Amplifier

AI-powered modular development assistant - currently in early preview.

[!CAUTION] This project is a research demonstrator. It is in early development and may change significantly. Using permissive AI tools on your computer requires careful attention to security considerations and careful human supervision, and even then things can still go wrong. Use it with caution, and at your own risk, we have NOT built in the safety systems yet. We are performing our active exploration in the open for others to join in the conversation and exploration, not as a product or "official release".

[!NOTE] Looking for the earlier Claude Code-based version? The previous version of Amplifier, built on top of Claude Code, has been moved to the amplifier-claude branch.

What is Amplifier?

Amplifier brings AI assistance to your command line with a modular, extensible architecture.

This CLI is just one interface—the reference implementation. The real power is the modular platform underneath. Soon you'll see web interfaces, mobile apps, voice-driven coding, and even Amplifier-to-Amplifier collaborative experiences. The community will build custom interfaces, mixing and matching modules dynamically to craft tailored AI experiences.

Quick Start - Zero to Working in 90 Seconds

[!IMPORTANT] Amplifier is currently developed and tested on macOS, Linux, and Windows Subsystem for Linux (WSL). Native Windows shells have known issues—use WSL unless you're actively contributing Windows fixes.

Step 1: Install UV (30 seconds)

# macOS/Linux/WSL
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows PowerShell
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

Step 2: Install Amplifier (30 seconds)

uv tool install git+https://github.com/microsoft/amplifier

Step 3: Run Amplifier (30 seconds)

# First-time wizard (auto-detects missing config)
amplifier init

# Ask a question
amplifier run "Explain async/await in Python"

# Start chat mode
amplifier

Step 4: Add bundles (optional)

# Add additional capability bundles
amplifier bundle add git+https://github.com/microsoft/amplifier-bundle-recipes@main
amplifier bundle add git+https://github.com/microsoft/amplifier-bundle-design-intelligence@main

# Use a bundle
amplifier bundle use recipes

Bundles ship focused agents you can invoke by name. Use /agents in chat to see available agents like recipes:recipe-author or design-intelligence:component-designer.

First time? Quick setup wizard:

<details> <summary>With Anthropic Claude (recommended)</summary>

Provider? [1] Anthropic [2] OpenAI [3] Azure OpenAI [4] Ollama: 1

API key: ••••••••
  Get one: https://console.anthropic.com/settings/keys
✓ Saved

Model? [1] claude-sonnet-4-5 [2] claude-opus-4-6 [3] custom: 1
✓ Using claude-sonnet-4-5

Ready! Starting chat...

Ready! Starting chat...
>

</details> <details> <summary>With Azure OpenAI (enterprise)</summary>

Provider? [1] Anthropic [2] OpenAI [3] Azure OpenAI [4] Ollama: 3

Azure endpoint: https://my-resource.openai.azure.com/
✓ Saved

Authentication? [1] API key [2] Azure CLI (az login): 2
✓ Using DefaultAzureCredential
  (Works with 'az login' locally or managed identity in Azure)

Deployment name: gpt-5.4
  Note: Use your Azure deployment name, not model name
✓ Configured

Ready! Starting chat...
>

</details> <details> <summary>With OpenAI</summary>

Provider? [1] Anthropic [2] OpenAI [3] Azure OpenAI [4] Ollama: 2

API key: ••••••••
  Get one: https://platform.openai.com/api-keys
✓ Saved

Model? [1] gpt-5.4 [2] gpt-5.4-codex [3] gpt-5.4-pro [4] custom: 1
✓ Using gpt-5.4

Ready! Starting chat...
>

</details> <details> <summary>With Ollama (local, free)</summary>

Provider? [1] Anthropic [2] OpenAI [3] Azure OpenAI [4] Ollama: 4

Model? [1] llama3 [2] codellama [3] mistral [4] custom: 1
✓ Using llama3

Make sure Ollama is running:
  ollama serve
  ollama pull llama3

Ready! Starting chat...
>

</details>

That's it! From nothing to productive AI assistant in 90 seconds.

What Can Amplifier Do?

First of all, this is still VERY early and we have not brought most of our features over yet, so keep your expectations low and we'll get it ramped up very quickly over the next week or two. Consider this just an early sneak peek.

Generate code - From simple functions to full applications
Debug problems - Systematic error resolution with the bug-hunter agent
Design systems - Architecture planning with the zen-architect agent
Research solutions - Find patterns and best practices with the researcher agent
Build modules - Use Amplifier to create new Amplifier modules (yes, really!)

Key features:

Modular: Swap AI providers, tools, and behaviors like LEGO bricks
Bundle-based: Composable configuration packages for different scenarios
Session persistence: Pick up where you left off, even across projects
Extensible: Build your own modules, bundles, or entire custom experiences

Developer Tools:

Log Viewer: Web-based tool for debugging sessions with real-time log streaming and interactive JSON inspection

# Install and run the log viewer while developing
uv tool install git+https://github.com/microsoft/amplifier-app-log-viewer@main
amplifier-log-viewer

Supported AI Providers

Amplifier works with multiple AI providers:

Anthropic Claude - Recommended, most tested (Sonnet 4.5, Opus 4.6, Haiku 4.5)
OpenAI - Good alternative (GPT-5.2, GPT-5.2-Pro, GPT-5.1-Codex)
Azure OpenAI - Enterprise users with Azure subscriptions (supports managed identity)
Ollama - Local, free, no API key needed (llama3, codellama, etc.)

Switch providers anytime:

# Switch provider (interactive - prompts for model/config)
amplifier provider use openai

# Or explicit
amplifier provider use anthropic --model claude-opus-4-6
amplifier provider use azure-openai --deployment gpt-5.4

Note: We've done most of our early testing with Anthropic Claude. Other providers are supported but may have rough edges we're actively smoothing out.

Basic Usage

Interactive Chat Mode

# Start a conversation
amplifier

# Or explicitly
amplifier run --mode chat

In chat mode:

Context persists across messages
Use /help to see available commands
Use /tools, /agents, /status, /config to inspect session
Use /think and /do to toggle plan mode
Type exit or Ctrl+C to quit

Single Commands

# Get quick answers
amplifier run "Explain async/await in Python"

# Generate code
amplifier run "Create a REST API for a todo app with FastAPI"

# Debug issues
amplifier run "Why does this code throw a TypeError: [paste code]"

Using Bundles

Bundles are composable configuration packages that define tools, providers, agents, and behaviors:

# See current bundle (foundation is the default)
amplifier bundle current

# List available bundles
amplifier bundle list

# Use a specific bundle for one command
amplifier run --bundle recipes "Your prompt"

# Set as default
amplifier bundle use foundation

The foundation bundle is the default and includes:

Tools: filesystem, bash, web, search, task delegation
Agents: 14 specialized agents (zen-architect, bug-hunter, git-ops, web-research, explorer, etc.)
Behaviors: logging, redaction, streaming UI, todo tracking

Most users never need to change bundles—foundation provides everything for development work.

Working with Agents

Specialized agents for focused tasks:

# Let the AI delegate to specialized agents
amplifier run "Design a caching layer with careful consideration"
# The AI will use zen-architect when appropriate

# Or request specific agents
amplifier run "Use bug-hunter to debug this error: [paste error]"

Bundled agents:

zen-architect - System design with ruthless simplicity
bug-hunter - Systematic debugging
web-research - Web research and content fetching
modular-builder - Code implementation
explorer - Breadth-first exploration of local code, docs, and other files with citation-ready summaries

Sessions & Persistence

Every interaction is automatically saved:

# Resume most recent session
amplifier continue

# Resume with new prompt (single-shot mode)
amplifier continue "follow-up question"

# List your recent sessions (current project only)
amplifier session list

# See all sessions across all projects
amplifier session list --all-projects

# View session details
amplifier session show <session-id>

# Resume a specific session (interactive mode)
amplifier session resume <session-id>

# Resume specific session with new prompt
amplifier run --resume <session-id> "new question"

Sessions are project-scoped—when you're in /home/user/myapp, you see only myapp sessions. Change directories, see different sessions. Your work stays organized.

Configuration

Switching Providers

# Switch provider (interactive - prompts for model)
amplifier provider use openai

# Or explicit
amplifier provider use anthropic --model claude-opus-4-6

# Azure OpenAI (needs endpoint + deployment)
amplifier provider use azure-openai
  Azure endpoint: https://my-resource.openai.azure.com/
  Auth? [1] API key [2] Azure CLI: 2
  Deployment: gpt-5.4

# Configure where to save
amplifier provider use openai --model gpt-5.4 --local      # Just you
amplifier provider use anthropic --model claude-opus-4-6 --project  # Team

# See what's active
amplifier provider current

Switching Bundles

# See current bundle
amplifier bundle current

# Switch bundle
amplifier bundle use foundation
amplifier b

Amplifier

Install / Use

README

Amplifier

What is Amplifier?

Quick Start - Zero to Working in 90 Seconds

Step 1: Install UV (30 seconds)

Step 2: Install Amplifier (30 seconds)

Step 3: Run Amplifier (30 seconds)

Step 4: Add bundles (optional)

What Can Amplifier Do?

Supported AI Providers

Basic Usage

Interactive Chat Mode

Single Commands

Using Bundles

Working with Agents

Sessions & Persistence

Configuration

Switching Providers

Switching Bundles