Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration

Agentica SDK Reference (v0.3.1) Build AI agents in Python using the Agentica framework. Agents can implement functions, maintain state, use tools, and coordinate with each other. When to Use Use this skill when: Building new Python agents Adding agentic capabilities to existing code Integrating MCP tools with agents Implementing multi agent orchestration Debugging agent behavior Quick Start Agentic Function (simplest) Spawned Agent (more control) Core Patterns Return Types Premise vs System Prompt Passing Tools (Scope) SDK Integration Pattern Agent Instantiation spawn() Async (most cases) Agent() Sync (for init ) Model Selection Available models: openai:gpt 3.5 turbo , openai:gpt 4o , openai:gpt 4.1 , openai:gpt 5 anthropic:claude sonnet 4 , anthropic:claude opus 4.1 anthropic:claude sonnet 4.5 , anthropic:claude opus 4.5 Any OpenRouter slug (e.g., google/gemini 2.5 flash ) Persistence (Stateful Agents) For spawn() agents, state is automatic across calls to the same instance. Token Limits Token Usage Tracking Streaming MCP Integration mcp config.json format: Logging Default Behavior Prints to stdout with colors Writes to ./logs/agent <id .log Contextual Logging Per Agent Logging Global Config Error Handling Custom Exceptions Multi Agent Patterns Custom Agent Class Agent Orchestration Tracing & Debugging OpenTelemetry Tracing SDK Debug Logging Top Level Exports Checklist Before using Agentica: [ ] Functions with @agentic() MUST be async [ ] spawn() returns awaitable use await spawn(...) [ ] agent.call() is awaitable use await agent.call(...) [ ] First arg to call() is return type, second is prompt string [ ] Use persist=True for conversation memory in @agentic [ ] Use Agent() (not spawn() ) in synchronous init [ ] Document exceptions in docstrings for agent to raise them [ ] Import listeners from agentica.logging.agent listener (NOT agentica.logging )

agentica-sdk