daita-agents 0.1.2

Daita Agents - Data focused AI agent framework with free local use and premium hosted enterprise features

Daita Agents

Daita Agents is a commercial AI agent framework designed for production environments. Build intelligent, scalable, data first agent systems with automatic tracing, reliability features, and enterprise-grade observability.

Quick Start

# Install the SDK
pip install daita-agents

# Set up your first agent
daita init my-project
cd my-project

# Create and test an agent
daita create agent my-agent
daita test my-agent

Key Features

Free SDK Features

• Production-Ready Agents: BaseAgent and SubstrateAgent with automatic lifecycle management
• Multi-LLM Support: OpenAI, Anthropic, Google Gemini, and xAI Grok integrations
• Automatic Tracing: Zero-configuration observability for all operations
• Plugin System: Database (PostgreSQL, MySQL, MongoDB) and API integrations
• Workflow Orchestration: Multi-agent systems with relay communication
• CLI Tools: Development, testing, and deployment commands

Premium Features

• Enterprise Integrations: Advanced database plugins and connectors
• Horizontal Scaling: Agent pools and load balancing
• Advanced Reliability: Circuit breakers, backpressure control, task management
• Dashboard Analytics: Real-time monitoring and performance insights
• Priority Support: Direct access to engineering team
• Custom Integrations: Tailored solutions for enterprise needs

Installation

pip install daita-agents

For development with additional tools:

pip install daita-agents[dev]

Basic Usage

Simple Agent

from daita import SubstrateAgent, AgentConfig, LLMConfig

# Configure your agent
config = AgentConfig(
    name="data-processor",
    llm=LLMConfig(
        provider="openai",
        model="gpt-4",
    )
)

# Create and run agent
agent = SubstrateAgent(config)
result = await agent.process("Analyze this data: {...}")

Multi-Agent Workflow

from daita import Workflow, BaseAgent

# Create workflow with multiple agents
workflow = Workflow()
workflow.connect(data_agent, "processed_data", analysis_agent)
workflow.connect(analysis_agent, "insights", report_agent)

# Execute workflow
results = await workflow.run(input_data)

CLI Commands

# Initialize new project
daita init my-project

# Create components
daita create agent my-agent
daita create workflow data-pipeline

# Test and deploy
daita test --watch
daita push production

Architecture

Core Components

• Agents: Intelligent processing units with LLM integration
• Workflows: Orchestrate multiple agents with communication channels
• Plugins: Extensible integrations for databases and APIs
• Tracing: Automatic observability for debugging and monitoring
• Reliability: Production-grade error handling and retry logic

Automatic Tracing

All operations are automatically traced:

• Agent lifecycle and decisions
• LLM calls with token usage and costs
• Plugin/tool executions
• Workflow communication
• Error handling and retries

Examples

Database Integration

from daita.plugins import traced_postgresql

async def process_data():
    # Automatic tracing of database operations
    async with traced_postgresql() as db:
        results = await db.query("SELECT * FROM users")
        return await agent.analyze(results)

Decision Tracing

from daita import record_decision_point

async def make_decision(data):
    confidence = analyze_confidence(data)
    
    # Trace decision reasoning
    decision = record_decision_point(
        decision_type="classification",
        confidence=confidence,
        reasoning="Based on data patterns..."
    )
    
    return decision

Authentication & Deployment

API Key Setup

export DAITA_API_KEY="your-api-key"
export OPENAI_API_KEY="your-openai-key"

Cloud Deployment

# Deploy to managed infrastructure
daita push production

# Monitor deployments
daita logs production
daita status

Documentation

• Getting Started Guide
• API Reference
• Plugin Development
• Enterprise Features

Commercial Licensing

Daita Agents is commercial software with a generous free tier:

• Free: Core SDK, basic plugins, community support
• Premium: Enterprise features, advanced scaling, priority support
• Enterprise: Custom integrations, dedicated support, SLA

Contact Sales for premium features and enterprise licensing.

Support

• Documentation: docs.daita-technologies.com
• Commercial Support: [e-mail]

Links

• Homepage: daita-tech.io
• PyPI Package: pypi.org/project/daita-agents

---

Built for production AI agent systems. Start free, scale with premium features.