An LLM-based AI agent that generates n8n automation workflows from a single text prompt using vector search and knowledge graphs.
n8n_agent is an LLM-based AI agent designed to generate n8n agentic automation workflows from a single text prompt. It analyzes, categorizes, and stores n8n workflows using vector databases, graph databases, and relational databases to enable semantic search and intelligent workflow management. The project solves the problem of manually creating and managing complex automation workflows by providing tools for automated generation, validation, and storage.
Developers and automation engineers who use n8n for workflow automation and want to leverage AI to generate, search, and validate workflows more efficiently. It is also suitable for teams managing large libraries of n8n workflows who need advanced categorization and retrieval capabilities.
Developers choose n8n_agent because it combines LLM-powered analysis with multiple database systems (vector, graph, relational) to provide intelligent workflow search, validation, and generation. Its unique selling point is the integration of Model Context Protocol (MCP) servers for seamless interaction with n8n, QDRANT, and Supabase, making workflow management more automated and scalable.
LLM based AI Agent for generating n8n agentic automation workflows from a one-shot text prompt
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Combines vector (QDRANT), graph (Neo4j), and relational (Supabase) databases for semantic search, relationship mapping, and structured metadata, enabling comprehensive workflow analysis as per the README.
Integrates Model Context Protocol servers for n8n, QDRANT, and Supabase, allowing programmatic workflow import, validation, and data interaction through tools like list_workflows and search_similar_workflows.
Validates n8n workflows against best practices in naming, error handling, security, performance, and documentation with configurable strictness and specific validator tools.
Provides CLI and MCP tools to import and manage workflows directly with n8n's API, facilitating batch processing from analyzed data as shown in import-to-n8n.js.
Requires configuration of multiple external services (QDRANT, Neo4j, Supabase, n8n) and environment variables, with MCP server setups adding to deployment complexity.
Neo4j and Supabase integrations are listed as 'to be implemented' in the README, limiting current functionality for relationship mapping and structured metadata storage.
Heavily dependent on specific technologies like n8n and the chosen databases, reducing flexibility for other automation tools or storage systems without significant modification.
Using LLM embeddings (via OpenAI) and multiple database queries may introduce latency in workflow analysis and semantic search operations, especially at scale.