Features
Multi-agent team orchestration
Long-horizon workflow automation
Dynamic agent roles (planner, researcher, coder, reviewer)
Shared context and artifact passing between agents
Observability dashboard for agent activity
Failure recovery within workflows
Natural language workflow definition
Code-based workflow definition
Persistent memory across sessions
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
