# Y Combinator Scraper + Traction Score (`lsso/ai-startup-radar`) Actor

Find the AI startups getting real traction. Scans the latest Y Combinator batches and Launch HN posts, ranks each startup with a transparent 0-100 traction score (Hacker News, Product Hunt, team, hiring) and flags breakouts. Lookup any company. JSON + HTML radar report.

- **URL**: https://apify.com/lsso/ai-startup-radar.md
- **Developed by:** [Haidong Nan](https://apify.com/lsso) (community)
- **Categories:** Business, Lead generation, AI
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $5.00 / 1,000 startup profiles

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

## 🚀 Y Combinator Scraper + Traction Score: YC companies, Launch HN & Product Hunt

**Which new AI startups are actually getting traction?** This Actor scans the newest Y Combinator batches and recent *Launch HN* posts, checks each startup's public signals, and ranks them with a transparent **0–100 traction score** and **breakout alerts**. One run replaces hours of scrolling YC's directory, Hacker News and Product Hunt.

- ✅ **Every company in the latest YC batches** (or any batch you pick), with one-liner, description, tags, team size, location, hiring status and YC profile link
- ✅ **Recent Launch HN posts** matched to their YC profiles, with points and comments
- ✅ **Traction score 0–100** built from public signals: Launch HN reception, Hacker News coverage over the last year, stories in the last 30 days, Product Hunt, team size, hiring, YC top-company flag. Every component is returned, nothing is a black box
- ✅ **Breakout flag** for startups that are taking off (e.g. a Launch HN with 150+ points or 5+ stories in 30 days)
- ✅ **Look up any company** by name or website, YC or not
- ✅ **Filters**: AI only, keywords (`agent`, `robotics`, `voice`…), hiring only
- ✅ **HTML radar report** plus clean JSON, ready for Sheets, a CRM or an AI agent
- ✅ **Fair billing**: all candidates are scored for free, you pay only for the top N startups returned

### 🎯 Who is it for?

- **VCs and scouts**: a weekly shortlist of the YC and Launch HN startups people are paying attention to.
- **Sales and partnerships**: new AI companies that are hiring, with website and one-liner, ready to prospect.
- **Founders and analysts**: what the newest batch is building (tag breakdown) and who is breaking out.
- **Newsletters and content creators**: "10 AI startups to watch this week" in one run.

### 🚀 Quick start

1. Leave **What to scan** on *Latest Y Combinator batches* (or pick *Recent Launch HN posts*).
2. Optionally add **keywords** such as `agent` or `robotics`.
3. Click **Start**. Open the **HTML report** from the Storage tab, or download the dataset as JSON, CSV or Excel.

### ⬇️ Input examples

The newest YC batches, AI companies that are hiring:

```json
{ "mode": "yc", "onlyHiring": true, "maxStartups": 50 }
```

Everyone who posted a Launch HN in the last 90 days, AI agents only:

```json
{ "mode": "launches", "launchDays": 90, "keywords": ["agent"] }
```

Check specific companies:

```json
{ "mode": "lookup", "companies": ["coveragecat.com", "Anthropic", "herdr"] }
```

### ⬆️ Output (one item per startup)

```json
{
  "rank": 1,
  "name": "ProvenMetal",
  "website": "https://provenmetal.com",
  "oneLiner": "AI-native electronics manufacturing for the American industrial base",
  "batch": "Summer 2026",
  "tags": ["Hardware", "Manufacturing", "Electronics"],
  "teamSize": 4,
  "isHiring": true,
  "tractionScore": 49,
  "tier": "rising",
  "breakout": true,
  "signals": ["Launch HN: 237 points, 156 comments", "Hiring"],
  "scoreComponents": { "launchHn": 26, "hnBuzz": 14, "recentMentions": 0, "productHunt": 0, "team": 4, "hiring": 5, "ycTop": 0 },
  "hackerNews": {
    "launchPost": { "title": "Launch HN: ProvenMetal (YC S26) delivers circuit boards in days instead of weeks", "points": 237, "comments": 156, "date": "2026-08-06T15:59:15Z", "hnUrl": "https://news.ycombinator.com/item?id=49198464" },
    "mentions": 1, "mentions30d": 0, "points": 237
  },
  "ycUrl": "https://www.ycombinator.com/companies/provenmetal"
}
```

The key-value store also has `OUTPUT` (top 10, breakouts, tag breakdown) and `REPORT` (the HTML radar).

**Tiers:** `hot` (60+), `rising` (35–59), `emerging` (15–34), `quiet` (under 15).

### 💵 Pricing

| Event | Price |
|---|---|
| Startup profile returned (scored and enriched) | **$0.005** ($5 per 1,000) |
| Radar report (HTML + summary), once per run | **$0.10** |

**Example:** a weekly radar of the top 50 AI startups costs **$0.35**. Candidates that are scored but not returned are free.

### 🤖 Use it from AI agents (MCP)

Add this URL as an MCP server in Claude, Cursor or any MCP client and ask *"Which AI startups from the latest YC batch are getting the most traction?"*:

```
https://mcp.apify.com?tools=lsso/ai-startup-radar
```

### ❓ FAQ

**Where does the data come from?** Y Combinator's public company directory (via the open yc-oss mirror, refreshed daily), the official Hacker News search API (Algolia) and Product Hunt's public feed. No logins, no private data. This Actor is not affiliated with Y Combinator, Hacker News or Product Hunt; yc-oss is a community project that mirrors YC's public directory.

**Is funding included?** Not yet: there is no free, reliable funding source. We only use signals we can show you the source for.

**Why is a well-known startup scored low?** The score measures *public developer-community traction* (Hacker News, Product Hunt), not revenue. Companies that sell to enterprises quietly can score low while doing well.

**How fresh is it?** Every run fetches live data. Schedule it weekly and compare scores to see who is accelerating.

### 📝 Changelog

- **1.2** (2026-09-25): New lower price: $5 per 1,000 startup profiles; clearer data-source and not-affiliated note.
- **1.1** (2026-09-24): Launch HN posts are matched to the right company (the YC batch code or launch date must fit, so a 2026 startup no longer inherits a 2020 company's launch with the same name); very short names no longer match unrelated HN stories; report links are always absolute https links.
- **1.0** (2026-09-24): First release: YC batches, Launch HN, lookup mode, traction score with components, breakout flag, HTML radar.

# Actor input Schema

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

**yc**: every company in the chosen YC batches (default: the two newest). **launches**: startups that posted a *Launch HN* recently. **lookup**: your own list of company names or websites.

## `batches` (type: `array`):

e.g. `Fall 2026`, `Summer 2026`, `Winter 2026`. Leave empty for the two newest batches.

## `launchDays` (type: `integer`):

Only for mode *launches*.

## `companies` (type: `array`):

Only for mode *lookup*: names (`Anthropic`) or websites (`coveragecat.com`). YC companies are enriched with their full directory profile.

## `aiOnly` (type: `boolean`):

Keep companies tagged or described as AI / ML / LLM / agents.

## `keywords` (type: `array`):

Keep only startups whose name, one-liner, description or tags contain one of these words, e.g. `agent`, `robotics`, `voice`, `healthcare`.

## `onlyHiring` (type: `boolean`):

Useful for recruiters and job seekers.

## `maxStartups` (type: `integer`):

All candidates are scored for free; you are charged only for the top N returned, ranked by traction score.

## `hnLookbackDays` (type: `integer`):

Window for counting Hacker News stories about each startup.

## `includeProductHunt` (type: `boolean`):

Flag startups that appear in Product Hunt's current launch feed.

## Actor input object example

```json
{
  "mode": "yc",
  "batches": [],
  "launchDays": 90,
  "companies": [],
  "aiOnly": true,
  "keywords": [],
  "onlyHiring": false,
  "maxStartups": 50,
  "hnLookbackDays": 365,
  "includeProductHunt": true
}
```

# Actor output Schema

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

No description

# 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("lsso/ai-startup-radar").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("lsso/ai-startup-radar").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 '{}' |
apify call lsso/ai-startup-radar --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,lsso/ai-startup-radar"
        }
    }
}
```

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/ijIeelOivou3Dsh7y/builds/ToapLncq9eEkvH25w/openapi.json