Claude's ant CLI gains `ant apply` for declarative agent infrastructure
- Source
- x.com
- Date
We've added `ant apply` to the ant CLI. Now you can declare Claude Managed Agent environments, agents, skills, memory stores, and deployments as files in your repository and keep the API's resources in sync with them using `ant apply`. Docs: https://t.co/qQchmDjTmm
Context
Anthropic's developer team, posting as ClaudeDevs, added `ant apply` to its `ant` command-line tool. According to Anthropic's own documentation, a Claude Managed , its environment, its skills, and its memory stores can each be written as a file, typically Markdown with configuration in the frontmatter, and `ant apply` then creates or updates the matching resources through the Claude API in dependency order.
Files can reference each other by relative path instead of an API-assigned ID, and a generated lock file tracks the resulting resource for every file in the project, a structure similar in shape to infrastructure-as-code tools built for cloud servers. The command requires CLI version 1.30.0 or later.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Checking sign-in…
Loading comments…