Features
19 specialized agents across build, review, and domain lanes
39 skills for varied development tasks
25+ MCP tools including LSP, AST grep, Python REPL
Multi-AI orchestration with Claude, Gemini, and Codex
10 execution modes: Autopilot, Ralph, Ultrawork, Team, Planning, Deep Interview
Durable Ultragoal workflow with persistent multi-goal plans
Native teams integration with staged execution pipeline
Language server integration (LSP): hover, go-to-def, references, type checking
AST grep for structural code search and replace
Python REPL with pandas, numpy, matplotlib
Safety guardrails for destructive workspace cleanup
Cross-platform support: macOS, Linux, Windows (v4.14)
Plugin cache repair and registry alignment for reliability
Teleport and wait commands for session management
Notification profiles and event-driven notifications
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
