Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI
Python agentagentopsagents-sdkaianthropicautogencost-estimationcrewaievalsevaluation-metricsgroqlangchainllmmistralollamaopenaiopenai-agents
Smolagents Examples
This directory contains examples demonstrating how to use Smolagents with AgentOps for agent monitoring and observability.
Examples
1. Simple Task Agent (simple_task_agent.py)
A minimal example showing how to create a single agent that can answer questions using web search. This is the best starting point for understanding Smolagents basics.
Features:
- Basic agent setup with search capabilities
- AgentOps integration for tracking
- Error handling and session management
2. Multi-Agent System (multi_smolagents_system.py)
A more complex example demonstrating a hierarchical multi-agent system with:
- Manager agent coordinating multiple specialized agents
- Web search agent with custom tools
- Code interpreter capabilities
- Tool creation and usage
3. Text to SQL Agent (text_to_sql.py)
An example showing how to create an agent that can convert natural language queries into SQL statements.
Running the Examples
- Install dependencies:
pip install agentops smolagents python-dotenv
- Set up your API keys in a
.envfile:
AGENTOPS_API_KEY=your_agentops_api_key_here
OPENAI_API_KEY=your_openai_api_key_here
- Run any example:
python simple_task_agent.py
- View the results in your AgentOps Dashboard
Key Concepts
- Agents: AI assistants that can use tools and reason through problems
- Tools: Functions that agents can call to interact with external systems
- Models: LLM backends via LiteLLM (supports OpenAI, Anthropic, etc.)
- AgentOps Integration: Automatic tracking of all agent activities