplifier profile use <name> [--local|--project|--global]
amplifier profile create <name> --extend <parent>
amplifier profile current
amplifier profile list
amplifier profile show <name>
# Collection management
amplifier collection add <git-url> [--local]
amplifier collection list
amplifier collection show <name>
amplifier collection remove <name> [--local]
# Module management
amplifier module add <name> [--local|--project|--global]
amplifier module remove <name> [--scope]
amplifier module current
amplifier module list
amplifier module show <name>
# Source management
amplifier source add <id> <uri> [--local|--project|--global]
amplifier source remove <id> [--scope]
amplifier source list
amplifier source show <id>amplifier run "prompt" # Single interaction
amplifier # Interactive chat
amplifier session list # Recent sessions
amplifier session show <id> # Session details
amplifier session resume <id> # Continue sessionamplifier init # First-time setup
amplifier logs # Watch activity log
amplifier --install-completion # Set up tab completion
amplifier --version # Show version
amplifier --help # Show helpEnable tab completion with one command. Amplifier automatically installs completion for standard shell setups.
amplifier --install-completionWhat happens:
- Detects your shell (bash, zsh, or fish) from
$SHELL - Automatically appends the completion line to your shell config:
- Bash:
~/.bashrc - Zsh:
~/.zshrc - Fish:
~/.config/fish/completions/amplifier.fish
- Bash:
- Checks if already installed (safe to run multiple times)
- Falls back to manual instructions if custom configuration detected
Output (standard setup):
Detected shell: bash
✓ Added completion to /home/user/.bashrc
To activate:
source ~/.bashrc
Or start a new terminal.
Output (already installed):
Detected shell: bash
✓ Completion already configured in /home/user/.bashrc
Once active, tab completion works throughout the CLI:
amplifier pro<TAB> # Completes to "profile"
amplifier profile u<TAB> # Completes to "use"
amplifier profile use <TAB> # Shows available profiles
amplifier run --<TAB> # Shows all optionsThis CLI is built on top of amplifier-core and provides:
- Profile system - Reusable, composable configuration bundles
- Settings management - Three-scope configuration (local/project/global)
- Module resolution - Six-layer module source resolution
- Session storage - Project-scoped session persistence
- Interactive mode - REPL with slash commands
- Key management - Secure API key storage
- Anthropic Claude - Recommended, most tested (Sonnet, Opus models)
- OpenAI - Good alternative (GPT-4o, GPT-4o-mini, o1 models)
- Azure OpenAI - Enterprise users with Azure subscriptions
- Ollama - Local, free, no API key needed
- Python 3.11+
- UV package manager
cd amplifier-app-cli
uv pip install -e .
uv run pytestamplifier_app_cli/
├── commands/ # CLI command implementations
├── collections/ # Collection system (installation, resolution)
├── data/
│ ├── collections/ # Bundled collections (foundation, developer-expertise)
│ ├── profiles/ # Bundled profiles (inside collections)
│ ├── agents/ # Bundled agents (inside collections)
│ └── context/ # Bundled context files
├── profile_system/ # Profile loading and compilation
├── session_storage/ # Session persistence
├── toolkit/ # Utilities for building scenario tools
├── settings.py # Settings management
├── key_manager.py # API key management
└── main.py # CLI entry point
- Complete user guide
- Configuration reference
- Collections guide
- Scenario tools guide
- Profile authoring
- Agent authoring
- Module development
- Toolkit guide
Note
This project is not currently accepting external contributions, but we're actively working toward opening this up. We value community input and look forward to collaborating in the future. For now, feel free to fork and experiment!
Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit Contributor License Agreements.
When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.
This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.