Deep Agents CLI

• File operations - read, write, and edit files in your project with tools that enable agents to manage and modify code and documentation.
• Shell command execution - execute shell commands to run tests, build projects, manage dependencies, and interact with version control systems.
• Web search - search the web for up-to-date information and documentation (requires Tavily API key).
• HTTP requests - make HTTP requests to APIs and external services for data fetching and integration tasks.
• Task planning and tracking - break down complex tasks into discrete steps and track progress through the built-in todo system.
• Memory storage and retrieval - store and retrieve information across sessions, enabling agents to remember project conventions and learned patterns.
• Human-in-the-loop - require human approval for sensitive tool operations.
• Skills - extend agent capabilities with custom expertise and instructions stored in skill directories.

deepagents --auto-approve

​

Quickstart

export OPENAI_API_KEY="your-api-key"

OPENAI_API_KEY=your-api-key

export ANTHROPIC_API_KEY="your-api-key"

ANTHROPIC_API_KEY=your-api-key

export GOOGLE_API_KEY="your-api-key"

GOOGLE_API_KEY=your-api-key

uv tool install deepagents-cli
deepagents

> Create a Python script that prints "Hello, World!"

pip install deepagents-cli

deepagents --model claude-opus-4-5-20251101

export TAVILY_API_KEY="your-key"

​

Tracing with LangSmith

1. Enable LangSmith tracing:
   Copy

   export LANGCHAIN_TRACING=true
   export LANGCHAIN_API_KEY="your-api-key"
   
2. Configure agent tracing for deep agent operations such as tool calls and agent decisions:
   Copy

   export DEEPAGENTS_LANGSMITH_PROJECT="my-deep-agent-execution"
   
3. If you are building a LangChain app with deep agents, and want to separate agent traces from your app’s traces, also configure LANGSMITH_PROJECT:
   Copy

   export LANGSMITH_PROJECT="my-app-calls-to-langchain"
   

✓ LangSmith tracing: 'my-project'

​

Configuration

# List all configured agents
deepagents list

# Use a specific agent configuration
deepagents --agent mybot

# Use a specific model (auto-detects provider)
deepagents --model claude-sonnet-4-5-20250929
deepagents --model gpt-4o

# Auto-approve tool usage (skip human-in-the-loop prompts)
deepagents --auto-approve

# Execute code in a remote sandbox
deepagents --sandbox modal        # or runloop, daytona
deepagents --sandbox-id dbx_123   # reuse existing sandbox

​

Interactive mode

!git status
!npm test
!ls -la

​

Teach your agent project conventions

1. Research: Searches memory for relevant context before starting tasks
2. Response: Checks memory when uncertain during execution
3. Learning: Automatically saves new information for future sessions

~/.deepagents/backend-dev/memories/
├── api-conventions.md
├── database-schema.md
└── deployment-process.md

uvx deepagents-cli --agent backend-dev
> Our API uses snake_case and includes created_at/updated_at timestamps

> Create a /users endpoint
# Applies conventions without prompting

​

Customize your deep agent

• Memory: Global and project-specific AGENTS.md files which are loaded in full at session start. Use memory for general coding style and preferences.
• Skills: Global and project-specific context, conventions, guidelines, or instructions. Use skills for context that is only required when performing specific tasks.

​

Provide project or user context

​

Use remote sandboxes

• Safety: Protect your local machine from potentially harmful code execution
• Clean environments: Use specific dependencies or OS configurations without local setup
• Parallel execution: Run multiple agents simultaneously in isolated environments
• Long-running tasks: Execute time-intensive operations without blocking your machine
• Reproducibility: Ensure consistent execution environments across teams

1. Configure your sandbox provider (Runloop, Daytona, or Modal):
   Copy

   # Runloop
   export RUNLOOP_API_KEY="your-key"
   
   # Daytona
   export DAYTONA_API_KEY="your-key"
   
   # Modal
   modal setup
   
2. Run the CLI with a sandbox:
   Copy

   uvx deepagents-cli --sandbox runloop --sandbox-setup ./setup.sh
   
   The agent runs locally but executes all code operations in the remote sandbox. Optional setup scripts can configure environment variables, clone repositories, and prepare dependencies.
3. (Optional) Create a setup.sh file to configure your sandbox environment:
   Copy

   #!/bin/bash
   set -e
   
   # Clone repository using GitHub token
   git clone https://x-access-token:${GITHUB_TOKEN}@github.com/username/repo.git $HOME/workspace
   cd $HOME/workspace
   
   # Make environment variables persistent
   cat >> ~/.bashrc <<'EOF'
   export GITHUB_TOKEN="${GITHUB_TOKEN}"
   export OPENAI_API_KEY="${OPENAI_API_KEY}"
   cd $HOME/workspace
   EOF
   
   source ~/.bashrc
   
   Store secrets in a local .env file for the setup script to access.

​

Use skills

​

Add skills

1. Start by creating a skill:
   • User skill
   • Project skill

   Copy

   deepagents skills create test-skill
   

   This will generate the correct the following files in your ~/.deepagents/<agent_name> folder:

   Copy

   deepagents skills create test-skill --project
   

   This will generate the correct the following files in your ~/{project}/.deepagents/skills folder:
   Copy

   skills/
   └── test-skill
       └── SKILL.md
   
2. Open the generated SKILL.md and edit the file to include your instructions.
3. Optionally add additional scripts or other resources to the test-skill folder. For more information, see Examples.

mkdir -p ~/.deepagents/<agent_name>/skills
cp -r examples/skills/web-research ~/.deepagents/<agent_name>/skills/

​

List skills

deepagents skills list

deepagents skills list --project

deepagents skills info test-skill

deepagents skills info test-skill --project