Dhenara Agent Open-source AI agent framework with powerful DSL
Create, compose, and orchestrate AI agents with sophisticated behaviors using our expressive domain-specific language, while maintaining robust observability and reproducibility.
from dhenara.agent.dsl import (
AIModelNode,
AIModelNodeSettings,
FlowDefinition,
ResourceConfigItem,
)
from dhenara.ai.types import Prompt
# Define a flow
my_flow = FlowDefinition()
# Add an AI model node to the flow
my_flow.node(
"question_answerer",
AIModelNode(
resources=ResourceConfigItem.with_model("claude-3-5-haiku"),
settings=AIModelNodeSettings(
system_instructions=["You are a helpful assistant."],
prompt=Prompt.with_dad_text("Answer the following question: $var{question}"),
),
),
)Powerful Features
Everything you need to build advanced AI agents
Dhenara Agent provides a comprehensive set of tools and features to create, deploy, and manage sophisticated AI agents.
- Expressive Agent Definition
- Create complex agent workflows using a straightforward, programming language-like approach that makes it easy to define sophisticated behaviors.
- Component-Based Architecture
- Compose reusable components to build sophisticated agent systems with a hierarchical component model of nodes, flows, and agents.
- Comprehensive Observability
- Built-in logging, tracing, and metrics collection for all agent activities, making it easy to debug and optimize your agents.
- Reproducible Execution
- Track and replay agent execution through a run context system, ensuring that you can reproduce and analyze agent behavior.
- Extensible Node System
- Easily create custom node types to extend functionality and integrate with your existing systems and workflows.
- Resource Management
- Flexible management of AI model resources and credentials, making it easy to work with different LLM providers and models.
Key Benefits
Build better AI agents faster
Dhenara Agent's design principles enable faster development, better maintainability, and more powerful AI agents.
Hierarchical Component Model
Build complex agents using a hierarchical structure of nodes, flows, and agents that can be composed and reused.
Event-Driven Architecture
An event system enables loose coupling between components, allowing agents to react to events, request inputs, and communicate with each other.
Powerful Template Engine
A versatile template engine supports variable substitution, expressions, and hierarchical references for dynamic prompts and response processing.
Why Choose Dhenara Agent?
Dhenara Agent offers significant advantages over other agent frameworks:
Advantages
- Built on top of our robust dhenara-ai package for consistent API access
- First-class support for complex multi-agent workflows
- Complete observability and reproducibility out-of-the-box
- Easy to extend with custom node types and integrations
- Open-source with a genuine community focus
- Designed for both development and production use cases