brute

A framework-agnostic coding agent for Ruby. Rack-style middleware pipelines for agent turns, a full set of coding tools, and session persistence — bring your own LLM library.

Brute treats an agent turn the way Rack treats an HTTP request: an env hash flowing through a middleware stack toward a terminal app. The middleware handles the agentic machinery — the tool loop, session persistence, the system prompt, iteration guards. The terminal app is a proc you write with whatever LLM library you prefer (ruby_llm, llm.rb, the official openai or anthropic gems, or raw HTTP). Brute depends on none of them.

See the project documentation:

• Getting Started — install brute and build your first agent.
• The Agent Pipeline — Brute.agent, .use, .run, .start.
• Messages — the Brute::Message format.
• Message Transports — translate between Brute and any LLM library.
• Tools — four ways to define a tool; the built-in coding toolset.
• Middleware — the built-in turn middleware catalog.

require "brute"
require "ruby_llm"

agent = Brute.agent
  .use(Brute::Middleware::SessionLog, path: "tmp/session.jsonl")
  .use(Brute::Middleware::SystemPrompt)
  .use(Brute::Middleware::Loop::ToolResult)
  .use(Brute::Middleware::MaxIterations)
  .use(Brute::Middleware::ToolPipeline, tools: Brute::Tools::ALL)
  .run do |env|
    response = provider.complete(
      Brute::MessageTransport::RubyLLM.dump_all(env[:messages]),
      tools: rubyllm_tools(env[:tools]), model: model,
    )
    Brute::MessageTransport::RubyLLM.wrap_each(response) { |m| env[:messages] << m }
  end

agent.start("What files are in the current directory?")

The documentation site is a Just the Docs Jekyll project under docs/. Serve it locally:

docs/bin/serve.sh          # http://localhost:4000/brute/

• Examples directory — the same agent on four LLM libraries, plus sub-agents, sessions, and HTTP serving.

MIT