Features
Visual drag-and-drop workflow builder with typed variables and loops
Self-patching AI agents that rewrite workflows on failure
Real browser control: click, type, extract, screenshot
Desktop cursor and keyboard automation (mouse, scroll, hotkeys)
Shell command execution with stdout/stderr/exit code capture
80+ built-in integrations (no plugin store needed)
Local LLM support via Ollama (Llama, Mistral, Qwen, etc.)
Cloud AI support: OpenAI GPT-4o, Anthropic Claude, Claude Code CLI
AI copilot for conversational workflow step creation
Cron, interval, or one-time scheduling for workflows and agents
Command-line interface (loopi-cli) for terminal-driven automation
Goal-driven agents bundle goal, workflows, schedule, and LLM
Reflection engine compares per-node outcomes against goal
Encrypted credential storage (AES-256-CBC, local only)
Real-time Chromium window preview or headless mode
Multi-agent orchestration
Low-code visual interface
Human-in-the-loop interactions
Conversation pattern customization
Web-based agent monitoring
Group chat and debate patterns
