llm-boxlisted

## Overview llm-box is an AI-powered terminal workflow engine that generates and executes multi-step automation pipelines from natural language descriptions. It supports 30+ agent nodes including LLM providers, code analysis, file operations, web fetching, and system integrations. Workflows are defined as deterministic YAML files that can be version-controlled and reused. Key features: - Natural language to YAML workflow generation - 30+ built-in nodes (LLM, fetch, execute, transform, etc.) - MCP protocol support for external tool integration - Security-hardened with SSRF protection, path traversal prevention, and resource limits - On-device LLM inference support (1B-8B models) ## Prerequisites - llm-box CLI installed (`go install github.com/alib8b8/llm-box/cmd/llm-box@latest`) - Go 1.21+ or a pre-built binary - Optional: Ollama for local LLM inference ## Instructions 1. **Generate a workflow**: Describe the task in natural language 2. **Review the YAML**: The generated workflow is deterministic and editable 3. **Execute**: Run the workflow with progress tracking 4. **Chain outputs**: Use `{{.steps[N].output}}` to pass data between steps ### CLI Commands ```bash # Generate a workflow from plain English llm-box create "fetch weather data and save to file" # Run a workflow file llm-box run workflow.yaml # List all available nodes llm-box list # Validate a workflow without executing llm-box validate workflow.yaml # Dry run (show steps without executing) llm-box --dry