Skip to main content
The Agent Stack command-line interface (CLI) provides tools to manage agents, configure models, and control the platform directly from your terminal.

Basic Usage

agentstack [COMMAND] [OPTIONS] [ARGUMENTS]
To see all available commands:
agentstack --help

Agent Commands

list

List all available agents:
agentstack list
Shows agent names, statuses, descriptions, locations, and any configuration issues.

run

Run an agent with specified input:
agentstack run <agent-name> [input]
Examples:
# Interactive mode
agentstack run chat

# Direct input
agentstack run chat "Hello!"

# Input from file
agentstack run chat < input.txt

# Output to file
agentstack run chat "Summarize this" > output.txt

# Append to file
agentstack run chat "More analysis" >> output.txt

# Pipe between agents
agentstack run agent1 "input" | agentstack run agent2

info

Get detailed information about a specific agent:
agentstack info <agent-name>
Shows description, input/output schemas, examples, and configuration options.

add

Add an agent to your environment:
agentstack add <location>
Location formats:
# From Docker image
agentstack add ghcr.io/i-am-bee/agentstack/agents/chat:latest

# From GitHub repository
agentstack add "https://github.com/user/repo.git"

# From GitHub with version tag
agentstack add "https://github.com/user/[email protected]"

# From GitHub with specific path
agentstack add "https://github.com/user/repo.git#path=/agents/my-agent"

# From GitHub with specific dockerfile location within the repository
agentstack add --dockerfile /my-agent/Dockerfile "https://github.com/user/repo.git#path=/agents/my-agent"

remove

Remove an agent from your environment:
agentstack remove <agent-name>

update

Update an existing agent to a new version:
agentstack update <agent-name> <location>
Location formats:
# From Docker image
agentstack update my-agent ghcr.io/i-am-bee/agentstack/agents/chat:latest

# From GitHub repository
agentstack update my-agent "https://github.com/user/repo.git"

# From GitHub with version tag
agentstack update my-agent "https://github.com/user/[email protected]"

# From GitHub with specific path
agentstack update my-agent "https://github.com/user/repo.git#path=/agents/my-agent"

# From GitHub with specific dockerfile location within the repository
agentstack update my-agent --dockerfile /my-agent/Dockerfile "https://github.com/user/repo.git#path=/agents/my-agent"

logs

View and stream logs for an agent:
agentstack logs <agent-name>
Displays the agent’s log output and continues streaming new logs as they are generated.

build

Build an agent from a GitHub repository: This command clones the repository and builds the agent image on the platform. You will get an image ID which you can use to add the agent to your environment.
agentstack build <github-repository-url>
Examples:
# Build from GitHub repository
agentstack build https://github.com/org/repo.git

# Build specific version
agentstack build https://github.com/org/[email protected]

# Specify Dockerfile location (useful for monorepos)
agentstack build --dockerfile=./path/to/Dockerfile https://github.com/org/[email protected]

# Specify docker context location
agentstack build https://github.com/org/[email protected]#path=/path/to/context
Arguments:
  • github-repository-url: GitHub repository URL
Options:
  • --dockerfile <path>: Use custom dockerfile path

Client-side-build

Build an agent from a local directory. This is useful for CI/CD, multi-platform image build or local push of agent image to registry.
Requires Docker running
agentstack client-side-build [OPTIONS] <docker-context>
Examples:
# Build from current directory
agentstack client-side-build .

# Build with custom tag
agentstack client-side-build . --tag my-agent:latest

# Build without importing to platform
agentstack client-side-build . --no-import

# Build with custom dockerfile
agentstack client-side-build . --dockerfile ./custom.Dockerfile
Options:
OptionDescription
--dockerfile <path>Use a custom Dockerfile path. Path should be relative to the repo root or a subdirectory.
--tag <name>Docker tag for the agent
--multi-platformBuild for multiple platforms
--pushPush the image to the target registry
--import/--no-importImport the image into Agent Stack (default: true)

Model Commands

model setup

Interactive setup for LLM provider configuration:
agentstack model setup
Guides you through configuring your LLM provider with the required API keys and settings.

Platform Commands

start

Starts the platform:
agentstack platform start

stop

Stops the platform:
agentstack platform stop
Stops the platform but keeps all data intact.

delete

Deletes the platform and all data:
agentstack platform delete
This removes all agents, configurations, and data permanently.

MCP Commands

mcp

Manage MCP servers and toolkits:
agentstack mcp [subcommand]
Use agentstack mcp --help for available subcommands.

Server Commands

server

Manage Agent Stack servers and authentication:

login

Login to a server or switch between logged in servers:
agentstack server login

logout

Logout from a server:
agentstack server logout

show

Show current server information:
agentstack server show

list

List all configured servers:
agentstack server list

Environment Commands

env

Manage environment variables:
agentstack env [subcommand]
Use agentstack env --help for available subcommands.

System Commands

ui

Launch the web interface:
agentstack ui
Opens Agent Stack’s graphical interface in your default browser.

version

Display version information:
agentstack version

install

Install Agent Stack CLI and platform:
agentstack self install

upgrade

Upgrade Agent Stack CLI and platform to the latest version:
agentstack self upgrade

uninstall

Uninstall Agent Stack CLI and platform:
agentstack self uninstall
Removes the CLI, stops the platform, and deletes all data.

Global Options

Most commands support these options:
  • --help: Show help information for a command
  • -v, --verbose: Show verbose output
  • --debug: Enable debug output for troubleshooting (set via environment)