Features
Multiple AI coding agents in parallel terminals
Isolated git worktrees per session
Issue board with lanes: Planning, Implementation, Review, Done
GitHub and Linear issue import and PR/comment posting
Real PTY terminals with user dotfiles and aliases
Built-in Monaco editor for file editing
SQLite databases explorer with read-only queries
Git diff viewer and commit history
Dependency tracking with cycle detection
Quick commands (CLI and terminal) with keyboard shortcuts
Agent MCP server to spawn additional sessions
Resume sessions with full conversation history
Support for Claude Code, Codex, Gemini CLI, Claude Fable 5
Multiple sessions on the same issue
Session settings for CLI, model, and effort
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
