belt

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

belt cli

belt is the cloud platform cli for ai agents. single ~4mb binary, no runtime dependencies.

belt 是面向AI agents的云平台CLI工具。仅约4MB的二进制文件，无运行时依赖。

install

安装

bash

curl -fsSL cli.inference.sh | sh
belt login
belt me

bash

curl -fsSL cli.inference.sh | sh
belt login
belt me

apps — run 250+ ai models

应用——运行250+款AI模型

bash

belt app search "flux"                    # find apps
belt app get fal/flux-pro                 # view schema
belt app sample fal/flux-pro --save in.json  # generate sample input
belt app run fal/flux-pro --input in.json    # run it
belt app run fal/flux-pro --input '{"prompt": "..."}' --save output.png

common apps:

image:
```
fal/flux-pro
```
,
```
fal/real-esrgan
```
(upscale)
video:
```
google/veo-2
```
,
```
seedance/seedance-2-i2v
```
search:
```
tavily/search
```
,
```
exa/search
```
audio:
```
elevenlabs/tts
```

bash

belt app search "flux"                    # 查找应用
belt app get fal/flux-pro                 # 查看 schema
belt app sample fal/flux-pro --save in.json  # 生成示例输入
belt app run fal/flux-pro --input in.json    # 运行应用
belt app run fal/flux-pro --input '{"prompt": "..."}' --save output.png

常用应用：

图像类：
```
fal/flux-pro
```
、
```
fal/real-esrgan
```
（图像放大）
视频类：
```
google/veo-2
```
、
```
seedance/seedance-2-i2v
```
搜索类：
```
tavily/search
```
、
```
exa/search
```
音频类：
```
elevenlabs/tts
```

knowledge — persistent agent memory

知识库——持久化Agent记忆

bash

belt know search "query"                  # semantic search
belt know list --type observation         # list by type
belt know get namespace/name              # get details
belt know create ./file.md --type concept # create from file
echo "learned X" | belt know create - --name x --type observation  # from stdin
belt know delete <id>

types:

skill

concept

observation

reference

preference

bash

belt know search "query"                  # 语义搜索
belt know list --type observation         # 按类型列出
belt know get namespace/name              # 获取详情
belt know create ./file.md --type concept # 从文件创建
echo "learned X" | belt know create - --name x --type observation  # 从标准输入创建
belt know delete <id>

类型：

skill

、

concept

、

observation

、

reference

、

preference

skills — reusable workflows

技能——可复用工作流

bash

belt skill search "deployment"            # search registry
belt skill store --featured               # browse featured

bash

belt skill search "deployment"            # 搜索注册表
belt skill store --featured               # 浏览精选技能

use on-demand (no install, stdout)

按需使用（无需安装，输出至标准输出）

belt skill use namespace/skill-name # from store belt skill use github.com/user/repo # from github belt skill use user/repo --skill name # pick from multi-skill repo

belt skill use namespace/skill-name # 从技能库获取 belt skill use github.com/user/repo # 从GitHub获取 belt skill use user/repo --skill name # 从多技能仓库中选择

install persistently

持久化安装

belt skill add namespace/skill-name # auto-detects agents belt skill add ns/name --agent claude-code belt skill list # list installed

belt skill upload ./my-skill # publish

undefined

belt skill add namespace/skill-name # 自动检测Agent belt skill add ns/name --agent claude-code belt skill list # 列出已安装技能

belt skill upload ./my-skill # 发布技能

undefined

connectors — mcp servers

连接器——MCP服务器

bash

belt mcp list                             # available connectors
belt mcp search "slack"                   # search
belt mcp connect slack                    # connect
belt mcp tools slack                      # list tools
belt mcp run slack send_message --input '{"channel": "#general", "text": "hello"}'

bash

belt mcp list                             # 查看可用连接器
belt mcp search "slack"                   # 搜索连接器
belt mcp connect slack                    # 连接
belt mcp tools slack                      # 列出工具
belt mcp run slack send_message --input '{"channel": "#general", "text": "hello"}'

suggest — unified search

智能建议——统一搜索

bash

belt suggest "how to generate images"     # searches apps + skills + knowledge

bash

belt suggest "how to generate images"     # 搜索应用+技能+知识库

tips

小贴士

use
```
--json
```
for structured output when piping
use
```
--save filename
```
to save media outputs directly
```
belt app sample
```
generates valid input — start there for unfamiliar apps
```
belt update
```
to get latest version

管道输出时使用
```
--json
```
获取结构化输出
使用
```
--save filename
```
直接保存媒体输出
```
belt app sample
```
会生成合法输入——不熟悉的应用从这里开始
```
belt update
```
获取最新版本