How yosef-ali/erpnext-ai-agent-project works
ERPNext AI Agent is an ERPNext-facing assistant for semantic document search, business-relationship graphs, document ingestion, and generated ERP designs. The primary workflow begins with a user task, which the multi-agent orchestrator turns into requirements, architecture, schema, and implementation deliverables. Separate branches support indexing/search, graph building, and MCP-based IDE access; RL training data is another distinct capability. The excerpts show connector API access and some orchestration behavior, but not every integration call, so uncertain links are omitted or marked dashed.
Main entry points: multi_agent_workflows.py Workflow orchestrator · start_erpnext_ai_agent.py Agent startup · document_indexer.py Document indexer · knowledge_graph_builder.py Knowledge graph builder
Components 15
Workflow generation
- Agent startup
start_erpnext_ai_agent.py - Workflow orchestrator
integrations/multi_agent_workflows.py - Requirements analysis
integrations/multi_agent_workflows.py - Architecture design
integrations/multi_agent_workflows.py - DocType design
integrations/multi_agent_workflows.py
ERPNext data intelligence
- Document indexer
integrations/document_indexer.py - Vector database
- Knowledge graph builder
integrations/knowledge_graph_builder.py - Graph store
External integrations
- ERPNext connector
integrations/erpnext_connector.py - MCP configuration
integrations/mcp_server_config.py
Learning data
- RL dataset generator
integrations/rl_training_dataset.py
Other components
- User
- ERPNext instance
- IDE MCP client
Connections 14
- User → Agent startup: starts
README.md - Agent startup → Workflow orchestrator: runs workflows
start_erpnext_ai_agent.py - Workflow orchestrator → Requirements analysis: analyzes requirements
README.md - Workflow orchestrator → Architecture design: designs architecture
README.md - Workflow orchestrator → DocType design: designs schema
README.md - Workflow orchestrator → User: returns deliverables
integrations/multi_agent_workflows.py - Agent startup → ERPNext connector: checks connection
start_erpnext_ai_agent.py - ERPNext connector → ERPNext instance: requests data
integrations/erpnext_connector.py - Document indexer → Vector database: indexes documents
README.md - User → Document indexer: searches documents
README.md - Agent startup → Knowledge graph builder: builds graph
start_erpnext_ai_agent.py - Knowledge graph builder → Graph store: stores relationships
- MCP configuration → IDE MCP client: configures access
README.md - RL dataset generator → ERPNext instance: derives usage patterns