# AI News — Latest Artificial Intelligence & LLM News (`straightforward_hydra/ai-news`) Actor

The latest AI news from OpenAI, DeepMind, Hugging Face, TechCrunch, Wired, MIT Tech Review and more, fused with GDELT worldwide. Search any AI topic. Headlines + link, no key.

- **URL**: https://apify.com/straightforward\_hydra/ai-news.md
- **Developed by:** [Dev D](https://apify.com/straightforward_hydra) (community)
- **Categories:** News, AI, Automation
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per event

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/platform/actors/running/actors-in-store#pay-per-event

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
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.
Actors are written with capital "A".

## 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.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## AI News 🤖📰

**The latest artificial-intelligence news in one feed — from OpenAI, Google DeepMind, Hugging Face, TechCrunch, Wired, The Register, VentureBeat, MIT Technology Review and more, fused with GDELT worldwide coverage. Search any AI topic. No API key.**

AI moves fast and the news is scattered across lab blogs, tech press and thousands of outlets worldwide. This Actor pulls the **primary-source lab blogs** and the **best AI-focused press**, blends them with **GDELT** (the open global news-metadata service), de-duplicates, and hands you one clean, ranked feed — headlines, snippets and links, never full article bodies.

***

### Three modes

- **Latest** (default) — the newest AI stories across every curated outlet, topped up with GDELT worldwide coverage, de-duplicated and sorted newest-first.
- **Search** — search worldwide news for any AI topic (`"OpenAI"`, `"Nvidia earnings"`, `"open source LLM"`, `"AI regulation"`), filter by language, source country and time window.
- **Digest** — one summary row: top sources, **trending AI topics** of the moment, and counts by country.

### Sources

**Lab / primary source:** OpenAI · Google DeepMind · Hugging Face
**AI-focused press:** TechCrunch AI · Wired AI · The Register AI · VentureBeat AI · MIT Technology Review · MarkTechPost · The Decoder
**Worldwide:** GDELT global news metadata (AI-filtered)

### What you get per article

| Field | Example |
|---|---|
| `title` | "OpenAI releases new model with improved reasoning" |
| `source` | TechCrunch |
| `summary` | Publisher's own snippet (RSS sources) |
| `image` | Article thumbnail (when provided) |
| `published_at` | ISO-8601 UTC |
| `language` · `country` | English · United States (GDELT) |
| `url` | Link back to the original article |

### Examples

**The latest AI news right now**

```json
{ "mode": "latest" }
```

**Search worldwide coverage of a company or topic**

```json
{ "mode": "search", "query": "OpenAI", "timespan": "3d", "language": "english" }
```

**Trending AI topics + top sources**

```json
{ "mode": "digest" }
```

### Run it on a schedule

Schedule an hourly run to keep a live AI-news table in a sheet or dashboard, power an AI newsletter or news page, monitor coverage of your company or a competitor, or diff the digest to catch breaking AI stories the moment coverage spikes.

### How it stays clean (sources & policy)

- **Headlines + the publisher's own snippet + image + a link back — never the full article body.** The standard aggregator model: facts and attribution with a link to the source.
- **GDELT** — open, commercial-friendly global news-metadata API (no key), returning metadata only.
- **Curated RSS/Atom** — hand-picked AI outlets that publish syndication feeds.
- **No API key** for any mode.

### Notes & limitations

- GDELT is rate-limited (~1 query / 5s); the Actor paces and retries automatically, so a single run is always fine.
- Some feeds carry a short excerpt as `summary`, some none.
- `country` uses GDELT source-country codes; `language` uses GDELT language names (e.g. `english`).
- Coverage skews English by default — widen it with the `language` filter.

***

#### Keywords

AI news, artificial intelligence news, machine learning news, LLM news, generative AI news, AI news API, AI news scraper, OpenAI news, DeepMind, Hugging Face, ChatGPT news, AI research, AI regulation, tech news, AI monitoring, GDELT, news aggregator, AI headlines, AI industry news, no API key.

# Actor input Schema

## `mode` (type: `string`):

latest = newest AI stories across all outlets (+ GDELT worldwide). search = search worldwide for an AI topic. digest = one summary row.

## `query` (type: `string`):

Keyword or phrase to search worldwide news for, e.g. "OpenAI", "Nvidia", "open source LLM", "AI regulation". Use quotes for exact phrases.

## `language` (type: `string`):

Restrict GDELT results to one source language, e.g. "english", "spanish".

## `country` (type: `string`):

Restrict GDELT results to one source country code, e.g. "US", "UK", "IN". Leave blank for worldwide.

## `timespan` (type: `string`):

How far back GDELT looks: e.g. "1d", "3d", "1w", "1m". Default: 1 day for latest, 1 week for search.

## `includeWorldwide` (type: `boolean`):

In latest/digest modes, top up the curated feeds with GDELT worldwide AI coverage (broader, more global sources).

## `includeSummary` (type: `boolean`):

Include the publisher's short summary snippet for each article (RSS sources).

## `maxArticlesPerFeed` (type: `integer`):

Cap on how many items to take from each individual outlet feed.

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

Cap on total article rows returned.

## Actor input object example

```json
{
  "mode": "latest",
  "includeWorldwide": true,
  "includeSummary": true,
  "maxArticlesPerFeed": 25,
  "maxResults": 200
}
```

# 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 = {};

// Run the Actor and wait for it to finish
const run = await client.actor("straightforward_hydra/ai-news").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 = {}

# Run the Actor and wait for it to finish
run = client.actor("straightforward_hydra/ai-news").call(run_input=run_input)

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

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

```

## CLI example

```bash
echo '{}' |
apify call straightforward_hydra/ai-news --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "command": "npx",
            "args": [
                "mcp-remote",
                "https://mcp.apify.com/?tools=straightforward_hydra/ai-news",
                "--header",
                "Authorization: Bearer <YOUR_API_TOKEN>"
            ]
        }
    }
}

```

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/RFdSiQzFozfEE4cz8/builds/5PITg48edboqiSBej/openapi.json