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

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

---

Output example

A story row (one per Hacker News hit):

{
  "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):

{
  "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 — 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, 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

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 — Score and profile any GitHub repository: activity, health and an AI read.
• AI Social Listening — Track what people are saying about a brand or topic across the social web, with AI.
• Signal Radar — Catch early buying and trend signals across the web before your competitors do.
• Google News Scraper — Turn any query into a structured news feed from Google News.

---

Part of the No Niner toolkit — no-code web scraping, enrichment & AI data tools, all pay-per-use. Browse the full set at noniner.io.