Workflow JSON and samples
Export format
The export format is stable and explicit:
json
{
"schemaVersion": "1.0.0",
"workflowVersion": 1,
"workflow": {
"id": "wf-basic-llm",
"name": "Basic LLM Flow",
"schemaVersion": "1.0.0",
"workflowVersion": 1,
"nodes": [],
"edges": []
},
"exportedAt": "2026-03-30T00:00:00.000Z"
}It includes node types and config, the edge graph, and node positions for canvas restoration. Import and export go through the GET /api/workflows/:id/export and POST /api/workflows/import routes; see API endpoints.
Sample workflows
The files under samples/workflows/ are the seed dataset and runnable examples:
basic-flow.json: text-in / LLM / text-out, runs zero-key with the bundled echo provider.mcp-agent-quickstart-flow.json: zero-key MCP agent (the target of the 5-minute tutorial).supervisor-worker-swarm-flow.json: multi-agent: a Supervisor delegating to a researcher and a computer worker.workflow-as-mcp-tool-flow.json:mcp_server_triggerexposing a workflow as a callable MCP tool.agentic-mcp-flow.json: webhook, agent, MCP tools and memory.two-turn-report-code-helper-flow.json: multi-turn helper with deterministic session artifacts.vscode-l2m-coding-agent-flow.json: canonical wiring for the VS Code extension.conditional-flow.json: branching from a webhook trigger.rag-flow.json: RAG with Google Drive and an in-memory vector store.rag-pinecone-flow.json: RAG backed by Pinecone.structured-output-flow.json: schema-validated structured output extraction.azure-openai-flow.json: basic LLM flow using Azure OpenAI.azure-connectors-demo-flow.json: Azure Storage, Cosmos DB, Monitor and AI Search.
Set SEED_SAMPLE_WORKFLOWS=true to load these into the database when the workflow table is empty. See the pattern library for when to use which.
For full real-world reference projects (helpdesk agent, support triage, VS Code repo reviewer) with end-to-end READMEs and production-deployment notes, see the l2m-samples repository.