Omakase 0.2 — agents as plain Ruby objects

The useful part

I released Omakase 0.2, a small agent framework on top of RubyLLM about 800 lines. The idea is that an agent is an ordinary Ruby object: its fields are state, its public methods are what the model can call (no tool registry, no JSON schemas to keep in sync. describe above a method is the description the model reads), and the methods you declare without a body are written by the model at runtime.

How it works

• There's also:predict for one-shot structured output, MCP servers and SKILL.md directories that arrive as methods, per-method model selection, attachments, and a FakeChat so agents can be tested without a...
• and are blunt about the fact that generated code runs with instance_eval, so untrusted input belongs to:predict unless you swap in your own executor.
• under the default:code_act strategy the model answers by writing Ruby that is evaluated on the agent itself and calling finish(value), so the answer is computed rather than retyped as JSON.