manus

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Manus

Manus is an autonomous AI agent that handles complex tasks asynchronously. Particularly strong at deep research with parallel processing, web browsing, and generating comprehensive reports with data visualizations.

Manus是一款可异步处理复杂任务的自主AI Agent。它在深度调研方面表现尤为突出，具备并行处理、网页浏览能力，还能生成带有数据可视化的全面报告。

When to Use Manus

何时使用Manus

Deep research - Market analysis, competitive landscaping, product comparisons
Stock/financial analysis - Company research, technical analysis, price charts
Product research - Feature comparisons across brands, specs analysis
Report generation - Creates markdown reports, CSVs, charts, and visualizations
Multi-source synthesis - Gathers and combines information from multiple websites
Long-running tasks - Anything taking 1-10+ minutes of autonomous work

深度调研 - 市场分析、竞品格局梳理、产品对比
股票/金融分析 - 企业调研、技术分析、价格图表
产品调研 - 跨品牌功能对比、规格分析
报告生成 - 创建Markdown报告、CSV文件、图表及可视化内容
多源信息整合 - 从多个网站收集并整合信息
长耗时任务 - 任何需要1-10分钟以上自主处理的工作

Research Prompt Examples

调研提示示例

Effective research prompts are specific about scope, sources, and desired output:

Product comparison:

Find the best 4K monitors for Mac with Thunderbolt connectivity and 120Hz+ refresh rate.
Focus on BenQ, Samsung, Dell, LG. Only include models released in the last year.
Compare specs, prices, and Mac-specific features. Output a comparison table.

Stock/company analysis:

Analyze [TICKER] stock: company profile, recent performance, technical indicators,
valuation metrics, and insider activity. Include a price chart for the past year.

Market research:

Research the [industry] market: key players, market size, growth trends,
recent developments, and competitive landscape. Focus on [region/segment].

Competitive analysis:

Compare [Product A] vs [Product B] vs [Product C]: features, pricing,
user reviews, pros/cons. Create a decision matrix for [use case].

有效的调研提示需明确范围、来源和期望输出：

产品对比：

Find the best 4K monitors for Mac with Thunderbolt connectivity and 120Hz+ refresh rate.
Focus on BenQ, Samsung, Dell, LG. Only include models released in the last year.
Compare specs, prices, and Mac-specific features. Output a comparison table.

股票/企业分析：

Analyze [TICKER] stock: company profile, recent performance, technical indicators,
valuation metrics, and insider activity. Include a price chart for the past year.

市场调研：

Research the [industry] market: key players, market size, growth trends,
recent developments, and competitive landscape. Focus on [region/segment].

竞品分析：

Compare [Product A] vs [Product B] vs [Product C]: features, pricing,
user reviews, pros/cons. Create a decision matrix for [use case].

Environment Setup

环境配置

Requires

MANUS_API_KEY

environment variable. Base URL:

https://api.manus.ai

需要设置

MANUS_API_KEY

环境变量。基础URL：

https://api.manus.ai

Core Workflow

核心工作流

Create task → Returns
```
task_id
```
immediately
Poll status → Check until
```
status
```
is
```
completed
```
or
```
failed
```
Return results → Extract output text and file attachments

创建任务 → 立即返回
```
task_id
```
轮询状态 → 检查直到
```
status
```
变为
```
completed
```
或
```
failed
```
获取结果 → 提取输出文本和附件文件

Creating a Task

创建任务

bash

curl -s -X POST "https://api.manus.ai/v1/tasks" -H "API_KEY:$MANUS_API_KEY" -H "Content-Type:application/json" -d '{"prompt":"<task description>","agentProfile":"manus-1.6"}'

Agent Profiles:

```
manus-1.6-lite
```
- Fast, simple tasks (quick lookups, simple questions)
```
manus-1.6
```
- Standard (default, good for most research)
```
manus-1.6-max
```
- Complex reasoning (deep research, multi-source analysis, detailed reports)

Response:

json

{"task_id":"abc123","task_title":"...","task_url":"https://manus.im/app/abc123"}

bash

curl -s -X POST "https://api.manus.ai/v1/tasks" -H "API_KEY:$MANUS_API_KEY" -H "Content-Type:application/json" -d '{"prompt":"<task description>","agentProfile":"manus-1.6"}'

Agent配置文件：

```
manus-1.6-lite
```
- 快速处理简单任务（快速查询、简单问题）
```
manus-1.6
```
- 标准版（默认，适用于大多数调研场景）
```
manus-1.6-max
```
- 复杂推理（深度调研、多源分析、详细报告）

响应：

json

{"task_id":"abc123","task_title":"...","task_url":"https://manus.im/app/abc123"}

Checking Task Status

检查任务状态

bash

curl -s -X GET "https://api.manus.ai/v1/tasks/{task_id}" -H "API_KEY:$MANUS_API_KEY"

Status values:

pending

running

completed

failed

Poll every 5-10 seconds until completed.

Extract text output:

bash

curl -s -X GET "https://api.manus.ai/v1/tasks/{task_id}" -H "API_KEY:$MANUS_API_KEY" | jq -r '.output[] | select(.role=="assistant") | .content[] | select(.type=="output_text") | .text'

Extract file attachments:

bash

curl -s -X GET "https://api.manus.ai/v1/tasks/{task_id}" -H "API_KEY:$MANUS_API_KEY" | jq -r '.output[] | select(.role=="assistant") | .content[] | select(.type=="output_file") | "\(.fileName): \(.fileUrl)"'

bash

curl -s -X GET "https://api.manus.ai/v1/tasks/{task_id}" -H "API_KEY:$MANUS_API_KEY"

状态值：

pending

running

completed

failed

每5-10秒轮询一次，直到任务完成。

提取文本输出：

bash

curl -s -X GET "https://api.manus.ai/v1/tasks/{task_id}" -H "API_KEY:$MANUS_API_KEY" | jq -r '.output[] | select(.role=="assistant") | .content[] | select(.type=="output_text") | .text'

提取附件文件：

bash

curl -s -X GET "https://api.manus.ai/v1/tasks/{task_id}" -H "API_KEY:$MANUS_API_KEY" | jq -r '.output[] | select(.role=="assistant") | .content[] | select(.type=="output_file") | "\(.fileName): \(.fileUrl)"'

Listing Tasks

列出任务

bash

curl -s -X GET "https://api.manus.ai/v1/tasks" -H "API_KEY:$MANUS_API_KEY" | jq '.data[] | {id, status, title: .metadata.task_title}'

bash

curl -s -X GET "https://api.manus.ai/v1/tasks" -H "API_KEY:$MANUS_API_KEY" | jq '.data[] | {id, status, title: .metadata.task_title}'

Multi-turn Conversations

多轮对话

Continue an existing task by including

taskId

bash

curl -s -X POST "https://api.manus.ai/v1/tasks" -H "API_KEY:$MANUS_API_KEY" -H "Content-Type:application/json" -d '{"prompt":"follow-up question","taskId":"abc123","agentProfile":"manus-1.6"}'

通过包含

taskId

来延续现有任务：

bash

curl -s -X POST "https://api.manus.ai/v1/tasks" -H "API_KEY:$MANUS_API_KEY" -H "Content-Type:application/json" -d '{"prompt":"follow-up question","taskId":"abc123","agentProfile":"manus-1.6"}'

Delete a Task

删除任务

bash

curl -s -X DELETE "https://api.manus.ai/v1/tasks/{task_id}" -H "API_KEY:$MANUS_API_KEY"

bash

curl -s -X DELETE "https://api.manus.ai/v1/tasks/{task_id}" -H "API_KEY:$MANUS_API_KEY"

Advanced Options

高级选项

Parameter	Description
`taskMode`	`chat` , `adaptive` , or `agent`
`projectId`	Associate with project for shared instructions
`attachments`	Array of file objects (see below)
`connectors`	Pre-configured connector IDs (Gmail, Calendar, Notion)
`createShareableLink`	Enable public access URL

参数	描述
`taskMode`	`chat` , `adaptive` , 或 `agent`
`projectId`	关联到项目以使用共享指令
`attachments`	文件对象数组（见下文）
`connectors`	预配置的连接器ID（Gmail、Calendar、Notion）
`createShareableLink`	启用公共访问URL

File Attachments

文件附件

Attach files using one of three formats:

URL attachment:

json

{"prompt":"Analyze this","attachments":[{"type":"url","url":"https://example.com/doc.pdf"}]}

Base64 attachment:

json

{"prompt":"What's in this image?","attachments":[{"type":"base64","data":"<base64>","mime_type":"image/png"}]}

File ID (after upload):

json

{"prompt":"Review this file","attachments":[{"type":"file","file_id":"file-xxx"}]}

可通过以下三种格式添加附件：

URL附件：

json

{"prompt":"Analyze this","attachments":[{"type":"url","url":"https://example.com/doc.pdf"}]}

Base64附件：

json

{"prompt":"What's in this image?","attachments":[{"type":"base64","data":"<base64>","mime_type":"image/png"}]}

文件ID（上传后）：

json

{"prompt":"Review this file","attachments":[{"type":"file","file_id":"file-xxx"}]}

Projects

项目

Create a project with shared instructions:

bash

curl -s -X POST "https://api.manus.ai/v1/projects" -H "API_KEY:$MANUS_API_KEY" -H "Content-Type:application/json" -d '{"name":"My Project","instruction":"Always respond concisely"}'

Use project in task:

bash

curl -s -X POST "https://api.manus.ai/v1/tasks" -H "API_KEY:$MANUS_API_KEY" -H "Content-Type:application/json" -d '{"prompt":"...","projectId":"proj_xxx","agentProfile":"manus-1.6"}'

创建带有共享指令的项目：

bash

curl -s -X POST "https://api.manus.ai/v1/projects" -H "API_KEY:$MANUS_API_KEY" -H "Content-Type:application/json" -d '{"name":"My Project","instruction":"Always respond concisely"}'

在任务中使用项目：

bash

curl -s -X POST "https://api.manus.ai/v1/tasks" -H "API_KEY:$MANUS_API_KEY" -H "Content-Type:application/json" -d '{"prompt":"...","projectId":"proj_xxx","agentProfile":"manus-1.6"}'

Best Practices

最佳实践

Use
```
manus-1.6-lite
```
for simple queries (faster, cheaper)
Use
```
manus-1.6
```
or
```
manus-1.6-max
```
for research tasks
Always report
```
task_url
```
so user can view progress in browser
Poll status with reasonable intervals (5-10s for simple, 15-30s for research)
Check
```
credit_usage
```
field to track consumption
For research: be specific about scope, timeframe, sources, and desired output format
Research tasks typically produce multiple output files (reports, CSVs, charts) - extract all attachments
Manus uses parallel processing for multi-faceted research - one prompt can cover multiple angles

对于简单查询，使用
```
manus-1.6-lite
```
（更快、成本更低）
对于调研任务，使用
```
manus-1.6
```
或
```
manus-1.6-max
```
务必提供
```
task_url
```
，以便用户在浏览器中查看进度
以合理的间隔轮询状态（简单任务5-10秒，调研任务15-30秒）
查看
```
credit_usage
```
字段以跟踪消耗情况
调研时：明确范围、时间框架、来源和期望的输出格式
调研任务通常会生成多个输出文件（报告、CSV、图表）——提取所有附件
Manus使用并行处理进行多维度调研——一个提示可覆盖多个角度

Error Handling

错误处理

Check for failed tasks:

bash

curl -s -X GET "https://api.manus.ai/v1/tasks/{task_id}" -H "API_KEY:$MANUS_API_KEY" | jq '{status, error}'

status

failed

, the

error

field contains the reason. Common issues:

Invalid API key → Check
```
MANUS_API_KEY
```
is set
Task timeout → Simplify prompt or use
```
manus-1.6-max
```
Rate limited → Wait and retry

检查失败的任务：

bash

curl -s -X GET "https://api.manus.ai/v1/tasks/{task_id}" -H "API_KEY:$MANUS_API_KEY" | jq '{status, error}'

如果

status

为

failed

，

error

字段会包含失败原因。常见问题：

API密钥无效 → 检查
```
MANUS_API_KEY
```
是否已设置
任务超时 → 简化提示或使用
```
manus-1.6-max
```
速率限制 → 等待后重试

API Reference

API参考

For complete endpoint documentation, see references/api.md.

完整的端点文档，请查看references/api.md。