> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentkey.app/llms.txt
> Use this file to discover all available pages before exploring further.

# Zhihu data for AI agents

> Zhihu questions, answers and comments, column articles, pins, user profiles and follow graphs, keyword search and the Zhihu hot list through AgentKey.

Zhihu (知乎) is China's question-and-answer network — the place for long,
reasoned answers from practitioners, and a prime source for research on how
Chinese professionals think about a topic. It has no public API and gates most
pages behind a login. Through AgentKey your agent reads public Zhihu data the
same way it reads everything else — `find_tools`, `describe_tool`,
`execute_tool` — with more than one provider behind the scenes, so one route
failing does not stop the task.

## What you can ask

* *"What are the top answers to this Zhihu question?"*
* *"知乎热榜现在有什么？"*
* *"Search Zhihu for discussions about AI agents from the past month."*
* *"Pull this column's recent articles and summarize them."*
* *"Who does this Zhihu user follow, and which topics do they follow?"*
* *"Get the comments on this answer, hottest first."*
* *"这个用户在知乎上写过哪些文章？"*

## What's covered

**Questions and answers**

* Question detail; the answers to a question with sorting and pagination
* Answer detail; a user's answers

**Articles and columns**

* Column article detail and the article list of a column; related articles
* A user's articles sorted by publish time or upvotes; their included (收录)
  articles
* Similar column recommendations

**Pins (想法)**

* Pin detail, pin comments, a user's pins

**Comments**

* Comments on an answer or other content, hottest or latest; replies

**Users**

* Public profile by URL token; user search
* Followers and following
* Followed topics, columns, questions and collections; created collections

**Search**

* Keyword search with result type, sort, time interval and topic display
  controls
* Dedicated search for articles, columns, topics, users, videos, ebooks, Salt
  (盐选) and scholar content
* Search suggestions and recommendations; AI search

**Trending**

* The hot list, the hot recommend feed, the video list

## How to use it

Pass the request in plain language and let the router pick the tool:

```text theme={null}
find_tools(q="top answers to this Zhihu question")
find_tools(q="知乎热榜现在有什么")
find_tools(prefix="social/zhihu")          # browse everything for Zhihu
describe_tool("<returned Provider/Operation>")
execute_tool("<Provider/Operation>", { ...params })
```

Both English and Chinese phrasing work, and the platform's usual English and Chinese names all land here. Always `describe_tool` before executing — parameters and per-call
costs differ between providers.

> [!NOTE]
>
> **Building with code?** The same capability is available as fixed-contract
> [Scenario Methods](/api-reference/scenario/overview) with automatic provider
> failover:
> [`social.zhihu.post.search`](/api-reference/scenario/methods/social-zhihu-post-search),
> [`social.zhihu.post.get`](/api-reference/scenario/methods/social-zhihu-post-get),
> [`social.zhihu.topic.search`](/api-reference/scenario/methods/social-zhihu-topic-search),
> [`social.zhihu.user.get`](/api-reference/scenario/methods/social-zhihu-user-get),
> [`social.zhihu.user.posts`](/api-reference/scenario/methods/social-zhihu-user-posts),
> [`social.zhihu.user.search`](/api-reference/scenario/methods/social-zhihu-user-search),
> [`social.zhihu.trending`](/api-reference/scenario/methods/social-zhihu-trending).

## FAQ

> **Do I need a Zhihu account?**
>
> No. AgentKey holds the upstream access; your agent only needs your AgentKey
> subscription.

> **Does it cover paid Salt (盐选) content?**
>
> Salt titles can be searched like other content types. Whether a given
> title's body is returned depends on what Zhihu serves publicly for it;
> paywalled text is not unlocked.

> **How fresh is the data?**
>
> Every call goes to Zhihu at request time; the hot list, answers and
> comments reflect what Zhihu returns at that moment.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.