Skip to main content
Plans: Pro and Enterprise. Self-hosted: Included in the open-source server.
On Free and Individual you can run the sample workflows. Creating or running your own needs Pro or Enterprise. Workflows (/workflows) and Executions (/executions) are the dashboard for MAF: named pipelines of agent steps. They sit under the Orchestrator module, next to live orchestrator chat.

Workflows

/workflows lists every active workflow you can run — your own plus public ones such as the sample workflows. Your drafts are on the Drafts tab. Each row shows name, step count, updated time. New workflow opens /workflow-new. Opening a row loads /workflow with the step list, assigned agents, and Run. Creating a workflow in the UI is the same model as:
- (and omitting an agent in the UI) lets the routing engine assign that step. Generate a draft calls POST /api/maf/generate: describe the workflow in plain language, review the suggested steps, then save. It uses your saved OpenAI key, or the server’s own if you haven’t added one. With no usable key the request fails with 502 (llm_key_rejected); if the model can’t produce a plan, it fails with 422. Soft-delete from the workflow page. Executions already queued keep running.

Executions

/executions lists runs across workflows: status, started time, workflow name. Open one for step-level status, output, and cost (TokenOps can also attribute by workflow).
--wait polls until the run finishes and prompts for any HITL pause inline.

MAF workflows

The workflow model, CLI, and API.

Orchestrator chat

Live ReAct over accessible agents, without a pre-defined pipeline.