Create your first agent
By the end of this section you’ll have a named agent answering your messages from the CLI, backed by the LLM provider of your choice.
The three steps
Stash an Anthropic or OpenAI key in the encrypted vault.
1. Store an LLM credentialOne command. Pick a model and a name.
2. Create the agenthiveloom chat <name> — a streaming REPL.
What you’ll have at the end
A tenant-local agent reachable over the CLI. The next section, Connect a chat client, exposes the same agent over MCP so Claude Desktop and Cursor can talk to it too.
Last updated on