Anthropic adds ant apply to CLI: declare Claude agents and resources as code
ClaudeDevs · x · 2026-09-04
Anthropic has added ant apply to its ant CLI, enabling infrastructure-as-code style management for Claude Platform resources.
- Environments, agents, skills, memory stores, and deployments can be declared as files in your repo and synced with the API
- Agents are defined in Markdown: frontmatter holds config (model, tools), the body is the system prompt, and file paths infer resource types
- Each run prints a plan for approval, then writes claude-lock. so subsequent applies update existing resources instead of creating duplicates
- Agent config changes go through the same review process as code, bringing versioning and auditability to agent deployments
More from coding & agent
- GPT-6 built a full macOS simulator in under 75 minutes, stunning the panel — thursdai_pod · 2026-09-04
- Matt Shumer reviews GPT-6 Astra: first model he trusts to run his inbox and business — mattshumer_ · 2026-09-04
- Agent refused orders for 40 minutes after mistaking Anthropic's hidden tag for prompt injection — Grimmoner · 2026-09-04
- Tardigrade: an open-source framework building agent harnesses as components over an immutable event log — viksit · 2026-09-04
- Keeping an always-on AI agent: clone a second MacBook via Migration Assistant + codex remote — hudzah · 2026-09-04
- Using Linear as a shared state layer for specialist AI agents — ChenBuilds · 2026-09-04