MarkItDown vs Crawl4AI

A label partly reflects how much of each tool is visible and scannable, not only how risky it is. A tool without a lockfile cannot get a dependency check.

• MarkItDown: code and instruction-file checks found nothing, but there is no runtime lockfile or manifest, so dependencies were not checked
• Crawl4AI: 29 critical-severity known vulnerabilities in runtime dependencies (OSV)

MarkItDown scores 2 points higher in Week 45: MarkItDown 54, Crawl4AI 52 out of 100. The score combines maintenance, adoption and docs (percentiles of public GitHub signals): MarkItDown 16, 83 and 69; Crawl4AI 37, 56 and 69. Community (20% weight) is not measured yet. It is not a hands-on test, so a higher score does not say which tool suits your project.

Safety labels from the automated scan of 2 Nov 2026: MarkItDown: No dependencies scanned, code checks clean, no lockfile to check; Crawl4AI: Caution, 29 critical-severity known vulnerabilities in runtime dependencies (OSV). “No dependencies scanned” means the code checks were clean but there is no lockfile, so dependencies could not be checked; it is not a clean bill. It is an automated scan, not a manual audit.

By GitHub stars: MarkItDown 193,454, Crawl4AI 86,744. Adoption score (percentile among all 52 tracked tools): MarkItDown 83, Crawl4AI 56. Stars are one public signal and do not measure real-world use.

MarkItDown: MIT; Crawl4AI: Apache-2.0. Read each licence text before commercial use.

Pick MarkItDown if you want the more widely adopted option (adoption 83). Pick Crawl4AI if recent activity and releases matter most to you (maintenance 37). This comes from measured public data and licences only, not from hands-on testing.