Features
Dynamic task planning and decomposition
Automatic tool selection and invocation
Multi-agent workforce orchestration
Memory and persistent file system
Knowledge base integration
Model-agnostic LLM support
Docker-based one-command setup
Outcome-driven (no flowchart required)
Iterative execution with evaluation
Enterprise-ready scaling from one agent to workforces
Autonomous planning system
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
