Claude Platform Ships the 'ant' CLI for Running Managed Agent Workers From the Terminal

Anthropic's Claude Platform documents an ant command-line tool that runs a self-hosted Managed Agents worker straight from the terminal. The CLI polls a work queue, downloads the agent's skills, executes tool calls on infrastructure you control, and posts results back to Anthropic's control plane (Claude Platform docs).

The launch was surfaced via a ClaudeDevs announcement on June 2, 2026 (ClaudeDevs). The durable details below come from the official Claude Platform documentation, which is the source of truth for what the CLI actually does.

What the 'ant' CLI Is

The ant CLI is a terminal binary that ships a pre-built worker for Claude Managed Agents running in a self_hosted environment. Managed Agents is Anthropic's pre-built agent harness for long-running, asynchronous work; the self_hosted environment moves tool execution onto your own infrastructure while orchestration stays on Anthropic's side (self-hosted sandboxes).

In that setup, the self_hosted environment acts as a work queue. When a session is assigned to it, Anthropic enqueues the session as a work item. A worker -- run by the ant CLI or an Anthropic SDK -- claims items from the queue, spawns an execution context, downloads the agent's skills, runs the tool calls, and posts the results back (self-hosted sandboxes).

What You Can Run From the Terminal

The documentation shows ant commands across the Managed Agents lifecycle, not a generic wrapper over the full Claude API. The commands that appear in the official docs include:

Anthropic notes the ant CLI supports the always-on polling pattern only; the SDK additionally supports a webhook-triggered handler (self-hosted sandboxes).

Installing and Running the Worker

The docs install ant from the anthropic-cli GitHub releases (version 1.10.0 in the documented example) onto a Linux host with /bin/bash, then run the worker against an environment (self-hosted sandboxes).

VERSION=1.10.0
OS=$(uname -s | tr '[:upper:]' '[:lower:]')
ARCH=$(uname -m | sed -e 's/x86_64/amd64/' -e 's/aarch64/arm64/')
curl -fsSL "https://github.com/anthropics/anthropic-cli/releases/download/v${VERSION}/ant_${VERSION}_${OS}_${ARCH}.tar.gz" \
  | sudo tar -xz -C /usr/local/bin ant

ant beta:worker poll --workdir "/workspace"

The worker authenticates to its queue with an environment key (ANTHROPIC_ENVIRONMENT_KEY) and targets an environment ID (ANTHROPIC_ENVIRONMENT_ID); your separate Claude API key is used from outside the worker host to create sessions and read queue stats (self-hosted sandboxes).

Worker Flags

The reference documents the flags for ant beta:worker that control where work runs and how the process behaves (Managed Agents reference):

Why It Matters

For teams that need agent tool execution to stay inside their security perimeter, the ant CLI is the lowest-friction way to stand up a self-hosted worker: a single long-running process that needs only outbound HTTPS, no inbound firewall rules, and no custom agent loop. It pairs with the broader self-hosted-sandbox push Anthropic shipped in May 2026 (self-hosted sandboxes and MCP tunnels).

Choose the ant CLI when you want the simplest always-on worker and don't need webhook-triggered handling. Reach for an Anthropic SDK (Python, TypeScript, or Go) when you need the webhook-triggered pattern or finer control over per-session sandboxing (self-hosted sandboxes).

Availability

The CLI's commands live under the beta: namespace, and every Managed Agents request requires the managed-agents-2026-04-01 beta header, so the capability is in beta, not general availability (Managed Agents overview). This is a worker CLI for Managed Agents specifically; the docs do not position ant as a general-purpose command-line client for the full Messages API.

Sources

• ClaudeDevs announcement post (June 2, 2026): https://x.com/ClaudeDevs/status/2061877343078244459
• Claude Platform docs, "Self-hosted sandboxes": https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes
• Claude Platform docs, "Reference" (self-hosted worker CLI flags): https://platform.claude.com/docs/en/managed-agents/reference
• Claude Platform docs, "Claude Managed Agents overview": https://platform.claude.com/docs/en/managed-agents/overview