# Hacker News Intelligence — Mentions, Trends & AI (`noniner/hn-community-intelligence`) Actor

Track what Hacker News is saying about any product, company or topic: top stories, points, comment volume, who's posting and 90-day trend — with an AI read on sentiment and themes. For dev marketing, launch tracking and tech trend research.

- **URL**: https://apify.com/noniner/hn-community-intelligence.md
- **Developed by:** [Fredrik Hansson](https://apify.com/noniner) (community)
- **Categories:** Developer tools, AI, Automation
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

$100.00 / 1,000 query analyzeds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Hacker News Intelligence — Mentions, Trends & AI

**Know exactly what Hacker News is saying about your product, your competitors, or any tech topic — without scrolling the front page all day.** Give this Actor a list of products, companies or keywords and it searches the entire Hacker News archive, pulls the top stories (with points and comment counts), works out who's posting and how much attention a topic is getting, and adds an **AI read on sentiment and themes**.

You bring the topics. It hands back a tracked, scored view of the conversation.

***

### The flow

```
1. List your topics             2. Search Hacker News            3. Get mentions + AI read
   ("Supabase", "Rust",    →       (public Algolia HN API,   →      top stories · points ·
    "AI agents")                    no key needed)                   comments · authors · 90-day
                                                                     trend · sentiment + themes
```

1. **List the products, companies or keywords** you want to track in `queries`.
2. **The Actor searches Hacker News** through the public Algolia HN Search API — top stories, comment threads, Show HN / Ask HN, whatever your `tags` filter allows. No API key required.
3. **Each query comes back** as a set of story records plus one AI summary: total mentions, top authors, a 90-day activity signal, and an AI read on sentiment, themes and the most notable discussions.

***

### What you get per query

For every query, the Actor:

1. **Searches Hacker News** via the Algolia HN Search API for your term, sorted by `popularity` or `date`, filtered by `tags` (`story`, `comment`, `show_hn`, `ask_hn`, `(story,poll)`, …), up to `maxHitsPerQuery` hits.
2. **Returns one record per hit:** `title`, `url` (the story's external link), `points`, `numComments`, `author`, `createdAt`, `objectID`, and `hnUrl` — the permalink to the Hacker News discussion.
3. **Aggregates the conversation:** `totalMentions` (total matches across all of HN, not just the page fetched), `totalPoints`, `totalComments`, `topAuthors`, and a best-effort **`recentActivity.last90Days`** story count so you can see whether a topic is heating up or cooling down.

Then the **AI layer** (OpenAI `gpt-4o-mini`, a fast and low-cost model) adds one summary record per query:

- **`sentiment`** — `negative` / `mixed` / `neutral` / `positive`, inferred from titles and engagement and hedged (the Actor does not read comment text, so it never invents quotes).
- **`themes`** — what the discussion is actually about.
- **`notableDiscussions`** — the stories worth clicking, each with its real points, comments and a one-line reason.
- **`buzzSignal`** — one sentence on how much attention the topic is getting and which way the trend points.
- **`summary`** — a two-sentence read of the Hacker News conversation.

***

### Three ways people use it

- **Dev-tool launch tracking** — shipped a Show HN or a new release? Track how it lands on Hacker News: points, comment volume, sentiment and the themes people latch onto. Perfect for **dev marketing** and measuring the reaction to a launch.
- **Tech trend research** — watch keywords like "Rust", "LLM", "AI agents" or "WebAssembly" over time with the 90-day activity signal and theme extraction. A lightweight **tech trends** radar built straight on the **Hacker News API** / **HN search**.
- **Brand & competitor monitoring on HN** — track your product and your competitors' products side by side to read **community sentiment**, spot complaints early, and see which discussions are driving the most attention in the developer community.

Keywords this Actor is built for: **Hacker News API**, **HN search**, Hacker News mentions, **tech trends**, **dev marketing**, **community sentiment**, launch tracking, competitor monitoring.

***

### Input

| Field | Type | Notes |
|---|---|---|
| `queries` | array | **Required.** Products, companies or keywords to track (e.g. `"Rust"`, `"Supabase"`, `"AI agents"`). One per line. |
| `tags` | string | Algolia HN tags filter. Default `story`. Also `comment`, `show_hn`, `ask_hn`, `(story,poll)`. |
| `maxHitsPerQuery` | integer | Hits to fetch and analyze per query. Default `30`. |
| `sortBy` | string | `popularity` (points/relevance) or `date` (most recent first). Default `popularity`. |
| `maxResults` | integer | Max queries to analyze. One charge per query. Default `100`. |
| `maxConcurrency` | integer | Queries processed in parallel. Default `4`. |
| `model` | string | Override the OpenAI model. Default `gpt-4o-mini`. |

#### Minimal input example

```json
{
  "queries": ["Supabase", "Rust", "AI agents"],
  "tags": "story",
  "maxHitsPerQuery": 30,
  "sortBy": "popularity"
}
```

***

### Output example

A **story row** (one per Hacker News hit):

```json
{
  "query": "Supabase",
  "recordType": "story",
  "title": "Supabase (YC S20) Is Hiring",
  "url": "https://supabase.com/careers",
  "points": 312,
  "numComments": 141,
  "author": "kiwicopple",
  "createdAt": "2023-04-18T15:02:11.000Z",
  "hnUrl": "https://news.ycombinator.com/item?id=35623451",
  "objectID": "35623451"
}
```

A **summary row** (one per query):

```json
{
  "query": "Supabase",
  "recordType": "summary",
  "totalMentions": 1840,
  "totalPoints": 5231,
  "totalComments": 2104,
  "hitsAnalyzed": 30,
  "recentActivity": {
    "last90Days": 47,
    "oldestHit": "2020-07-30T09:11:00.000Z",
    "newestHit": "2026-09-28T18:44:12.000Z"
  },
  "topAuthors": [
    { "author": "kiwicopple", "mentions": 6 },
    { "author": "awalias", "mentions": 3 }
  ],
  "sentiment": "positive",
  "themes": ["open-source Firebase alternative", "Postgres tooling", "developer experience", "pricing"],
  "notableDiscussions": [
    { "title": "Supabase (YC S20) Is Hiring", "points": 312, "comments": 141, "why": "High engagement thread, strong signal of community interest." }
  ],
  "buzzSignal": "Steady, high-engagement attention with 47 story matches in the last 90 days — the topic is active and trending up.",
  "summary": "Hacker News discussion around Supabase centres on it as an open-source Firebase alternative, with recurring threads on Postgres tooling and developer experience. Engagement is high and consistently positive, with regular front-page appearances."
}
```

***

### Pay-per-event pricing

This Actor uses **pay-per-event** billing with a single event:

| Event | Charged when | Price |
|---|---|---|
| `query-analyzed` | Once per topic searched across Hacker News and summarized with AI. | $0.10 |

One charge covers the Hacker News searches **and** the single AI summary call for that query. The Actor logs its OpenAI token usage and the estimated AI cost at the end of every run, so the event price always stays safely above the model cost.

***

### Data source

All Hacker News data comes from the **[Algolia HN Search API](https://hn.algolia.com/api)** — the official, free, public search index for Hacker News. **No API key is required.** The Actor sends a descriptive User-Agent and returns the data as-is (real titles, points, comment counts and permalinks to `news.ycombinator.com`).

***

### Setup

The AI layer calls the OpenAI API. Set the environment variable / secret **`OPENAI_API_KEY`** on the Actor. Without it, Hacker News stories and aggregates are still collected and shipped — only `sentiment`, `themes`, `notableDiscussions`, `buzzSignal` and `summary` are left empty.

***

### Use it from an AI agent (Apify MCP server)

This Actor is available through the [Apify MCP server](https://mcp.apify.com), so AI agents (Claude, ChatGPT, or anything that speaks MCP) can call it as a tool — hand it a list of `queries`, and read back the Hacker News mentions and AI summary — with no custom integration code.

***

### Run it locally

```bash
npm install
## put your input in storage/key_value_stores/default/INPUT.json
export OPENAI_API_KEY=sk-...   # optional, enables the AI layer
apify run -p
```

***

### Related actors

- [GitHub Repo Analyzer](https://apify.com/noniner/github-repo-analyzer) — Score and profile any GitHub repository: activity, health and an AI read.
- [AI Social Listening](https://apify.com/noniner/ai-social-listening) — Track what people are saying about a brand or topic across the social web, with AI.
- [Signal Radar](https://apify.com/noniner/signal-radar) — Catch early buying and trend signals across the web before your competitors do.
- [Google News Scraper](https://apify.com/noniner/google-news-scraper) — Turn any query into a structured news feed from Google News.

***

**Part of the [No Niner](https://noniner.io) toolkit** — no-code web scraping, enrichment & AI data tools, all pay-per-use. Browse the full set at **[noniner.io](https://noniner.io)**.

# Actor input Schema

## `queries` (type: `array`):

Products, companies or keywords to track on Hacker News (e.g. "Rust", "Supabase", "AI agents"). One per line.

## `tags` (type: `string`):

Algolia HN Search tags filter. Common values: "story", "comment", "(story,poll)", "show_hn", "ask_hn". Default "story".

## `maxHitsPerQuery` (type: `integer`):

How many Hacker News hits to fetch and analyze per query.

## `sortBy` (type: `string`):

"popularity" ranks by points/relevance; "date" returns the most recent hits first.

## `maxResults` (type: `integer`):

Max queries to analyze. One pay-per-event charge per query analyzed.

## `maxConcurrency` (type: `integer`):

How many queries to process in parallel.

## `model` (type: `string`):

Override the model (default gpt-4o-mini).

## Actor input object example

```json
{
  "queries": [
    "Rust",
    "Supabase"
  ],
  "tags": "story",
  "maxHitsPerQuery": 30,
  "sortBy": "popularity",
  "maxResults": 100,
  "maxConcurrency": 4
}
```

# Actor output Schema

## `results` (type: `string`):

All Hacker News hits and per-query AI summaries in the default dataset.

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "queries": [
        "Rust",
        "Supabase"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("noniner/hn-community-intelligence").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "queries": [
        "Rust",
        "Supabase",
    ] }

# Run the Actor and wait for it to finish
run = client.actor("noniner/hn-community-intelligence").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "queries": [
    "Rust",
    "Supabase"
  ]
}' |
apify call noniner/hn-community-intelligence --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,noniner/hn-community-intelligence"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/MNsGTPEsBoyWlsoSp/builds/5EPy0DipP4n6xrVog/openapi.json