# Mastra Workflows — TypeScript Agent Orchestration

> Mastra Workflows defines multi-step typed agent flows in TypeScript. Build pipelines with .then(), .branch(), .parallel(), .while(). End-to-end type-safe.

## Install

Copy the content below into your project:

## Quick Use

1. `npm create mastra@latest` (scaffolds project + installs deps)
2. Define Steps with `inputSchema`, `outputSchema`, `execute` (Zod-typed)
3. Chain with `new Workflow().step().then().commit()`, then `createRun().start()`

---

## Intro

Mastra Workflows is Mastra's typed orchestration primitive — chain `.step().then().branch().parallel().while()` to build multi-step agent pipelines where TypeScript inferring carries type-safety from the first input to the last output. Best for: production TypeScript agents that need readable, testable, observable workflows. Works with: Mastra 0.5+, Node 20+. Setup time: 5 minutes.

---

### Define a workflow

```typescript
import { Workflow, Step } from "@mastra/core";
import { z } from "zod";

const fetchData = new Step({
  id: "fetch",
  inputSchema: z.object({ url: z.string().url() }),
  outputSchema: z.object({ markdown: z.string() }),
  execute: async ({ context }) => {
    const res = await fetch(context.inputData.url);
    return { markdown: await res.text() };
  },
});

const summarize = new Step({
  id: "summarize",
  inputSchema: z.object({ markdown: z.string() }),
  outputSchema: z.object({ summary: z.string() }),
  execute: async ({ context, mastra }) => {
    const agent = mastra.getAgent("summarizer");
    const result = await agent.generate(`Summarize: ${context.inputData.markdown}`);
    return { summary: result.text };
  },
});

const workflow = new Workflow({
  name: "fetch-and-summarize",
  triggerSchema: z.object({ url: z.string().url() }),
}).step(fetchData).then(summarize).commit();
```

### Branching

```typescript
.then(classify)
.branch([
  [async ({ context }) => context.results.classify.kind === "bug",
   fixerStep],
  [async ({ context }) => context.results.classify.kind === "feature",
   plannerStep],
])
```

### Run and stream

```typescript
const { runId, start } = workflow.createRun();

start({ triggerData: { url: "https://example.com/blog" } });

// Subscribe to step events
workflow.watch(runId, (event) => {
  console.log(event.type, event.payload);
});
```

Each step's input/output is checkpointed — restart from the last successful step if a downstream step fails.

---

### FAQ

**Q: Mastra Workflows vs LangGraph?**
A: LangGraph is Python-first with a graph DSL. Mastra Workflows is TypeScript-first with a fluent chain API. Pick by language preference + ecosystem; both handle the same shape of problems.

**Q: Is Mastra free?**
A: Yes — Mastra is open-source under Elastic License 2.0. Self-hostable. Mastra Cloud (managed deployment + observability) is paid.

**Q: Can workflows call other workflows?**
A: Yes — `step(otherWorkflow)` embeds a workflow as a sub-step. Useful for shared sub-flows (e.g. `validateAndCleanData` reused across pipelines).

---

## Source & Thanks

> Built by [Mastra](https://github.com/mastra-ai). Licensed under Elastic License 2.0.
>
> [mastra-ai/mastra](https://github.com/mastra-ai/mastra) — ⭐ 13,000+

---

<!-- ZH -->

## 快速使用

1. `npm create mastra@latest`（搭项目 + 装依赖）
2. 定义 Step 带 `inputSchema` / `outputSchema` / `execute`（Zod 类型化）
3. `new Workflow().step().then().commit()` 串起来，然后 `createRun().start()`

---

## 简介

Mastra Workflows 是 Mastra 的类型化编排原语 —— 用 `.step().then().branch().parallel().while()` 串多步 agent 流水线，TypeScript 从第一个输入推断到最后一个输出，整条链类型安全。适合需要可读、可测、可观测工作流的生产 TypeScript agent。需要 Mastra 0.5+ 和 Node 20+。装机时间 5 分钟。

---

### 定义 workflow

```typescript
import { Workflow, Step } from "@mastra/core";
import { z } from "zod";

const fetchData = new Step({
  id: "fetch",
  inputSchema: z.object({ url: z.string().url() }),
  outputSchema: z.object({ markdown: z.string() }),
  execute: async ({ context }) => {
    const res = await fetch(context.inputData.url);
    return { markdown: await res.text() };
  },
});

const summarize = new Step({
  id: "summarize",
  inputSchema: z.object({ markdown: z.string() }),
  outputSchema: z.object({ summary: z.string() }),
  execute: async ({ context, mastra }) => {
    const agent = mastra.getAgent("summarizer");
    const result = await agent.generate(`Summarize: ${context.inputData.markdown}`);
    return { summary: result.text };
  },
});

const workflow = new Workflow({
  name: "fetch-and-summarize",
  triggerSchema: z.object({ url: z.string().url() }),
}).step(fetchData).then(summarize).commit();
```

### 分支

```typescript
.then(classify)
.branch([
  [async ({ context }) => context.results.classify.kind === "bug",
   fixerStep],
  [async ({ context }) => context.results.classify.kind === "feature",
   plannerStep],
])
```

### 跑 + 流式

```typescript
const { runId, start } = workflow.createRun();

start({ triggerData: { url: "https://example.com/blog" } });

// 订阅 step 事件
workflow.watch(runId, (event) => {
  console.log(event.type, event.payload);
});
```

每个 step 的输入输出会 checkpoint —— 下游 step 失败时从最后一个成功 step 重启。

---

### FAQ

**Q: Mastra Workflows 跟 LangGraph 比？**
A: LangGraph 是 Python 优先 + 图 DSL。Mastra Workflows 是 TypeScript 优先 + 流式链 API。按语言偏好和生态选；解决同一类问题。

**Q: Mastra 免费吗？**
A: 免费 —— Elastic License 2.0 开源。可自托管。Mastra Cloud（托管部署 + 可观测）付费。

**Q: workflow 能调 workflow 吗？**
A: 能 —— `step(otherWorkflow)` 把一个 workflow 当成子 step。共享子流程（比如 `validateAndCleanData` 在多个流水线复用）有用。

---

## 来源与感谢

> Built by [Mastra](https://github.com/mastra-ai). Licensed under Elastic License 2.0.
>
> [mastra-ai/mastra](https://github.com/mastra-ai/mastra) — ⭐ 13,000+


---
Source: https://tokrepo.com/en/workflows/mastra-workflows-typescript-agent-orchestration
Author: Mastra