ArchiveBox

Workflows the agent can manage

• archive URLs
• preserve research sources
• capture screenshots and PDFs
• browse historical snapshots

Agent operability

Editorial agent-readiness estimate: 4/5. This reflects documented interfaces and proposed workflows, not a successful installation or a support promise. Assessment date not recorded; verify upstream documentation before use.

• CLI — Official CLI supports adding URLs, managing archives and running the server
• UI-ONLY — Web administration and archive browsing are first-class supported surfaces

Evidence consulted

• Official README recommends Docker Compose and documents persistent /data storage plus CLI and web administration flows. [stated; https://github.com/ArchiveBox/ArchiveBox]
• Official project repository records the self-hosted web-archiving implementation and current installation methods. [stated; https://github.com/ArchiveBox/ArchiveBox]

Implementation notes

Use the upstream Docker Compose path, keep the archive on persistent storage with backup coverage, and enable only the capture methods needed for the user's retention goal.

Licence / edition: MIT Archiving third-party content does not grant rights to redistribute that content; users remain responsible for source-site and copyright obligations.

Resources: standard class — Official Docker Compose setup includes browser and archiving dependencies. CPU/RAM demand varies with capture methods, while disk usage grows directly with archive volume and media capture; storage planning matters more than a fixed memory baseline. (inferred)

External prerequisites: sufficient persistent disk for the intended archive

Security: Catalogue qualification is not a security certification; inspect current advisories, supported versions and deployment guidance before setup.