Deep Agents CLI

Documentation Index

Fetch the complete documentation index at: https://docs.langchain.com/llms.txt

Use this file to discover all available pages before exploring further.

​

Quickstart

Install and launch

OpenAI, Anthropic, and Google are installed by default. Other providers (Ollama, Groq, xAI, etc.) are available as optional extras—see Providers for details.

Script

Optional extras

uv

curl -LsSf https://langch.in/gh-da-cli | bash

deepagents

Add provider credentials

The CLI works with any LLM that supports tool calling. Use the /auth command to set an API key for your chosen providers — see Provider credentials for the full flow and storage details.For additional providers and headless runs, see Providers.

Give the agent a task

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

The agent interprets the query and proposes changes with diffs for your approval before modifying files. If needed, it can run shell commands to test the code, check documentation, or search the web for up-to-date information.

Enable tracing (optional)

To log agent operations, tool calls, and decisions in LangSmith, add the following to ~/.deepagents/.env or export the variables in your shell:

~/.deepagents/.env

LANGSMITH_TRACING=true
LANGSMITH_API_KEY=lsv2_...
LANGSMITH_PROJECT=optional-project-name  # Specify a project name or default to "deepagents-cli"

For more details and usage, see Trace with LangSmith.

​

Capabilities

• File operations - read, write, and edit files with tools that enable agents to manage and modify code and documentation.
• Shell execution - execute commands to run tests, build projects, manage dependencies, and interact with version control.
• Remote sandboxes - run agent tools in LangSmith, Daytona, Modal, Runloop, or AgentCore instead of your local machine. The linked page covers provider installation, credentials, sandbox flags (--sandbox, --sandbox-id, --sandbox-setup), and setup scripts.
• 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.
• Subagents - delegate work with the task tool. In the CLI, define custom subagents as AGENTS.md files; the linked page covers paths, frontmatter, and examples.
• Memory storage and retrieval - store and retrieve information across sessions, enabling agents to remember project conventions and learned patterns.
• Context compaction & offloading - summarize older conversation messages and offload originals to storage, freeing context window space during long sessions.
• Human-in-the-loop - require human approval for sensitive tool operations.
• Skills - extend agent capabilities with custom expertise and instructions.
• MCP tools - load external tools from Model Context Protocol servers.
• Tracing - trace agent operations in LangSmith for observability and debugging.

deepagents -y
# or
deepagents --auto-approve

​

Command reference

# Use a specific agent configuration
deepagents --agent mybot

# Use a specific model (provider:model format or auto-detect)
deepagents --model anthropic:claude-opus-4-7
deepagents --model gpt-5.5

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

# list directory contents, then summarize directory as first prompt — the command runs first, then the prompt is submitted
# the prompt does NOT have access to the command output
deepagents --startup-cmd "ls -la" -m "Summarize what's in this directory"

# Non-interactive with startup command: show git status before the task runs
# the task does NOT have access to the command output
deepagents --startup-cmd "git diff --stat" -n "Review these changes"

​

Configuration

# List all configured agents
deepagents agents list

​

Interactive mode

git status
npm test
ls -la

​

Non-interactive mode and piping

deepagents -n "Write a Python script that prints hello world"

echo "Explain this code" | deepagents
cat error.log | deepagents -n "What's causing this error?"
git diff | deepagents -n "Review these changes"
git diff | deepagents --skill code-review -n 'summarize changes'

deepagents -n "fix the failing tests" --max-turns 10

deepagents -n "Generate a .gitignore for Python" -q > .gitignore
deepagents -n "List dependencies" -q --no-stream | sort

# Allow specific commands (validated against the list)
deepagents -n "Run the tests and fix failures" -S "pytest,git,make"

# Use the curated safe-command list
deepagents -n "Build the project" -S recommended

# Allow any shell command
deepagents -n "Fix the build" -S all

​

Trace with LangSmith

LANGSMITH_TRACING=true
LANGSMITH_API_KEY=lsv2_...
LANGSMITH_PROJECT=optional-project-name  # Specify a project name or default to "deepagents-cli"

export LANGSMITH_TRACING=false

DEEPAGENTS_CLI_LANGSMITH_PROJECT=my-deep-agent-execution

LANGSMITH_PROJECT=my-app-traces

✓ LangSmith tracing: 'my-project'