cli-anything-exa

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Exa CLI Skill

Identity

身份信息

Name: cli-anything-exa
Version: 1.0.0
Category: search
Entry Point:
```
cli-anything-exa
```

名称: cli-anything-exa
版本: 1.0.0
分类: 搜索
入口点:
```
cli-anything-exa
```

What This CLI Does

该CLI的功能

Provides an agent-native command-line interface to the Exa API — a neural search engine optimised for AI agent workflows. Supports web search across multiple modes (fast, deep, deep-reasoning) and fetching full-text or highlighted page contents.

为Exa API提供原生Agent命令行界面——Exa是一款针对AI Agent工作流优化的神经搜索引擎。支持多种模式（快速、深度、深度推理）的网页搜索，以及获取全文或高亮页面内容。

Prerequisites

前置条件

Python >= 3.10
```
pip install cli-anything-exa
```
```
export EXA_API_KEY="your-api-key"
```
(get one at https://dashboard.exa.ai/api-keys)

Python >= 3.10
```
pip install cli-anything-exa
```
```
export EXA_API_KEY="your-api-key"
```
（可在https://dashboard.exa.ai/api-keys获取）

Installation

安装

bash

pip install git+https://github.com/HKUDS/CLI-Anything.git#subdirectory=exa/agent-harness

bash

pip install git+https://github.com/HKUDS/CLI-Anything.git#subdirectory=exa/agent-harness

Command Reference

命令参考

search — Web search

search — 网页搜索

bash

cli-anything-exa search "<query>" [OPTIONS]

Options:
  --type       auto|fast|instant|deep|deep-reasoning  (default: auto)
  --num-results / -n   1–100  (default: 10)
  --category   company|people|research-paper|news|personal-site|financial-report
  --content    highlights|text|summary|none  (default: highlights)
  --freshness  smart|always|never  (default: smart)
  --include-domains DOMAIN   (repeatable)
  --exclude-domains DOMAIN   (repeatable)
  --from DATE   ISO 8601 start published date
  --to   DATE   ISO 8601 end published date
  --location CC  Two-letter country code for geo-bias

bash

cli-anything-exa search "<query>" [OPTIONS]

Options:
  --type       auto|fast|instant|deep|deep-reasoning  (默认值: auto)
  --num-results / -n   1–100  (默认值: 10)
  --category   company|people|research-paper|news|personal-site|financial-report
  --content    highlights|text|summary|none  (默认值: highlights)
  --freshness  smart|always|never  (默认值: smart)
  --include-domains DOMAIN   (可重复使用)
  --exclude-domains DOMAIN   (可重复使用)
  --from DATE   ISO 8601格式的发布起始日期
  --to   DATE   ISO 8601格式的发布结束日期
  --location CC  用于地域偏好的两位国家代码

contents — Fetch page contents

contents — 获取页面内容

bash

cli-anything-exa contents <url> [url ...] [--content text|highlights|summary] [--freshness smart|always|never]

bash

cli-anything-exa contents <url> [url ...] [--content text|highlights|summary] [--freshness smart|always|never]

server status — Verify API key and connectivity

server status — 验证API密钥与连通性

bash

cli-anything-exa server status

bash

cli-anything-exa server status

JSON Output

JSON输出

All commands support

--json

at the root level for machine-readable output:

bash

cli-anything-exa --json search "latest LLM papers" --num-results 5

所有命令在根级别支持

--json

参数，以生成机器可读的输出：

bash

cli-anything-exa --json search "latest LLM papers" --num-results 5

Common Agent Patterns

常见Agent使用模式

Fast keyword lookup

快速关键词查询

bash

cli-anything-exa --json search "site:arxiv.org transformer architectures" --type fast --content highlights

bash

cli-anything-exa --json search "site:arxiv.org transformer architectures" --type fast --content highlights

Deep research on a topic

主题深度研究

bash

cli-anything-exa --json search "EU AI Act compliance requirements 2024" --type deep --content text

bash

cli-anything-exa --json search "EU AI Act compliance requirements 2024" --type deep --content text

Academic paper discovery

学术论文发现

bash

cli-anything-exa --json search "retrieval augmented generation" --category research-paper --num-results 20

bash

cli-anything-exa --json search "retrieval augmented generation" --category research-paper --num-results 20

Company intelligence

企业情报收集

bash

cli-anything-exa --json search "Anthropic funding history" --category company

bash

cli-anything-exa --json search "Anthropic funding history" --category company

News monitoring

新闻监控

bash

cli-anything-exa --json search "AI regulation news" --category news --from 2024-01-01

bash

cli-anything-exa --json search "AI regulation news" --category news --from 2024-01-01

Fetch full content for summarisation

获取完整内容用于摘要生成

bash

cli-anything-exa --json contents https://example.com/article --content text

bash

cli-anything-exa --json contents https://example.com/article --content text

Interactive REPL

交互式REPL

bash

cli-anything-exa   # No subcommand → enters REPL

Type commands without the

cli-anything-exa

prefix. Type

exit

quit

to leave.

bash

cli-anything-exa   # 不输入子命令即可进入REPL

无需输入

cli-anything-exa

前缀即可键入命令。输入

exit

或

quit

退出。

Notes

注意事项

```
highlights
```
content mode is 10× more token-efficient than
```
text
```
— prefer it for agent pipelines
```
--type deep
```
triggers multi-step reasoning; slower but synthesises across many sources
```
--category company
```
and
```
--category people
```
do not support date or domain-exclude filters
Cost per query is included in JSON output under
```
cost_dollars
```

```
highlights
```
内容模式的Token效率是
```
text
```
模式的10倍——在Agent流水线中优先使用该模式
```
--type deep
```
会触发多步推理；速度较慢但可综合多个来源的信息
```
--category company
```
和
```
--category people
```
不支持日期或域名排除过滤器
每次查询的成本会包含在JSON输出的
```
cost_dollars
```
字段中