Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
High-performance web crawler API optimized for LLMs. Turn any search or website into clean Markdown using remote browsers. Firecrawl alternative
| Date | Stars |
|---|---|
| 2026-07-24 | 275 |
| 2026-07-25 | 275 |
| 2026-07-28 | 277 |
| 2026-07-30 | 277 |
| 2026-08-06 | 277 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
<h1>⭐ Teracrawl</h1>
<p>
<strong>High-performance web crawler & scraper API optimized for LLMs.</strong>
</p>
<p>
Powered by <a href="https://browser.cash/developers">Browser.cash</a> remote browsers.
</p>
<p>
<a href="#features">Features</a> •
<a href="#quick-start">Quick Start</a> •
<a href="#api-reference">API Reference</a> •
<a href="#configuration">Configuration</a> •
<a href="#docker">Docker</a>
</p>
<p>
<img src="https://img.shields.io/badge/license-MIT-blue.svg" alt="License">
<img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen" alt="Node.js Version">
<img src="https://img.shields.io/badge/typescript-5.6-blue" alt="TypeScript">
<img src="https://img.shields.io/badge/powered%20by-browser.cash-orange" alt="Visit Browser.cash">
</p>
<p>
<a href="https://x.com/aibrowsers">
<img src="https://img.shields.io/badge/Follow%20on%20X-000000?style=for-the-badge&logo=x&logoColor=white" alt="Follow on X" />
</a>
<a href="https://linkedin.com/company/megatera">
<img src="https://img.shields.io/badge/Follow%20on%20LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white" alt="Follow on LinkedIn" />
</a>
<a href="https://discord.gg/F9afFJPtYb">
<img src="https://img.shields.io/badge/Join%20our%20Discord-5865F2?style=for-the-badge&logo=discord&logoColor=white" alt="Join our Discord" />
</a>
</p>
<br>
<p>
⚠️ <strong>Important:</strong> Search functionality (`/crawl`) requires a running instance of
<a href="https://github.com/BrowserCash/browser-serp"><strong>browser-serp</strong></a>.
</p>
</div>
---
## 📊 Benchmarks
<div align="center">
<img src="scrape-evals.png" alt="Teracrawl achieves #1 coverage at 82.1%" width="700">
<p><strong>Teracrawl</strong> achieves <strong>#1 coverage (84.2%)</strong> across 14 scraping providers on the <a href="https://github.com/firecrawl/scrape-evals/pull/13">scrape-evals</a> benchmark, an open evaluation framework that tests web scrapers against 1,000 diverse URLs for success rate and content quality.</p>
</div>
---
## 🚀 What is Teracrawl?
**Teracrawl** is a production-ready API designed to turn websites into clean, LLM-ready Markdown. It handles the complexity of JavaScript rendering, anti-bot measures, and parallel execution allowing AI systems to access real-time data quickly.
Unlike simple HTML scrapers, Teracrawl uses real managed Chrome browsers, ensuring high success rates even across protected sites.
### Why use Teracrawl?
- **🤖 LLM-Optimized Output**: Converts complex HTML into clean, semantic Markdown perfect for RAG and context windows.
- **⚡ Smart Two-Phase Crawling**:
- _Fast Mode_: Optimized for static/SSR pages (reuses contexts, blocks heavy assets).
- _Dynamic Mode_: Automatic fallback for complex SPAs (waits for hydration/rendering).
- **🔍 Search & Scrape**: Single endpoint to query Google and scrape the top results in parallel.
- **🏎️ High Concurrency**: Built on a robust <a href="https://github.com/BrowserCash/browser-pool">session pool</a> to handle multiple pages simultaneously.
## <a name="features"></a>✨ Features
- **Search + Scrape**: Query Google and scrape top N results in a single API call.
- **Direct Scraping**: Convert any specific URL to Markdown.
- **Smart Content Extraction**: Automatically detects main content areas (article, main, etc.) and removes clutter (scripts, styles, navs).
- **Safety & Performance**:
- Blocks ads, trackers, and analytics.
- Removes base64 images to save token count.
- Automatic timeout handling and error recovery.
- **Docker Ready**: Deploy anywhere with a lightweight container.
## <a name="quick-start"></a>🛠️ Quick Start
### Prerequisites
1. **Node.js 18+** installed.
2. A **[Browser.cash](https://browser.cash/developers)** API Key.
3. A running SERP service like [browser-serp](https://github.com/BrowserCash/browser-serp) on port 8080 (optiExcerpt of 9,897 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:4c03da4bc4f5f9b4, topic:web-scraping, desc:web crawler, readme:web crawler
matched fp:4c03da4bc4f5f9b4, topic:ai-agents
matched fp:4c03da4bc4f5f9b4, topic:browser-automation