Composer

Define your entire agent team in a single YAML file. The Composer parses the spec and builds a live agent tree — no Python wiring needed.

pip install langchain-adk[composer]

Quick Start

compose.yaml

defaults:
  model:
    provider: anthropic
    name: claude-opus-4-6

agents:
  assistant:
    type: llm
    instructions: You are a helpful assistant.

main_agent: assistant

from langchain_adk.composer import Composer

agent = Composer.from_yaml("compose.yaml")

async for event in agent.astream("Hello!"):
    if event.is_final_response():
        print(event.text)

Architecture

The Composer is built around three modular registries under builders/:

composer/
├── __init__.py              # Public API: Composer, register_*
├── composer.py              # Orchestrates YAML → agent tree
├── errors.py                # ComposerError, CircularReferenceError
├── schema.py                # Pydantic models for YAML validation
└── builders/
    ├── agents/              # Agent builder registry
    │   ├── __init__.py      # register(), get(), Helpers
    │   ├── _common.py       # Shared LLM-agent builder logic
    │   ├── llm.py           # LlmAgent builder
    │   ├── react.py         # ReActAgent builder
    │   ├── sequential.py    # SequentialAgent builder
    │   ├── parallel.py      # ParallelAgent builder
    │   ├── loop.py          # LoopAgent builder
    │   └── a2a.py           # A2AAgent builder
    ├── models/              # Model provider registry
    │   └── __init__.py      # register(), create()
    └── tools/               # Tool builtin registry + resolvers
        └── __init__.py      # register_builtin(), resolve_*()

Each registry is independently extensible — register a custom agent type, model provider, or builtin tool without touching any other code.

YAML Schema

`defaults`

Global settings inherited by all agents.

defaults:
  model:
    provider: anthropic    # openai | anthropic | google | dotted.import.path
    name: claude-opus-4-6
    temperature: 0.7       # optional
  max_iterations: 10

`models`

Named model configurations. Agents reference them by name instead of repeating inline config.

models:
  fast:
    provider: openai
    name: gpt-4o-mini
    temperature: 0.0
  smart:
    provider: anthropic
    name: claude-opus-4-6
    max_tokens: 8192
    api_key: "sk-ant-..."
  local:
    provider: "myapp.models.OllamaChat"  # dotted import path
    name: llama3
    base_url: "http://localhost:11434"

Any key beyond provider, name, and temperature is forwarded directly to the LangChain model constructor (e.g. max_tokens, api_key, base_url, timeout, etc.). Agents reference models by name:

agents:
  researcher:
    type: llm
    model: smart             # reference to models section
  summarizer:
    type: llm
    model: fast              # different model for different agent

Or use inline model: for one-off overrides:

agents:
  bot:
    type: llm
    model:
      provider: openai
      name: gpt-4o
      max_tokens: 4096

`tools`

Named tool definitions referenced by agents.

tools:
  # Python function by import path
  search:
    function: "myapp.tools.search_web"

  # MCP server
  weather:
    mcp:
      url: "http://localhost:8001/mcp"

  # Built-in tool
  exit:
    builtin: exit_loop

  # Agent as tool (AgentTool)
  researcher:
    agent: ResearchAgent

`skills`

Named skill definitions, referenced by agents. Each agent that lists skills gets its own in-memory skill store with list_skills and load_skill tools. Skills can be defined inline or loaded from a FastMCP server.

skills:
  # Inline skill (content defined directly)
  summarize:
    name: summarize
    description: "Summarize text into bullet points."
    content: "Extract 3-5 key points. Be concise."

  # Remote skill (loaded from FastMCP server at build time)
  pdf_processing:
    name: pdf-processing
    description: "Process and extract data from PDFs."
    mcp:
      url: "http://localhost:8001/mcp"

  # Remote skill (in-memory FastMCP server)
  coding_standards:
    name: coding-standards
    description: "Team coding standards."
    mcp:
      server: "myapp.skills.server"  # dotted import path

Agents reference skills by name:

agents:
  triage:
    type: llm
    instructions: "Route to the right specialist."
    skills:
      - summarize
      - pdf_processing

`agents`

Flat dict of agent definitions. Agents reference each other by name.

agents:
  MyAgent:
    type: llm              # llm | react | sequential | parallel | loop | a2a
    description: "..."
    instructions: |
      System prompt goes here.
    model: smart            # reference to models section, or inline:
    # model:
    #   provider: anthropic
    #   name: claude-sonnet-4-6
    #   max_tokens: 4096
    tools:
      - search             # named reference
      - builtin: exit_loop # inline definition
      - agent: OtherAgent  # inline AgentTool
      - transfer:          # transfer routing
          targets: [A, B]
    skills:
      - summarize          # named reference to skills section
    planner:
      type: task            # plan_react | task
      tasks:
        - title: "Research"
    max_iterations: 10

Agent Types

Type	Description	Required fields
`llm`	LLM-powered agent with tool loop	`instructions`
`react`	Structured Reason+Act agent	`instructions` (optional)
`sequential`	Run sub-agents in order	`agents`
`parallel`	Run sub-agents concurrently	`agents`
`loop`	Repeat sub-agents until done	`agents`, `max_iterations`
`a2a`	Remote agent via A2A protocol	`url`

`main_agent`

The entry-point agent name.

main_agent: MyAgent

`runner`

Optional. Enables Composer.runner_from_yaml().

runner:
  app_name: my-app
  session_service: memory  # or dotted.import.path

`server`

Optional. Enables Composer.server_from_yaml() for A2A.

server:
  app_name: my-app
  version: "1.0.0"
  url: "http://localhost:8000"
  skills:
    - id: general
      name: General
      description: "General assistant."

Examples

Transfer Routing

agents:
  sales:
    type: llm
    description: "Order inquiries."
    tools: [lookup_order]
  support:
    type: llm
    description: "Technical help."
    tools: [search_docs]
  triage:
    type: llm
    instructions: "Route to the right specialist."
    tools:
      - transfer:
          targets: [sales, support]

main_agent: triage

Sequential Pipeline

agents:
  researcher:
    type: llm
    instructions: "Research the topic."
    tools: [search]
  writer:
    type: llm
    instructions: "Write an article from research."
  pipeline:
    type: sequential
    agents: [researcher, writer]

main_agent: pipeline

Loop with Exit

agents:
  writer:
    type: llm
    instructions: "Write a draft."
  reviewer:
    type: llm
    instructions: "Review. Call exit_loop if approved."
    tools:
      - builtin: exit_loop
  loop:
    type: loop
    agents: [writer, reviewer]
    max_iterations: 5

main_agent: loop

Extending with Registries

Custom Agent Types

from langchain_adk.composer import register_builder


async def build_custom(name, agent_def, spec, *, helpers):
    model_cfg = helpers.resolve_model(agent_def)
    tools = await helpers.resolve_tools(agent_def)
    return MyCustomAgent(name=name, tools=tools)

register_builder("custom", build_custom)

Then in YAML:

agents:
  my_agent:
    type: custom

The build function receives (name, agent_def, spec, *, helpers) where helpers provides:

helpers.resolve_model(agent_def) — merge agent/default model config
helpers.resolve_tools(agent_def) — resolve all tool references
helpers.build_agent(name) — recursively build a sub-agent by name

Custom Model Providers

from langchain_adk.composer import register_provider

register_provider("my_llm", MyCustomChatModel)

Built-in providers: openai, anthropic, google. Any unrecognized provider string is treated as a dotted import path to a custom BaseChatModel class.

Custom Builtin Tools

from langchain_adk.composer import register_builtin_tool

register_builtin_tool("my_tool", lambda: my_tool_instance)

Then reference it in YAML:

tools:
  my_tool:
    builtin: my_tool

Python API

Method	Returns	Description
`Composer.from_yaml(path)`	`BaseAgent`	Build root agent (sync)
`Composer.from_yaml_async(path)`	`BaseAgent`	Build root agent (async)
`Composer.runner_from_yaml(path)`	`Runner`	Build Runner with sessions
`Composer.runner_from_yaml_async(path)`	`Runner`	Build Runner with sessions (async)
`Composer.server_from_yaml(path)`	`FastAPI`	Build A2A server app
`Composer.server_from_yaml_async(path)`	`FastAPI`	Build A2A server app (async)

Registry function	Description
`register_builder(type, fn)`	Add a custom agent type builder
`register_provider(name, cls)`	Add a custom model provider
`register_builtin_tool(name, factory)`	Add a custom builtin tool

Getting Started

Core Concepts

Tools

Orchestration

Runtime

Integrations

Composer

Quick Start

Architecture

YAML Schema

`defaults`

`models`

`tools`

`skills`

`agents`

Agent Types

`main_agent`

`runner`

`server`

Examples

Transfer Routing

Sequential Pipeline

Loop with Exit

Extending with Registries

Custom Agent Types

Custom Model Providers

Custom Builtin Tools

Python API

Getting Started

Core Concepts

Tools

Orchestration

Runtime

Composer

Integrations

​Quick Start

​Architecture

​YAML Schema

​defaults

​models

​tools

​skills

​agents

​Agent Types

​main_agent

​runner

​server

​Examples

​Transfer Routing

​Sequential Pipeline

​Loop with Exit

​Extending with Registries

​Custom Agent Types

​Custom Model Providers

​Custom Builtin Tools

​Python API

Quick Start

Architecture

YAML Schema

`defaults`

`models`

`tools`

`skills`

`agents`

Agent Types

`main_agent`

`runner`

`server`

Examples

Transfer Routing

Sequential Pipeline

Loop with Exit

Extending with Registries

Custom Agent Types

Custom Model Providers

Custom Builtin Tools

Python API