Browse Registry Agents

Discover pre-built agents for task automation, data analysis, and workflow orchestration in the Compozy registry

Browse Registry

​
What are Agents?

Agents in Compozy are autonomous AI-powered components that can understand instructions, use tools, and make decisions. They serve as the intelligent workers in your workflows, capable of processing information, interacting with various services, and producing structured outputs. Agents can be used within tasks to create sophisticated automation workflows.

agents:
  - id: content_moderator
    use: compozy/agents:content-moderator
    config:
      provider: openrouter
      model: openai/gpt-4-turbo
      api_key: "{{ env.OPENROUTER_KEY }}"
    with:
      language: en
      threshold: 0.7

​
Core Features

Model Flexibility

Support for multiple AI providers and models, allowing you to choose the best fit for each task

Task Integration

Seamless integration with Compozy tasks for complex workflows and parallel processing

Tool Integration

Seamless integration with tools for extended capabilities like API calls, data processing, and external services

Structured Output

Define exact output schemas for predictable and validated responses

Context Management

Built-in memory and context management through MCP integration

Framework Agnostic

Use any agent framework like LangChain, AutoGPT, or create custom implementations

​
How Agents Work

Task Definition

Agents are defined within tasks with specific configurations and tools

Configuration

Configure the agent with an AI provider, model, and optional tools

Tool Integration

Connect agents with tools to extend their capabilities beyond language processing

Execution

Agents execute within task contexts, processing inputs and producing structured outputs

Memory Management

Maintain context across interactions using built-in memory systems

​
Memory and Context

Agents in Compozy maintain context through:

Task Context

Access task state, inputs, and outputs within the workflow

Short-term Memory

Maintains conversation context within a single execution

Long-term Memory

Persists information across multiple executions using MCP

Tool State

Tracks tool interactions and their outcomes

​
Key Points

AI-Powered Automation

Leverage advanced language models to process instructions and make intelligent decisions

Tool Integration

Extend capabilities by connecting agents with tools for API calls, data processing, and external services

Context Management

Built-in memory systems maintain context across conversations and workflow executions

Structured Interactions

Define precise input/output schemas for predictable and validated agent responses

​
Next Steps