agentjido / jido
- воскресенье, 8 марта 2026 г. в 00:00:03
🤖 Autonomous agent framework for Elixir. Built for distributed, autonomous behavior and dynamic workflows.
Pure functional agents and OTP runtime for building autonomous multi-agent workflows in Elixir.
The name "Jido" (自動) comes from the Japanese word meaning "automatic" or "automated", where 自 (ji) means "self" and 動 (dō) means "movement".
Learn more about Jido at agentjido.xyz.
With Jido, your agents are immutable data structures with a single command function:
defmodule MyAgent do
use Jido.Agent,
name: "my_agent",
description: "My custom agent",
schema: [
count: [type: :integer, default: 0]
]
end
end
{agent, directives} = MyAgent.cmd(agent, action)State changes are pure data transformations; side effects are described as directives and executed by an OTP runtime. You get deterministic agent logic, testability without processes, and a clear path to running those agents in production.
Jido is the core package of the Jido ecosystem. The ecosystem is built around the core Jido Agent behavior and offer several opt-in packages to extend the core behavior.
| Package | Description |
|---|---|
| req_llm | HTTP client for LLM APIs |
| jido_action | Composable, validated actions with AI tool integration |
| jido_signal | CloudEvents-based message envelope and supporting utilities for routing and pub/sub messaging |
| jido | Core agent framework with state management, directives, and runtime |
| jido_ai | AI/LLM integration for agents |
For demos and examples of what you can build with the Jido Ecosystem, see https://agentjido.xyz.
OTP primitives are excellent. You can build agent systems with raw GenServer. But when building multiple cooperating agents, you'll reinvent:
| Raw OTP | Jido Formalizes |
|---|---|
| Ad-hoc message shapes per GenServer | Signals as standard envelope |
| Business logic mixed in callbacks | Actions as reusable command pattern |
| Implicit effects scattered in code | Directives as typed effect descriptions |
| Custom child tracking per server | Built-in parent/child hierarchy |
| Process exit = completion | State-based completion semantics |
Jido isn't "better GenServer" - it's a formalized agent pattern built on GenServer.
cmd/2 as the core operation: actions in, updated agent + directives outThe fastest way to get started is with Igniter:
mix igniter.install jidoThis automatically:
MyApp.Jido instance module (use Jido, otp_app: :my_app)config/config.exsMyApp.Jido to your supervision treeGenerate an example agent to get started:
mix igniter.install jido --exampleAdd jido to your list of dependencies in mix.exs:
def deps do
[
{:jido, "~> 2.0"}
]
endThen define a Jido instance module and add it to your supervision tree:
# In lib/my_app/jido.ex
defmodule MyApp.Jido do
use Jido, otp_app: :my_app
end# In config/config.exs
config :my_app, MyApp.Jido,
max_tasks: 1000,
agent_pools: []# In your application.ex
children = [
MyApp.Jido
]
Supervisor.start_link(children, strategy: :one_for_one)defmodule MyApp.CounterAgent do
use Jido.Agent,
name: "counter",
description: "A simple counter agent",
schema: [
count: [type: :integer, default: 0]
],
signal_routes: [
{"increment", MyApp.Actions.Increment}
]
enddefmodule MyApp.Actions.Increment do
use Jido.Action,
name: "increment",
description: "Increments the counter by a given amount",
schema: [
amount: [type: :integer, default: 1]
]
def run(params, context) do
current = context.state[:count] || 0
{:ok, %{count: current + params.amount}}
end
end# Create an agent
agent = MyApp.CounterAgent.new()
# Execute an action - returns updated agent + directives
{agent, directives} = MyApp.CounterAgent.cmd(agent, {MyApp.Actions.Increment, %{amount: 5}})
# Check the state
agent.state.count
# => 5# Start the agent server
{:ok, pid} = MyApp.Jido.start_agent(MyApp.CounterAgent, id: "counter-1")
# Send signals to the running agent (synchronous)
# Signal types must be declared in signal_routes
{:ok, agent} = Jido.AgentServer.call(pid, Jido.Signal.new!("increment", %{amount: 10}, source: "/user"))
# Look up the agent by ID
pid = MyApp.Jido.whereis("counter-1")
# List all running agents
agents = MyApp.Jido.list_agents()The fundamental operation in Jido:
{agent, directives} = MyAgent.cmd(agent, action)Key invariants:
agent is always complete - no "apply directives" step neededdirectives describe external effects only - they never modify agent statecmd/2 is a pure function - same inputs always produce same outputs| Actions | Directives | State Operations |
|---|---|---|
| Transform state, may perform side effects | Describe external effects | Describe internal state changes |
Executed by cmd/2, update agent.state |
Bare structs emitted by agents | Applied by strategy layer |
| Can call APIs, read files, query databases | Runtime (AgentServer) interprets them | Never leave the strategy |
State operations are internal state transitions handled by the strategy layer during cmd/2. Unlike directives, they never reach the runtime.
| StateOp | Purpose |
|---|---|
SetState |
Deep merge attributes into state |
ReplaceState |
Replace state wholesale |
DeleteKeys |
Remove top-level keys |
SetPath |
Set value at nested path |
DeletePath |
Delete value at nested path |
| Directive | Purpose |
|---|---|
Emit |
Dispatch a signal via configured adapters |
Error |
Signal an error from cmd/2 |
Spawn |
Spawn a generic BEAM child process |
SpawnAgent |
Spawn a child Jido agent with hierarchy tracking |
StopChild |
Gracefully stop a tracked child agent |
Schedule |
Schedule a delayed message |
Stop |
Stop the agent process |
Start here:
Guides:
Advanced:
API Reference: hexdocs.pm/jido
mix testmix quality # Runs formatter, dialyzer, and credoWe welcome contributions! Please see our Contributing Guide for details on:
Copyright 2024-2025 Mike Hostetler
Licensed under the Apache License, Version 2.0. See LICENSE for details.