How do I test Jido agents without running the AgentServer?

Jido agents are pure data structures, so you can test cmd/2 functions directly without processes by inspecting returned state and directives. The testing guide recommends this approach for deterministic unit tests without runtime overhead.

Jido vs Elixir's built-in Agent module – which should I use?

Use Elixir's Agent for simple, shared state with minimal overhead. Jido is better for complex, multi-agent systems with supervision, fault tolerance, and structured side effects, as it formalizes patterns on top of GenServer for coordinated workflows.

Can Jido handle persistent storage for agent state?

Yes, Jido supports persistence through hibernation and thawing via InstanceManager, with guides covering storage strategies for durable state across restarts. This is essential for long-running workflows but requires additional configuration.

How to integrate Jido with external APIs in actions?

Actions can perform side effects like API calls, but should return directives for effects. Use companion packages like req_llm for LLM APIs or implement custom actions that handle HTTP requests and emit signals for decoupled integration.

What's the performance impact of using Jido compared to raw GenServer?

Jido adds a thin abstraction layer over GenServer, so performance is comparable for most use cases. However, for very high-throughput, single-agent tasks, raw GenServer might have lower overhead due to less indirection from directives and routing.

How to scale Jido agents in a distributed Elixir cluster?

Jido supports partitions and multi-tenancy for distributed deployments via pods and instance managers. The multi-tenancy guide describes partition-safe tenancy boundaries and durable groups for scaling across nodes in a cluster.

Jido — Elixir Autonomous Agent Framework

What is Jido?

Jido is an autonomous agent framework for Elixir that helps developers build agent systems as ordinary Elixir and OTP software. It provides a formalized architecture for creating distributed, cooperating agents with built-in supervision and fault tolerance, separating pure state transformations from side effects.

Target Audience

Elixir developers building multi-agent systems, workflows, or complex stateful applications that require reliable coordination, fault tolerance, and a structured approach to managing side effects.

Value Proposition

Developers choose Jido because it formalizes the agent pattern on top of OTP/GenServer, providing a structured, testable architecture with clear separation of pure state logic and side effects, while maintaining the reliability and concurrency benefits of the BEAM ecosystem.

🤖 Autonomous agent framework for Elixir. Built for distributed, autonomous behavior and dynamic workflows.

Use Cases

Best For

Building multi-agent systems with formalized parent-child hierarchies and signal routing.
Creating stateful workflows where business logic needs to be cleanly separated from side effects for testability.
Developing fault-tolerant, supervised agent systems that leverage OTP's concurrency and reliability patterns.
Implementing complex, durable workflows with plan-based orchestration and partition-safe tenancy.
Extending agent capabilities with composable plugins for state isolation and lifecycle management.
Running deterministic agent logic in production with GenServer-based runtime and configurable execution strategies like Finite State Machines (FSM).

Not Ideal For

Simple, single-process applications where raw GenServer or Task abstractions are sufficient without agent coordination.
Rapid prototyping scenarios where the overhead of defining schemas, actions, and directives slows down iteration.
Teams not using Elixir or the BEAM ecosystem, as Jido is tightly integrated with OTP and lacks cross-language support.
Applications with strict real-time latency requirements where Jido's abstraction layer and signal routing might introduce unnecessary delays.

Pros & Cons

Pros

Immutable Functional Core

Based on pure functional design with cmd/2, ensuring deterministic state transformations and easy testing without processes, as highlighted in the README's core loop and separation of state from effects.

OTP Integration

Seamlessly built on GenServer with built-in supervision, parent-child hierarchies, and fault tolerance, leveraging BEAM's concurrency model for reliable production deployment, as shown in the runtime integration features.

Clear Effect Separation

Directives like Emit and Spawn explicitly describe side effects, separating them from state logic, which improves testability and maintainability, with typed directives covered in the guides.

Extensible Architecture

Supports composable plugins for reusable capabilities and multiple execution strategies like FSM, allowing customization without modifying core agent logic, as detailed in the plugins and strategies documentation.

Cons

Ecosystem Maturity

While core features are robust, companion packages like jido_ai are separate, and the overall ecosystem is smaller compared to more established frameworks, potentially requiring custom integrations for advanced use cases.

Setup Complexity

Without using Igniter, manual installation involves configuring instances and supervision trees, which can be cumbersome for newcomers or simple projects, as noted in the installation guide with multiple steps.

Overhead for Simple Agents

The formalized architecture, including schemas and directives, adds boilerplate for agents that don't need multi-agent coordination or complex state management, making it less efficient for trivial use cases compared to raw OTP.

Frequently Asked Questions

What is Jido?

Target Audience

Elixir developers building multi-agent systems, workflows, or complex stateful applications that require reliable coordination, fault tolerance, and a structured approach to managing side effects.

Value Proposition

Use Cases

Best For

Building multi-agent systems with formalized parent-child hierarchies and signal routing.
Creating stateful workflows where business logic needs to be cleanly separated from side effects for testability.
Developing fault-tolerant, supervised agent systems that leverage OTP's concurrency and reliability patterns.
Implementing complex, durable workflows with plan-based orchestration and partition-safe tenancy.
Extending agent capabilities with composable plugins for state isolation and lifecycle management.
Running deterministic agent logic in production with GenServer-based runtime and configurable execution strategies like Finite State Machines (FSM).

Not Ideal For

Simple, single-process applications where raw GenServer or Task abstractions are sufficient without agent coordination.
Rapid prototyping scenarios where the overhead of defining schemas, actions, and directives slows down iteration.
Teams not using Elixir or the BEAM ecosystem, as Jido is tightly integrated with OTP and lacks cross-language support.
Applications with strict real-time latency requirements where Jido's abstraction layer and signal routing might introduce unnecessary delays.

Pros & Cons

Pros

Immutable Functional Core

OTP Integration

Clear Effect Separation

Directives like Emit and Spawn explicitly describe side effects, separating them from state logic, which improves testability and maintainability, with typed directives covered in the guides.

Extensible Architecture

Cons

Ecosystem Maturity

Setup Complexity

Overhead for Simple Agents

Frequently Asked Questions

Jido

What is Jido?

Overview

Use Cases

Best For

Not Ideal For

Pros & Cons

Pros

Cons

Frequently Asked Questions

Related Projects

Found a gem we're missing?

Jido

What is Jido?

Overview

Use Cases

Best For

Not Ideal For

Pros & Cons

Pros

Cons

Frequently Asked Questions

Related Projects

Found a gem we're missing?