At a glance
- Category
- Agent tools and integrations
- Tags
- Open source, Self-hosted
Code
- Last push
- 15 October 2026
For developers
- Works with
- Claude, Cursor, Windsurf
What is Crawl4AI?
Crawl4AI is an open-source web crawling tool for developers who need LLM-ready data with browser control and self-hosting. It combines Generate Clean Markdown, Structured Extraction, Advanced Browser Control, and Adaptive Crawling, with hooks, proxies, stealth modes, and session reuse for harder pages. It integrates with CSS/XPath and LLM-based extraction paths, and the project is documented around AsyncWebCrawler workflows. The repo shows 65.7k GitHub stars and 6.7k forks.
What it actually does well
Crawl4AI is an async Python crawler (Playwright-based, also usable via a CLI or a Docker/FastAPI server) built specifically for feeding LLMs and RAG pipelines rather than general-purpose scraping. Its markdown generator applies heuristic content filtering (a pruning filter and a BM25 filter keyed to a query) to strip nav/boilerplate before the page ever reaches an LLM, and it ships three extraction paths — CSS/XPath schemas, LLM-based extraction against a Pydantic schema, and a table-specific LLM extractor with automatic chunking for large tables. Version 0.7.0 added 'adaptive crawling', which stops crawling a site once an information-sufficiency threshold is met rather than exhausting a fixed page budget, and 0.8.0 added crash-recoverable deep crawls (BFS/DFS/best-first with resumable state). It needs no API key or account to use at all — everything runs on infrastructure you control.
Adoption and maintenance
The PyPI package (github.com/unclecode/crawl4ai) has been downloaded 18.5 million times all-time and 1.64 million times in the trailing 30 days (pepy.tech/projects/crawl4ai, checked today); the Docker image has 3.21 million pulls (Docker Hub API). Development is active day-to-day, not just at release time, against a steady release cadence (v0.9.0 on 18 June 2026, v0.9.1 on 8 July 2026, v0.9.2 on 15 July 2026). This is a genuinely live, high-traffic project, not an abandoned star-farm.
The Docker API's security history
If you self-host the Docker deployment (rather than the plain pip library), know that it has twice shipped a critical, unauthenticated remote-code-execution flaw with a maximum CVSS score of 10.0. CVE-2026-26216 (disclosed Jan 2026, fixed in v0.8.0) let an unauthenticated caller smuggle Python code into the /crawl endpoint's hooks parameter and run arbitrary system commands via exec(). CVE-2026-57572 (disclosed mid-2026, fixed in v0.9.0) let an unauthenticated caller inject Chromium launch switches through browser_config.extra_args to spawn an attacker-controlled process — a partial denylist fix in v0.8.9 didn't fully close it. Both are documented candidly in the project's own SECURITY.md, which also lists a third fixed deserialization RCE (v0.8.1) and commits to a 48-hour acknowledgment and severity-tiered fix timeline. v0.9.0 (18 June 2026) changed the default posture: the Docker API now requires authentication and binds to loopback unless a token is explicitly configured, rather than shipping open by default. (Sources: github.com/advisories/GHSA-5882-5rx9-xgxp, ionix.io/threat-center/cve-2026-57572, github.com/unclecode/crawl4ai/blob/main/SECURITY.md)
Cost and what's actually priced
The library and Docker image are free under Apache 2.0 — no seat fees, no usage caps, no account required. The project's only current monetization is GitHub Sponsors, with published tiers from $5/month (support the project) to $2,000/month (a 'Data Infrastructure Partner' tier with dedicated support) — these buy sponsor recognition and, at higher tiers, direct maintainer access, not product features (github.com/sponsors/unclecode). A hosted 'Crawl4AI Cloud API' is announced as a closed beta with no public pricing; access is by application through a Google Form, and the vendor's own framing — 'drastically more cost-effective than any of the existing solutions' — is an unverified marketing claim with no numbers behind it yet.
Who's behind it, and what that means for continuity
Crawl4AI is led by Hossein Tohidi ('Unclecode' on GitHub/X), who is also the founder of Kidocode, an ed-tech company that appears in Crawl4AI's own sponsor list as a Gold-tier sponsor (github.com/unclecode/crawl4ai README). We found no evidence of institutional (VC) funding behind Crawl4AI itself, and no public information on team size beyond the maintainer and a small number of named contributors thanked in SECURITY.md. This is, as far as we can establish, a single-founder open-source project rather than a funded company — which is consistent with its extremely active commit history but also means there is no established institutional continuity plan if the maintainer stops.
One thing to check before you rely on their attribution language
The README states that using Crawl4AI 'requires' one of two attribution methods — a badge or a text credit — in your own documentation or product. The Apache 2.0 license itself (github.com/unclecode/crawl4ai/blob/main/LICENSE) only obligates preserving existing copyright and license notices when you redistribute the licensed source; it does not require a public 'powered by' badge on a downstream product built with the library. Teams with legal review processes should treat this as the maintainer's request, not a license term, when deciding whether to comply.
Independent reviews are thin
We could not find neutral, non-vendor-authored comparisons of Crawl4AI. Most comparison content found in search (Apify's blog, Bright Data's blog, Firecrawl's own 'alternatives' page, spider.cloud's benchmark post) is published by a competing scraping vendor and should be read as competitor marketing, not independent testing. We found no rating on Trustpilot, G2, or a comparable independent review site.
Crawl4AI price and terms
Terms
- Free plan
- YesYes
The terms in full
The Free hosted plan is presented as a standing no-card plan with 1,000 credits per month, 10 requests per minute, and two concurrent requests.
For AI agents
- MCP server
- YesChecked by us,
- API
- Yescrawl4ai.com,
Where these prices come from
crawl4ai.com, checked
All plans and limits
| Plan | Price | Concurrency | Credits | Rate limit |
|---|---|---|---|---|
| Free | $0 a month | 2 at a time | 1,000 every month | 10 a minute requests/minute |
| Starter | $10 a month | 10 at a time | 10,000 a month | 120 a minute requests/minute |
| Builder | $99 a month | 20 at a time | 125,000 a month | 600 a minute requests/minute |
| Scale | $499 a month | 50 at a time | 750,000 a month | 1,500 a minute requests/minute |
| Enterprise | Price on request | Not stated | Not stated | Not stated |
Read from crawl4ai.com.
What we checked on Crawl4AI
What the price counts
The hosted offering combines fixed monthly plan charges with included credits and separately priced extra credits.
Money enters through a monthly plan, and extra credits on a plan.
crawl4ai.com/docsChecked
Free to use
A standing hosted Free plan costs nothing, and the self-hosted crawler is also available without payment.
$0 · no card
crawl4ai.comChecked
Public API
The hosted service documents an authenticated HTTP interface for crawling, extraction, search, and related operations.
One key, plain JSON, one fast endpoint.
crawl4ai.com/docsChecked
MCP server
MCP server at api.crawl4ai.com, behind OAuth sign-in
https://api.crawl4ai.com/mcp
api.crawl4ai.com/.well-known/oauth-prot…Checked by us,
Open source
Apache-2.0 licence in its public repository
Apache License Version 2.0
github.com/unclecode/crawl4ai/blob/main…Checked by us,
Crawl4AI alternatives
Crawl4AI and TinyFish
Crawl4AI beside its alternatives: the price on each one's site and the day it was checked Tool Price Checked Crawl4AI Free, then $10 a month TinyFish Free, then $0.002 per minute
Questions about Crawl4AI
- How much does Crawl4AI cost?
- Crawl4AI has a free plan. Its paid plans include Starter at $10 a month, Builder at $99 a month and Scale at $499 a month. From crawl4ai.com/#pricing, checked 8 November 2026.
- Does Crawl4AI have an API or an MCP server?
- Crawl4AI has an API. From crawl4ai.com/docs, checked 29 October 2026. Crawl4AI has an MCP server. We checked api.crawl4ai.com/.well-known/oauth-protected-resource ourselves on 15 November 2026.
- Is Crawl4AI open source, and can you host it yourself?
- Crawl4AI is open source. We checked github.com/unclecode/crawl4ai/blob/main/LICENSE ourselves on 15 November 2026. You can host Crawl4AI yourself.
- What have we checked on Crawl4AI?
- 5 facts, under these headings: What it costs to start, how you build with it.
- How do we check Crawl4AI?
- We hold 5 facts on Crawl4AI, quoted from 8 pages. Facts last checked 15 November 2026. Price last checked 8 November 2026. Last change found 15 November 2026.
Repository
- Licence
- Apache-2.0
- Stars
- 85,621
- Last push
- 15 October 2026
Crawl4AI price history
Crawl4AI had a free plan, and paid plans from $10 a month, on all 4 of our reads, from 29 October 2026 to 8 November 2026.
| Price | Plan | First seen | Last seen | Readings | Source |
|---|---|---|---|---|---|
| $10 a month | Cheapest paid plan | 29 October 2026 | 8 November 2026 | 4 | Pricing page, read 29 October 2026 |
From our research, read twice since 29 October 2026, and 2 of our own checks since 30 October 2026. 2 more of our checks could not pick this price out of the page and are left out. A date is when we read the page, not when the price changed.
Similar in Agent tools and integrations
See all in Agent tools and integrations
- ERIUS PHONERented cloud Android phones, each in its own container, that keep an agent's apps and sign-ins between sessions.
- ClineFlowGit-native project memory and handoffs for coding agents.
- SmitheryPublic MCP server registry, now run by Arcade, listing direct vendor MCP URLs after its proxy shut down.
- UI DiscoveryA library of real websites, iOS apps and dashboards with each one's palette, fonts and original build prompt.
From our research
Is Crawl4AI yours?
Free, and the page then carries the verified owner mark. You confirm it with an email at crawl4ai.com. Claim this listing
Report an error if a fact is wrong.