Skip to main content

Build Goal-Driven AI Agents

Aden is a platform for building AI agents that improve themselves. Define your goal through natural language, and the framework generates a node graph with dynamically created connection code. When things break, the framework captures failure data, evolves the agent, and redeploys automatically.

Why Aden?

Traditional agent frameworks require you to manually design workflows, define agent interactions, and handle failures reactively. Aden flips this paradigm - you describe outcomes, and the system builds itself.

Goal-Driven

Define objectives in natural language; the coding agent generates the agent graph and connection code.

Self-Improving

Framework captures failures, updates objectives, and evolves the agent graph automatically.

Human-in-the-Loop

Built-in intervention nodes that pause execution for human input with configurable timeouts.

Production-Ready

SDK-wrapped nodes with shared memory, observability, tools, and LLM access out of the box.

Quick Start

# Clone and setup
git clone https://github.com/adenhq/hive.git
cd hive && ./scripts/setup-python.sh

# Build an agent using Claude Code
claude> /building-agents

# Test your agent
claude> /testing-agent

# Run your agent
PYTHONPATH=core:exports python -m your_agent run --input '{...}'

Quickstart Guide

Complete setup instructions and your first agent in under 10 minutes.

What Makes Aden Different

Traditional FrameworksAden
Hardcode agent workflowsDescribe goals in natural language
Manual graph definitionAuto-generated agent graphs
Reactive error handlingProactive self-evolution
Static tool configurationsDynamic SDK-wrapped nodes
DIY budget managementIntegrated cost controls

Platform Components

Need Help?

Book a Discovery Call

Schedule a call with our team to learn more.