Are you the author? Sign in to claim
The CLI for the Claude API
ant is the official CLI for the Claude Platform. It puts the Claude API in your terminal — send messages, manage agents and sessions, upload files, and script against every API endpoint.
Full documentation is available at platform.claude.com/docs/en/api/sdks/cli.
@codeguilds-knight
brew install anthropics/tap/ant
To install from source, you need Go version 1.22 or later.
go install 'github.com/anthropics/anthropic-cli/cmd/ant@latest'
The binary is placed in $(go env GOPATH)/bin. If ant isn't found after installation, add that directory to your PATH:
# Add to your shell profile (.zshrc, .bashrc, etc.)
export PATH="$PATH:$(go env GOPATH)/bin"
Log in with your Claude Console account:
ant auth login
Or set the ANTHROPIC_API_KEY environment variable to an API key from the Claude Console.
Then send your first message:
ant messages create \
--model claude-opus-4-8 \
--max-tokens 1024 \
--message '{role: user, content: "Hello, Claude"}'
Structured flags accept relaxed JSON or YAML, so unquoted keys are fine.
The CLI follows a resource-based command structure, with nested resources separated by colons:
ant <resource>[:<subresource>] <command> [flags...]
# List available models
ant models list
# Browse a response in the interactive explorer (the default in a terminal)
ant models retrieve --model-id claude-opus-4-8
# Extract a single field from a response, jq-style
ant messages create \
--model claude-opus-4-8 \
--max-tokens 1024 \
--message '{role: user, content: "Hello, Claude"}' \
--transform content.0.text --raw-output
# Send a file using the @path syntax
ant messages create \
--model claude-opus-4-8 \
--max-tokens 1024 \
--message '{role: user, content: [
{type: image, source: {type: base64, media_type: image/jpeg, data: "@photo.jpg"}},
{type: text, text: "What is in this image?"}
]}'
# Manage beta resources such as agents, sessions, and files
ant beta:agents list
Run ant --help for the full list of resources, or append --help to any command to see its flags.
macOS, Linux, or Windows.
See CONTRIBUTING.md.
This project is licensed under the MIT License. See the LICENSE file for details.
1000+ skills curated from Anthropic, Vercel, Stripe, and other engineering teams
Design enforcement with memory — keeps your UI consistent across a project
Detects 37 AI writing patterns and rewrites text with human rhythm across 5 voice profiles
WCAG accessibility audit — automated scanning, manual review, remediation