Deep Agents provides a number of configuration options to customize the agent’s behavior and capabilities:
  • Tools (required): The tools that the agent and any subagents will have access to.
  • Instructions (required): Custom instructions that serve as part of the agent’s prompt. This supplements the built-in system prompt.
  • Sub-agents: Specialized subagents for specific tasks.
  • Model: The model to use for the agent.

​
Tools

Required. A list of tools that the agent and any subagents will have access to.

​
Instructions

Required. Custom instructions that serve as part of the agent’s prompt. This supplements the built-in system prompt.

​
Sub-agents

Define specialized subagents for specific tasks: 
subagents = [{
    "name": "research-agent",
    "description": "Used to research more in depth questions",
    "prompt": sub_research_prompt,
    "tools": ["internet_search"]  # Optional: defaults to all tools
}]

agent = create_deep_agent(
    tools=tools,
    instructions=prompt,
    subagents=subagents
)

​
Model

Both the Python and JavaScript implementations default to "claude-sonnet-4-20250514" but support custom models: 
from langchain_openai import ChatOpenAI

custom_model = ChatOpenAI(model="gpt-4")
agent = create_deep_agent(
    tools=tools,
    instructions=instructions,
    model=custom_model
)

​
Custom models

Custom models are only supported in the Python implementation.
By default, deepagents uses "claude-sonnet-4-20250514". You can customize this by passing any LangChain model object. For example, use OpenAI’s gpt-oss model via Ollama: 
# pip install langchain langchain-ollama

from deepagents import create_deep_agent

# ... existing agent definitions ...

model = init_chat_model(
    model="ollama:gpt-oss:20b",  
)
agent = create_deep_agent(
    tools=tools,
    instructions=instructions,
    model=model,
    ...
)