Features
Define agents with custom actions
Agent callbacks for lifecycle hooks
Local space for in-process agent communication
AMQP space for distributed agent communication
Synchronous request-response messaging
Audit logging via agency.logger
Resource management via agency.resources
Schema definition via agency.schema
Agent queue management via agency.queue
Lightweight with minimal dependencies
Example application walkthrough provided
API documentation included
Multi-agent orchestration with handoffs
Sandbox Agents for containerized long-running tasks
Agent-as-tool delegation (v0.15.0+)
Realtime Agents with gpt-realtime-2 voice support (v0.17.6+)
Human-in-the-loop mechanisms
Automatic session history management
Built-in tracing for debugging
Provider-agnostic LLM support (100+ models via LiteLLM)
Redis session support (optional, v0.17.6+)
Instructions, tools, and guardrails configuration
Jupyter notebook compatibility
Supports OpenAI Responses and Chat Completions APIs
