HackerNews AI Researcher: Apify Actor for Tech Trend Analysis

Track Hacker News trends with an AI-assisted research workflow.
This Apify Actor finds relevant HackerNews stories by keyword, enriches them with optional article previews, and returns a structured research summary for content, market intelligence, and developer insights.

What Problem This Solves

Manual Hacker News research is slow and inconsistent. This actor automates:

• Story discovery for a specific topic
• Signal extraction from top stories
• Summary generation for faster decision making
• Structured output for downstream automation

Key Features

• Keyword-based HackerNews story filtering using the official API
• External enrichment using Mistral web_search
• Final summary generation using Google Gemini (gemini-3-flash-preview)
• Optional article preview fetch from story URLs
• Clean dataset output for reporting and integrations

Typical Use Cases

• AI and developer tooling trend reports
• Startup and product landscape scans
• Engineering newsletter drafting
• Competitive intelligence workflows
• Weekly Hacker News monitoring pipelines

Input Parameters

Parameter	Type	Required	Default	Description
query	string	Yes	-	Topic to research on Hacker News
maxStories	integer	No	5	Maximum matching stories to include (1-20)
includeWebSearch	boolean	No	true	Fetch article text previews from story URLs using CheerioCrawler

Example input:

{
    "query": "AI coding tools",
    "maxStories": 5,
    "includeWebSearch": true
}

Output Format

Each run writes one dataset item.

Representative output:

{
    "query": "AI coding tools",
    "summary": "# Research on: AI coding tools\n...",
    "summaryProvider": "gemini",
    "summaryModel": "gemini-3-flash-preview",
    "mistralSearchStatus": "success",
    "mistralSearchError": null,
    "mistralConversationId": "conv_...",
    "mistralToolsEnabled": true,
    "externalReferences": [
        {
            "tool": "web_search",
            "title": "Example source",
            "url": "https://example.com",
            "source": "example.com"
        }
    ],
    "generatedImageUrls": [],
    "generatedImageDataUriCount": 0,
    "storiesFound": 3,
    "stories": [
        {
            "id": 47211249,
            "title": "WebMCP is available for early preview",
            "url": "https://developer.chrome.com/blog/webmcp-epp",
            "score": 193,
            "by": "andsoitis",
            "time": "2026-03-01T22:13:58.000Z"
        }
    ],
    "timestamp": "2026-03-02T04:17:26.671Z"
}

Edge-case output (no matches):

{
    "query": "very specific topic",
    "message": "No matching stories found",
    "storiesFound": 0,
    "timestamp": "2026-03-02T04:17:26.671Z"
}

Quick Start on Apify Cloud

1. Set MISTRAL_API_KEY in Actor environment variables in Apify Console.
2. Set GEMINI_API_KEY in Actor environment variables in Apify Console.
3. Run the actor with your input (Console UI or API).
4. Open the default dataset to review stories, summary, and enrichment data.

CLI flow:

apify push
apify call -o

Pricing and Cost Expectations

• Apify platform billing applies to actor runs based on your actor monetization and plan.
• Mistral API usage is billed against your own MISTRAL_API_KEY.
• Gemini API usage is billed against your own GEMINI_API_KEY.
• If Mistral enrichment fails, the actor continues and still generates final summary with Gemini.
• If Gemini authentication fails or key is missing, the actor run fails.
• A PPE reference file exists at .actor/pay_per_event.json, but pay-per-event charging is only active if configured in Apify monetization settings.

FAQ and Troubleshooting

Why did summary generation fail?

Gemini summary generation failed or GEMINI_API_KEY is missing/invalid. Set a valid key in Apify environment variables.

Why do I get maxStories must be <= 20?

Input schema enforces maxStories range 1-20.

Why are there no results?

Your query may not match current top stories. Try broader keywords or rerun later.

Why is mistralSearchStatus failed?

Mistral web_search enrichment failed (often due rate limits or key permissions). The run still continues with Gemini final summary.

Known Limits

• Story matching is title-based against top stories.
• External page previews depend on target site availability and response speed.
• Summary quality depends on source story relevance and API availability.

Legal and Compliance

• Uses the official Hacker News API.
• Intended for research and informational use.
• You are responsible for complying with applicable laws and target-site terms for fetched URLs.

Support

• Issues: https://github.com/akash9078/multi-agent-researcher/issues
• Apify platform docs: https://docs.apify.com/

Related Links

• Hacker News API: https://github.com/HackerNews/API
• Apify Actors: https://docs.apify.com/platform/actors
• Crawlee: https://crawlee.dev/