# unclecode/crawl4ai

> Open-source web crawler and scraper that turns pages into clean, LLM-ready Markdown for RAG, agents and data pipelines. Runs via Python API, CLI and Docker with no API keys.

- Magnitude: 2.4 out of 10 — Cooling
- Stars: 84,280 total · +5 stars on 2026-09-26 (UTC), ≈ 27 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2024-05-09 · Last push: 2026-09-25
- GitHub: https://github.com/unclecode/crawl4ai · Homepage: https://crawl4ai.com · Page: https://gitnova.dev/en/r/unclecode/crawl4ai

## Useful for

- Build a Markdown corpus from a site for a RAG pipeline
- Extract structured data from pages using an LLM
- Run a deep BFS crawl over documentation pages

## Why it’s here

- 5 stars so far today, about 27 expected by the end of the day.
- Interest is fading: the two-day pace is 34% of the previous week and a half.
- About 11 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 8,716
- Issues and pull requests: 1,823
- Watchers: 418
- Average over the last week: 66 per day
- Usual pace: 175 per day
- Latest release: v0.9.4 (2026-09-23)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

09-13 5.0, 09-14 5.1, 09-15 3.1, 09-16 2.9, 09-17 2.9, 09-18 2.7, 09-19 2.4, 09-20 2.8, 09-21 2.8, 09-22 2.3, 09-23 2.5, 09-24 2.5, 09-25 2.5, 09-26 2.5

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-26 10:58 UTC, updated every 30 minutes.