Skip to content

Ecosystem

The Amplifier ecosystem consists of modular components that combine to create AI agent systems. This page provides an overview of the ecosystem structure and available components.

Ecosystem Layers

┌─────────────────────────────────────────────────┐
│  Applications                               │
│  User-facing apps that compose capabilities │
└─────────────────┬───────────────────────────────┘
                  │
┌─────────────────▼───────────────────────────────┐
│  Bundles                                    │
│  Composable configuration packages          │
└─────────────────┬───────────────────────────────┘
                  │
┌─────────────────▼───────────────────────────────┐
│  Runtime Modules                            │
│  Providers, Tools, Orchestrators, Hooks     │
└─────────────────┬───────────────────────────────┘
                  │
┌─────────────────▼───────────────────────────────┐
│  Kernel (amplifier-core)                    │
│  Ultra-thin kernel providing mechanisms     │
└─────────────────────────────────────────────────┘

Core Components

Kernel

The foundational layer that provides module loading, event emission, and coordination.

Component Description Repository
amplifier-core Ultra-thin kernel for modular AI agent system amplifier-core

Applications

User-facing applications that compose libraries and modules.

Component Description Repository
amplifier Main Amplifier project and entry point - installs amplifier-app-cli via uv tool install amplifier
amplifier-app-cli Reference CLI application implementing the Amplifier platform amplifier-app-cli
amplifier-app-log-viewer Web-based log viewer for debugging sessions with real-time updates amplifier-app-log-viewer
amplifier-app-benchmarks Benchmarking and evaluating Amplifier amplifier-app-benchmarks
amplifierd Localhost HTTP daemon exposing amplifier-core and amplifier-foundation over REST and SSE - drive sessions from any language or framework amplifierd
amplifier-chat Chat UI plugin for amplifierd - browser-based conversational interface for creating and managing Amplifier sessions amplifier-chat
amplifier-voice Voice plugin for amplifierd - WebRTC voice interface using the OpenAI Realtime API, standalone or as a plugin amplifier-voice

Note: When you install amplifier, you get the amplifier-app-cli as the executable application. amplifierd is a separate daemon that exposes Amplifier capabilities over HTTP, and amplifier-chat and amplifier-voice are plugins that extend it with web-based chat and voice interfaces.

Libraries

Foundational libraries used by applications (not used directly by runtime modules).

Component Description Repository
amplifier-foundation Foundational library for bundles, module resolution, and shared utilities amplifier-foundation

Architectural Boundary: Libraries are consumed by applications (like amplifier-app-cli). Runtime modules only depend on amplifier-core and never use these libraries directly.

Runtime Modules

Runtime modules implement specific capabilities and are loaded dynamically based on configuration.

Module Types

  • Providers - LLM backend integrations (Anthropic, OpenAI, Gemini, etc.)
  • Tools - Agent capabilities (filesystem, bash, web, etc.)
  • Orchestrators - Execution loop strategies (basic, streaming, events)
  • Contexts - Memory management (simple, persistent)
  • Hooks - Observability and control (logging, approval, redaction, etc.)

See the full module catalog for complete listings of:

  • Official runtime modules (providers, tools, orchestrators, contexts, hooks)
  • Bundles (recipes, browser-tester, design-intelligence, python-dev, etc.)
  • Community applications and bundles
  • Community modules

Bundles

Composable configuration packages that combine providers, behaviors, agents, and context into reusable units.

Bundles enable:

  • Reusable configurations - Pre-configured setups for common use cases
  • Behavior composition - Combine multiple capabilities
  • Agent libraries - Collections of specialized agents
  • Context resources - Skills, prompts, and knowledge bases

Using Bundles

# Add a bundle to the registry (name auto-derived from bundle metadata)
amplifier bundle add git+https://github.com/microsoft/amplifier-bundle-recipes@main

# Use a bundle by name
amplifier bundle use foundation
amplifier bundle use recipes

# Show current bundle
amplifier bundle current

# Check for bundle updates
amplifier bundle update --check

# Update bundle to latest
amplifier bundle update

See the Bundle Guide for creating your own bundles.

Module Discovery

Modules are discovered via:

  1. Python Entry Points - Standard entry points in pyproject.toml

Module Contracts

All modules implement standard protocols:

Module Type Purpose
Provider LLM backend integration
Tool Agent capabilities
Orchestrator Agent loop execution strategy
Context Conversation memory management
Hook Lifecycle observation and control

See Module Contracts for detailed specifications.

Community Contributions

The Amplifier community builds:

  • Applications - Domain-specific UIs and tools
  • Bundles - Specialized capability packages
  • Modules - Custom providers, tools, and hooks

SECURITY WARNING: Community components execute arbitrary code in your environment with full access to your filesystem, network, and credentials. Only use components from sources you trust. Review code before installation.

See the full community catalog for:

  • Community applications
  • Community bundles
  • Community modules (providers, tools, hooks)

Building Components

Amplifier can help you build Amplifier components! See:

Module Source Resolution

Modules can come from:

  • Git repositories - git+https://github.com/org/repo@branch

Next Steps