A r.uby.dev project.

Welcome to the canonical llm.rb repository.

llm.rb is an advanced runtime for building agentic AI applications on CRuby. It has zero runtime dependencies by default, it supports concurrent and parallel tool execution and has a single coherent API that spans 13+ providers. Streaming, tools, guards, compaction, the REPL, builtin MCP/A2A support and the database integrations all build on the same three concepts: providers, contexts, and agents.

Once you learn the fundamentals, everything else falls into place naturally. Some features, such as ActiveRecord support, require optional dependencies that are opt-in.

Install

gem install llm.rb

Quick start

Agents

The LLM::Agent class is the default high-level interface, and it is recommended for most use-cases. It manages tool execution automatically and guards against infinite loops, manages conversation state, and much more.

require "llm"

llm = LLM.deepseek(key: ENV["KEY"])
agent = LLM::Agent.new(llm, stream: $stdout)
agent.talk "hello world"

Stream

Streams can be simple IO objects or subclasses of LLM::Stream with structured callbacks for content, reasoning, tool calls, tool returns, and compaction. Streams can also observe message transformers, which rewrite outgoing messages before they reach the provider.

See the deepdive.md to learn more.

class MyStream < LLM::Stream
  # Visible assistant output.
  def on_content(content)
    print content
  end

  # Reasoning output streamed separately from visible content.
  def on_reasoning_content(content)
    warn content
  end

  # A streamed tool call has been fully parsed.
  def on_tool_call(tool)
  end

  # Queued streamed tool work has returned.
  def on_tool_return(tool, result)
  end

  # Before a transformer rewrites an outgoing message.
  def on_transform(transformer)
  end

  # Aftter a transformer rewrites an outgoing message.
  def on_transform_finish(transformer)
  end

  # Before a compactor trims the conversation.
  def on_compaction(compactor)
  end

  # After a compactor trims the conversation.
  def on_compaction_finish(compactor)
  end

  # Before a skill's subagent runs.
  def on_skill_call(skill)
  end

  # After a skill's subagent runs.
  # The subagent that ran it, the skill, and its response are passed
  # through, so you can introspect the agent, tally skill usage, or
  # track costs.
  def on_skill_return(agent, skill, result)
  end

  # A request was rate limited and will be retried.
  def on_rate_limit(error)
  end
end

llm = LLM.deepseek(key: ENV["KEY"])
agent = LLM::Agent.new(llm, stream: MyStream.new)
agent.talk "Explain Ruby fibers."

Tools

Subclasses of LLM::Tool are plain Ruby classes with an optional set of typed parameters.
The model can choose to call them on your behalf, and they're one of the most powerful features for extending the feature set or abilities of a model.

The runtime also ships with a catalog of built-in tools for filesystem, search, and shell operations.
See the deepdive.md to learn more.

class ReadFile < LLM::Tool
  name "read-file"
  description "Read a file"
  parameter :path, String, "The filename or path"
  required %i[path]

  def call(path:)
    {contents: File.read(path)}
  end
end

llm = LLM.deepseek(key: ENV["KEY"])
agent = LLM::Agent.new(llm, tools: [ReadFile], stream: $stdout)
agent.talk "summarize README.md"

Skills

A skill turns a markdown file into a callable tool. When the model calls it, the runtime spawns a subagent with the skill's instructions as its system prompt and the skill's own tool set. The subagent runs one turn and returns the result, then is discarded. Each call is fresh and stateless.

A LLM::Stream can be notified as a skill starts and when it returns. The on_skill_return callback hands back the subagent that ran the skill, so you can inspect its conversation, measure its usage, track costs or add a verification step (eg subagent.talk("verify your work")).

See the deepdive.md to learn more.

summary.md

---
name: summary
description: Reads recent git history and writes a summary
tools: all
---

Collect the recent git log, analyze each commit,
and write a summary to summary.txt.

agent.rb

require "llm"

llm   = LLM.deepseek(key: ENV["KEY"])
agent = LLM::Agent.new(llm, skills: ["summary.md"])
agent.talk "Summarize the last week of work"

Concurrency

The runtime supports six different concurrency strategies that have different attributes. The choice between all of them often depends on the requirements of your application.

IO-bound tools are a good fit for the :async, :thread, and :fiber strategies while true parallelism can be achieved with the :fork and :ractor strategies. The :sequential strategy runs tools one at a time and is the default. The :fork strategy also provides a separate process that offers isolation from its parent.

See the deepdive.md to learn more.

require "llm"
require "llm/tools"

llm   = LLM.deepseek(key: ENV["KEY"])
tools = LLM::Tool.subclasses
agent = LLM::Agent.new(llm, tools:, concurrency: :fork)
agent.talk "Run the tools in parallel"

Cancellation

Abort a request mid-stream and interrupt any running tools with LLM::Agent#interrupt! (or cancel!), from any thread. The runtime raises LLM::Interrupt on the caller and on every active tool. A forked tool gets interrupted over the control channel, a ractor via message passing, and pending tools are stopped before they run. The in-flight HTTP request is closed too, so a turn you no longer want stops without burning tokens.

See the deepdive.md to learn more.

llm = LLM.deepseek(key: ENV["KEY"])
agent = LLM::Agent.new(llm)
Thread.new { sleep(1); agent.cancel! }

begin
  agent.talk "write a very long poem", stream: $stdout
rescue LLM::Interrupt
  puts "cancelled"
end

Console (binding.pry for agents)

The LLM::Agent#repl method drops you into a highly capable read-eval-print loop (REPL) that is built on top of curses. It can help you debug agents, test your tools, connect to MCP servers, and even A2A agents. The REPL stands out because it connects to the surrounding runtime and it can be extended by your code. Think of it as binding.pry but for agents.

See the deepdive.md to learn more.

Demo

Watch in high quality on asciinema

Installation

The REPL is distributed with llm.rb so you don't have to install a separate gem but it requires a number of optional dependencies to be installed separately. The following gems provide the full experience:

gem install curses kramdown xchan.rb test-cmd.rb

Persistence

The path: option can be set on an agent for automatic persistence across REPL sessions. The tools: option attaches extra tools for the duration of the session. Recall previous turns with Ctrl+P and Ctrl+N.

require "llm"
require "llm/tools"

llm = LLM.deepseek(key: ENV["KEY"])
agent = LLM::Agent.new(llm, name: "my-agent", path: "agent.json")
agent.repl(tools: LLM::Tool.subclasses)

CLI

The llm.rb executable is available on your PATH after installation. It starts a REPL session from any directory.The CLI auto-detects your provider from standard environment variables (DEEPSEEK_API_KEY, OPENAI_API_KEY, ANTHROPIC_API_KEY, etc.). Persistent sessions are stored under ~/.llm.rb/ and restored automatically on your next visit.

llm.rb                     # auto-detect from $DEEPSEEK_API_KEY
llm.rb -p openai           # use OpenAI explicitly
llm.rb -t                  # temporary session, no persistence

Persistence

Set path: on an agent for automatic filesystem persistence: the agent restores conversation history from the file on startup and saves it back after every turn, with no manual serialization code. For database-backed persistence, ActiveRecord and Sequel integrations are also available. All persistence options use the same underlying serialization.

See the deepdive.md to learn more.

require "llm"

llm = LLM.deepseek(key: ENV["KEY"])
agent = LLM::Agent.new(llm, path: "session.json")
agent.talk "remember my name is robert"

# Next time, the conversation is restored automatically:
agent = LLM::Agent.new(llm, path: "session.json")
agent.talk "what's my name?"

ActiveRecord | Sequel

Because both LLM::Context and LLM::Agent can be serialized to JSON and stored in a simple string, both ActiveRecord and Sequel support can be implemented within a single column on a single row.

The runtime includes first-class support for both ActiveRecord / Sequel, and for both Rack-based / Rails-based applications. On databases where it is supported, such as PostgreSQL, the column can be optimized by using the jsonb type.

See the deepdive.md to learn more.

require "active_record"
require "llm"
require "llm/active_record"

class Email < ApplicationRecord
  acts_as_agent do |agent|
    agent.set name: "mail",
              instructions: "Write concise, friendly replies to emails",
              model: "deepseek-v4-pro"
  end

  def draft_reply!
    talk("Draft a reply to:\n\n#{body}")
  end

  def summarize
    talk("Summarize this email thread in a few sentences")
  end

  private

  ##
  # By convention, this method defines the provider for a model.
  # If necessary, it can be renamed with: provider: :your_method.
  def set_provider
    LLM.deepseek(key: ENV["KEY"])
  end

  ##
  # By convention, this method returns the context options given
  # to LLM::Context or LLM::Agent. This method can be left undefined.
  def set_context
    {}
  end
end

email = Email.create!(subject: "Streaming support", body: "How do I stream responses?")
email.draft_reply!

##
# The conversation (the email and the draft
# reply) is persisted to the email's column. A
# fresh instance restores it and continues the
# thread, so the summary below knows what was
# already drafted:
Email.find(email.id).summarize

MCP

The Model Context Protocol (MCP) has first-class support in llm.rb. The stdio and http transports work out of the box. MCP tools are translated into subclasses of LLM::Tool that can be used with LLM::Context or LLM::Agent.

See the deepdive.md, and the deepdive.md on persistent connections to learn more.

require "llm"

llm   = LLM.deepseek(key: ENV["KEY"])
mcp   = LLM::MCP.stdio(argv: ["ruby", "server.rb"])
agent = LLM::Agent.new(llm, stream: $stdout, tools: mcp.tools)
agent.talk "Run the tool"

A2A

The Agent 2 Agent (A2A) protocol has first-class support in llm.rb. The http and jsonrpc transports work out of the box. A2A skills are translated into subclasses of LLM::Tool that can be used with LLM::Context or LLM::Agent.

See the deepdive.md, and the deepdive.md on persistent connections to learn more.

require "llm"

llm   = LLM.deepseek(key: ENV["KEY"])
a2a   = LLM::A2A.rest(url: "https://remote-agent.example.com")
agent = LLM::Agent.new(llm, stream: $stdout, tools: a2a.skills)
agent.talk "Run the skill"

Structured outputs

LLM::Schema subclasses produce typed, structured output from any model call. Pass a schema to LLM::Context#talk, LLM::Agent#talk, or LLM::Provider#complete to receive validated JSON instead of free text. Schemas work alongside tools and streams.

LLM::Schema can define objects, arrays, enums, nested schemas, and more. It is also used internally by LLM::Tool for parameter definitions, so you already benefit from it when you declare tool parameters.

The LLM::DeepSeek provider includes runtime-level optimisations such as structured output support (despite no official structured outputs API) and SVG image generation. This example uses LLM::Schema with DeepSeek:

class Weather < LLM::Schema
  property :city, String, "The city name"
  property :temperature, Number, "Current temperature"
  property :conditions, String, "Weather conditions"
  required %i[city temperature conditions]
end

llm = LLM.deepseek(key: ENV["KEY"])
agent = LLM::Agent.new(llm, schema: Weather)
res = agent.talk "Weather in Paris?"
res.content!  # => {city: "Paris", temperature: 15.0, conditions: "Cloudy"}

Guards

LLM::Guard is the hook that sees every tool call before it runs. A guard can let a call through, cancel it, block it with an error, or even answer for it. Because it runs before the tool, anything it intercepts never executes. Policy, validation, quotas, and cost ceilings all live here.

LLM::Agent enables LLM::Guard::Loop by default, so agents get loop protection out of the box. To write your own guard, subclass LLM::Guard and implement LLM::Guard#call. The pending call arrives as function:. Return a value to close the call, or nil to let it run:

See the deepdive.md to learn more.

class PolicyGuard < LLM::Guard
  def call(function:)
    if function.name == "shell"
      function.return(error: true, type: "policy_error",
                      message: "shell is disabled")
    end
  end
end

llm = LLM.deepseek(key: ENV["KEY"])
agent = LLM::Agent.new(llm, tools: [Shell, ReadFile], guard: PolicyGuard)

Transformers

It is possible to rewrite outgoing messages before they reach the provider with LLM::Transformer. Create a subclass and implement call(message:) to scrub sensitive data, inject context, or normalize content. The transform runs automatically on every turn, so you never have to change your prompt code.

See the deepdive.md to learn more.

class RedactEmails < LLM::Transformer
  def call(message:)
    content = message.content.to_s.gsub(/[\w.+-]+@[\w-]+\.[\w.]+/, "[EMAIL]")
    LLM::Message.new(message.role, content, message.extra)
  end
end

llm = LLM.deepseek(key: ENV["KEY"])
agent = LLM::Agent.new(llm, transformer: RedactEmails)
agent.talk "Contact support@example.com for help"

Compactors

Every model has a context window: the finite number of tokens it can consider in a single request. Generally a compactor will drop or summarize older messages to keep the conversation within that window, and it runs automatically before every turn. By default it is disabled so it is a feature you must opt into.

LLM::Compactor::Truncate keeps the most recent messages via an integer count or a percentage like "80%". It preserves tool call and return pairs so the conversation never contains an orphaned result. It is also possible to subclass LLM::Compactor to implement your own compactor with its own logic. Streams can observe the process through the LLM::Stream#on_compaction and LLM::Stream#on_compaction_finish callbacks.

See the deepdive.md to learn more.

llm = LLM.deepseek(key: ENV["KEY"])
agent = LLM::Agent.new(
  llm,
  compactor: LLM::Compactor::Truncate,
  compactor_options: {keep: 64}
)
agent.talk "Hello"

Automatic retries

Rate-limited requests are retried automatically by default. Agents retry a 429 up to five times with a growing backoff before giving up, so most request failures resolve on their own. Set retry_budget to change the number of retries, or retry_budget: 0 to disable them.

require "llm"

llm = LLM.deepseek(key: ENV["KEY"])
agent = LLM::Agent.new(llm, retry_budget: 0)
agent.talk "Hello"

Observability

Trace what an agent is doing by attaching a tracer. Hook into requests, tool calls, and other runtime events to debug a misbehaving agent, monitor latency, or export spans to an observability backend. All built-in tracers share one interface, so switching between them means changing a class name:

• LLM::Tracer::PrettyLogger: human-readable single-line logs to stderr, ideal during development.
• LLM::Tracer::Telemetry: exports spans via OTLP for OpenTelemetry in production.
• LLM::Tracer::Logger: structured JSON to stdout or a file.

See the deepdive.md to learn more.

llm = LLM.deepseek(key: ENV["KEY"])
agent = LLM::Agent.new(llm, tracer: LLM::Tracer::PrettyLogger.new(llm))
agent.talk "Hello"

As a subclass

LLM::Agent.set is a class-level DSL that accepts a Hash of properties. Each key resolves to a corresponding class accessor: name, description, model, tools, instructions, schema, stream, tracer, concurrency, confirm, path, skills, tool_budget, and retry_budget. All options are optional; zero or more can be set. An error is raised for unknown keys so that typos are caught early.

require "llm"
require "llm/tools"

class Agent < LLM::Agent
  set name: "sysadmin",
      description: "system administration agent",
      model: "deepseek-v4-pro",
      tools: [LLM::Tool::Shell]
end

llm = LLM.deepseek(key: ENV["KEY"])
agent = Agent.new(llm)
agent.talk "Run 'date'"

Providers

Each provider is constructed with a class-level factory method on LLM, and the resulting instance is passed to LLM::Context or LLM::Agent. The same API drives every one of them, so switching models is a one-line change. See the deepdive for a full provider reference.

What providers does llm.rb support?

• Anthropic (LLM.anthropic)
• Google (LLM.google)
• OpenAI (LLM.openai)
• DeepSeek (LLM.deepseek)
• DeepInfra (LLM.deepinfra)
• xAI (LLM.xai)
• Z.ai (LLM.zai)
• Moonshot (Kimi) (LLM.moonshot)
• Alibaba (Qwen3) (LLM.alibaba, also LLM.aliyun)
• Mistral (LLM.mistral)
• AWS Bedrock (LLM.bedrock)
• Ollama (LLM.ollama)
• llama.cpp (LLM.llamacpp)

Implicit

Cloud providers can infer their API key automatically from a set of common defaults that are defined by the models.dev registry that is also distributed with llm.rb.

llm = LLM.openai
llm = LLM.anthropic
llm = LLM.deepseek
llm = LLM.alibaba  # also: LLM.aliyun
llm = LLM.moonshot
llm = LLM.mistral

Explicit

The key option can also be providied explicitly, and certain providers (eg ollama, llamacpp) usually do not require an API key at all.

llm = LLM.openai(key: ENV["OPENAI_API_KEY"])
llm = LLM.anthropic(key: ENV["ANTHROPIC_API_KEY"])
llm = LLM.deepseek(key: ENV["DEEPSEEK_API_KEY"])
llm = LLM.alibaba(key: ENV["DASHSCOPE_API_KEY"]) # also: LLM.aliyun
llm = LLM.moonshot(key: ENV["MOONSHOT_API_KEY"])
llm = LLM.mistral(key: ENV["MISTRAL_API_KEY"])

Model Registry

Each provider ships its model catalog, pricing, limits, and modalities with the gem, sourced from models.dev. Reach it from any provider, context, or agent, enumerate models, or sort them by price.

See the deepdive.md to learn more.

require "llm"

llm      = LLM.openai
registry = llm.registry                # => LLM::Provider#registry
cheapest = registry.models.sort.first  # => LLM::Model
cheapest.id                            # => "text-embedding-3-small"
cheapest.context_window                # => 8191
cheapest.structured_output?            # => false

Transports

The transport: option selects which HTTP library a provider uses for network communication. Three backends ship out of the box: net/http is always available and the default, net/http/persistent pools connections for many requests to the same host, and curb wraps libcurl. They share one interface, so switching is a one-word change.

See the deepdive.md to learn more.

llm = LLM.deepseek(
  key: ENV["KEY"],
  transport: :net_http_persistent
)

RAG

Most providers offer an embedding model that can be used for semantic search, or similarity search. An embedding model can generate embeddings that can then be stored in a database that is optimized for storing and querying vectors, such as SQLite's sqlite-vec or PostgreSQL's pg-vector.

llm.rb also includes support for OpenAI's vector store API. It provides a vector database as a HTTP service but we won't cover that here.

See the deepdive.md to learn more.

require "llm"

llm  = LLM.openai(key: ENV["KEY"])
body = "llm.rb is Ruby's capable AI runtime."
embedding = llm.embed([body]).embeddings.first

# Document is your ActiveRecord or Sequel model
# with a vector column (e.g. sqlite-vec or pgvector)
Document.create!(
  title: "llm.rb",
  body:,
  embedding:,
)

Images

A handful of providers can generate images from a text prompt. OpenAI, Google, xAI, and DeepInfra all support it. The API is the same across providers:

require "llm"

llm = LLM.openai(key: ENV["KEY"])
res = llm.images.create(prompt: "a dog on a rocket to the moon")
IO.copy_stream res.images[0], "rocket.png"

DeepSeek

DeepSeek does not have a dedicated image model, but the runtime generates SVG vector graphics through its text model. Each generation produces a valid SVG document that can be converted to PNG with tools like rsvg-convert. Pass an existing agent to maintain a session across generations:

require "llm"
llm = LLM.deepseek(key: ENV["KEY"])

##
# First generation
res = llm.images.create(prompt: "a rocket on the moon")
IO.copy_stream res.images[0], "rocket.svg"

##
# Refine with follow-up prompts (shares context)
res = llm.images.create(prompt: "add a dog next to the rocket",
                        agent: res.agent)
IO.copy_stream res.images[0], "rocket-with-dog.svg"

FAQ

What about local LLM support?

The following providers can be run used with models that are running on your own hardware. They're reasonably well tested but not my main driver:

• Ollama
• Llamacpp

I have a limited budget. What should I do?

There are a few options. The first option is to host your own model, and use the ollama or llamacpp providers. This can be difficult though because a capable model requires hardware that can match it. If you have the ability to self-host, this would be my first option.

The second option is DeepSeek.
The deepseek-v4-flash model costs pennies to use.
And llm.rb has been optimized for deepseek. For example, DeepSeek does not have image generation capabilities but on the llm.rb runtime it does (vector graphics only, though).

The same is true for structured outputs. DeepSeek does not support structured outputs in the same way as OpenAI or Google, but the llm.rb runtime makes it appear as though it does, through the `json_object` response type.

If you're on a budget, DeepSeek is hard to beat.

Sources other than GitHub?

We are on the radicle.network as well.
Every commit that lands on GitHub also lands on Radicle.
Our repository ID is z2PtfQ6dYwyYaW2aGrztG1sMyDmCE.
Browse on the web.

Who maintains llm.rb?

The llm.rb project is maintained primarily by one person. llm.rb has been in active development for more than three years and over that time multiple other contributors have contributed to llm.rb as well. New contributors are always welcome.

I use the repl that is distributed with llm.rb to build llm.rb itself so there is a healthy feedback loop and llm.rb has also been battle tested in production environments.

I have also also written llm.rb agents within the repository that help me maintain the documentation, and backport changes to the mruby-llm runtime as well.

I am constantly focused on improving llm.rb by using it as my primary driver for development.

Resources

If you like what you read so far, check out the deepdive.md to learn more. Unfortunately it wasn't possible to cover every feature without the README becoming a small book. The r.uby.dev homepage also includes more learning material and resources.

License

This software is released under the terms of the MIT license.
See LICENSE for details.