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
Live knowledge graph from code, commits, issues, and docs
Feasibility analysis: flags buildable vs risky items
Technical design document generation grounded in service topology
Impact assessment maps services, APIs, and dependencies across repos
Auto-scoping epics into Jira/Linear stories with effort estimates
One-shot production code generation grounded in service patterns
AI code reviews with cross-repo impact analysis
Production issue triage via MCP
Conversational learning from Slack and Jira
Accelerated onboarding via system-level Q&A in coding agents
Create Jira tickets and merge requests from Slack
MCP server for integration with Cursor, Claude Code, Codex
On-prem or cloud deployment
No code storage or model training
