Features
Edits code across entire project with dependency awareness
Runs bash commands and monitors output in real time
Plan mode explores codebase and asks clarifying questions
Act mode executes plan with diffs and checkpoints
Human-in-the-loop approval for every edit and command
Auto-approve toggle for fully autonomous execution
Project-specific .clinerules for coding standards
Skills to load rules on demand based on task context
Multi-model support: Claude, GPT, Gemini, Ollama, OpenRouter
Plugin system via SDK: register tools and lifecycle hooks
Kanban board for parallel agents with worktrees and auto-commit
Checkpoints to easily undo agent's work
Package manager commands (npm, pip, etc.)
Long-running process monitoring (dev servers, builds)
Browser support for web-based tasks
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
