Skip to content

Standalone

Clone Workflow Builder and run the reference editor locally. UI-only demo or the full AI Studio stack with backend execution.

Run Workflow Builder locally from the monorepo. Two paths depending on what you want to evaluate.

Don’t want to clone yet? Open the live demo to try it in your browser first.

GoalPathSetup timeDocker
See the editor running in your browserDemo~2 minno
Run the full reference stack (editor + execution + AI)Full Stack Demo~10 minyes

To embed the SDK in your own React app instead, see React Component.

  • Node.js 22.12.0
  • pnpm 10.17.0
  • Docker Desktop. Only required for the AI Studio path.

Works the same on macOS, Linux, and Windows.

After cloning, run this once. It verifies Node, pnpm, Docker, port availability, and required .env files.

Terminal window
git clone https://github.com/synergycodes/workflowbuilder.git
cd workflowbuilder
pnpm install
pnpm preflight

Expected output:

Workflow Builder preflight
✅ node 22.12.0
✅ pnpm 10.9.0
✅ docker running
✅ port_3001 free (backend)
✅ port_4200 free (demo)
✅ port_4201 free (ai-studio)
✅ port_5432 free (postgres)
✅ port_5433 free (temporal-db)
✅ port_7233 free (temporal)
✅ port_8233 free (temporal-ui)
⚠️ apps/backend/.env missing — copy from apps/backend/.env.example
⚠️ apps/execution-worker/.env missing — copy from apps/execution-worker/.env.example
Ready to go. Pick a path below.

The two .env warnings are expected on a fresh clone. They are only required for the Full Stack Demo path and get created by pnpm setup:env in step 1 of that path. After that they switch to ✅ present.

Fix any red (❌) items before continuing. pnpm preflight --json returns the same report in structured form for tooling.

UI only. No backend, no Docker. The fastest way to see the editor in action.

Terminal window
pnpm dev:demo

Expected output:

[1] VITE vX.Y.Z ready in NNN ms
[1]
[1] ➜ Local: http://localhost:4200/
[0] Found 0 errors. Watching for file changes.

Open http://localhost:4200. The editor loads with the default plugin set and a starter template.

Workflow Builder canvas, node palette, and properties panel

Full reference product: editor, Hono backend, Temporal worker, Postgres. The frontend on port 4201 is the AI Studio reference product (apps/ai-studio). Demonstrates end-to-end workflow execution.

First time only. Copies the .env.example templates into place; existing .env files are left untouched.

Terminal window
pnpm setup:env
Terminal window
pnpm infra:up

Expected output (first run):

Network backend_default Created
Volume "backend_temporal-db-data" Created
Volume "backend_app-db-data" Created
Container backend-app-db-1 Started
Container backend-temporal-db-1 Started
Container backend-temporal-1 Started
Container backend-temporal-ui-1 Started

Verify: open http://localhost:8233 (Temporal UI). The default namespace appears.

First time, or after pulling schema changes.

Terminal window
pnpm -F backend db:migrate

Expected output:

> drizzle-kit migrate
Using 'postgres' driver for database querying
[✓] migrations applied successfully!
Terminal window
pnpm dev:ai-studio

Expected output (three interleaved streams):

Temporal ready
[backend] Backend running on http://127.0.0.1:3001
[worker] Execution worker started on task queue: workflow-execution
[ai-studio] VITE vX.Y.Z ready in NNN ms
[ai-studio] ➜ Local: http://127.0.0.1:4201/

Open http://localhost:4201. Every bundled template contains AI Agent nodes, so either connect an LLM first (next section) or expect the run to stop at its first AI Agent node with ai_not_configured while the Trigger, Decision and Visualize nodes before it run. Pick a template, click Play. The Temporal UI at http://localhost:8233 shows the running execution.

To stop: Ctrl+C, then pnpm infra:down.

The stack starts without an LLM: Trigger, Decision and Visualize nodes run as usual, and an AI Agent node fails with ai_not_configured when the run reaches it. AI nodes need three variables in both apps/backend/.env and apps/execution-worker/.env. The files pnpm setup:env created already carry an endpoint and a model for OpenRouter, so only the key is missing:

AI_API_KEY=sk-or-v1-...
AI_BASE_URL=https://openrouter.ai/api/v1
AI_MODEL=mistralai/mistral-small-3.2-24b-instruct

None of the three has a built-in default. Any OpenAI-compatible endpoint works: set AI_BASE_URL to a gateway or to a model hosted inside your own network, AI_MODEL to an id that endpoint understands, and model requests stay inside it. That covers the model only: the optional web-search tool calls Tavily’s API when TAVILY_API_KEY is set, so leave it unset if nothing may call out. If the model id is wrong, the first AI node fails at runtime and the error surfaces in the UI log panel.

Connect a secured or external Temporal (optional)

Section titled “Connect a secured or external Temporal (optional)”

pnpm infra:up runs a plaintext dev cluster on localhost:7233. The connection is entirely env-driven, so an operated cluster or Temporal Cloud needs no code change. Set the same values in both apps/backend/.env and apps/execution-worker/.env — the two must agree on the namespace, or the worker polls a queue nobody submits to.

VariablePurposeDefault
TEMPORAL_ADDRESShost:port of the cluster127.0.0.1:7233
TEMPORAL_NAMESPACENamespace to usedefault
TEMPORAL_TLStrue requires TLS, false asserts plaintext, empty infersempty (infer)
TEMPORAL_API_KEYAPI-key authentication (Temporal Cloud). Implies TLS—
TEMPORAL_TLS_CA_PATHPEM of a private certificate authority—
TEMPORAL_TLS_CERT_PATHClient certificate for mTLS. Set together with the key—
TEMPORAL_TLS_KEY_PATHClient private key for mTLS. Set together with the certificate—

Any credential turns TLS on by itself, so TEMPORAL_TLS is only needed to force TLS without credentials or to assert plaintext. Contradictions — half an mTLS pair, an API key together with a client certificate, or credentials alongside TEMPORAL_TLS=false — are rejected with an explanatory error when the connection opens.

Temporal Cloud:

TEMPORAL_ADDRESS=<namespace>.<accountId>.tmprl.cloud:7233
TEMPORAL_NAMESPACE=<namespace>.<accountId>
TEMPORAL_API_KEY=<key>

A self-hosted cluster behind mTLS with a private CA:

TEMPORAL_ADDRESS=temporal.internal:7233
TEMPORAL_NAMESPACE=workflows
TEMPORAL_TLS_CA_PATH=/etc/workflowbuilder/tls/ca.pem
TEMPORAL_TLS_CERT_PATH=/etc/workflowbuilder/tls/client.pem
TEMPORAL_TLS_KEY_PATH=/etc/workflowbuilder/tls/client-key.pem

The Docker Compose deployment under deploy/ai-studio/ reads the same variables and additionally lets you retire its bundled cluster; see its README for the COMPOSE_FILE switch and the tls/ mount for certificate files.

SymptomCauseFix
EADDRINUSE on 3001, 4200, 4201, 5432, 5433, 7233, or 8233Another process holds the portpnpm preflight shows the conflict. Stop the other process or change the port.
Temporal UI loads but the default namespace is missingMigrations not runpnpm -F backend db:migrate
AI Agent node fails with ai_not_configuredLLM not configured — the worker starts anyway, only AI nodes are unavailableSet AI_API_KEY, AI_BASE_URL and AI_MODEL in apps/execution-worker/.env.
Backend or worker exits at boot with a TEMPORAL_TLS or TEMPORAL_TLS_*_PATH errorContradictory Temporal settings (half an mTLS pair, API key plus client cert, credentials with TEMPORAL_TLS=false)Remove one side, as the message says. Both .env files must carry the same values.
pnpm dev:demo shows TypeScript errors but the dev server still startsconcurrently runs typecheck alongside Vite. TS errors are non-fatalFix the errors or ignore them temporarily.
Vite acts up after a dependency changeStale node_modules/.viterm -rf node_modules/.vite and rerun.