Features
Parallel execution of multiple AI coding agents
Isolated sandbox environments per agent
Local execution using your own tools and agents
Agent-agnostic: supports Claude, Codex, Gemini, Qwen, Copilot, OpenCode
YAML-based workflows and custom workflows
Lifecycle hooks for automation
Context system for enriching tasks with external sources
Structured logging for agent sessions
Container image caching for faster task initialization (v2.2)
Custom sandbox images (v1.6)
Interactive task iterations (v1.7)
Multi-project support (v2.0)
Podman and Docker support
Open source under Apache 2.0
Autonomous vulnerability scanning and PR generation
PR review for quality, security, and best practices
Legacy COBOL to Java migration with testing
Incident triage and root cause analysis
Agent Canvas: manage multiple agents in one workspace
Cloud agents run even when your machine is off
Schedule recurring tasks via cron or event triggers
Trigger workflows from GitHub, Slack, PagerDuty
Model-agnostic: supports Claude Code, Codex, Gemini CLI, MiniMax M2.7
Isolated sandbox execution on VM or cloud
Fine-grained access control and budget guardrails
Audit trails for enterprise compliance
Self-hosted deployment in your VPC
Open-source SDK for custom agent development
In-chat model switching with saved LLM profiles
