Features
Autonomous AI agents with memory and function call history
Software engineering agents: local repo editing, ticket-to-PR, code review
Slack chatbot integration
Multi-agent extend-reasoning LLM interface
Generated function calling code with sandboxed execution
Cost tracking and configurable human-in-the-loop
Persistent state management for agents
Repository indexing and ad-hoc query agents
Pull request code review agent
OpenTelemetry-based tracing and observability
Support for 15+ LLM providers
Functional callable tools: filesystem, Jira, Slack, Perplexity, Google Cloud, GitLab, GitHub
Multi-user SSO enterprise deployment (Google Cloud IAP)
Scale-to-zero deployment on Firestore & Cloud Run
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
