{ "schema_version": 1, "generated_at": "2026-10-22T00:00:00.000Z", "canonical_url": "https://openlogs.fyi/tools/archivebox", "slug": "archivebox", "name": "ArchiveBox", "tagline": "Saves web pages and bookmarks as HTML, PDF and media for later.", "replaces": { "summary": "Paid web page archiving services, such as Pinboard.", "products": [ { "slug": "pinboard", "name": "Pinboard", "vendor": "Pinboard", "url": "https://openlogs.fyi/alternatives/pinboard" } ] }, "stack": [ { "kind": "language", "name": "Python" } ], "deployment_methods": [ "docker_compose" ], "requirements": { "min_ram_mb": null, "min_cpu_cores": null, "source_url": null }, "license": { "spdx": "MIT", "class": "osi", "source_url": "https://github.com/ArchiveBox/ArchiveBox/blob/c55089eaefcacf3439322eec897763f518588f37/LICENSE" }, "business_model": { "value": "unknown", "notes": "The README at the pinned commit does not state a business model, so it stays unknown.", "source_url": "https://github.com/ArchiveBox/ArchiveBox/blob/c55089eaefcacf3439322eec897763f518588f37/README.md", "checked_at": "2026-10-22" }, "difficulty": { "value": "medium", "reason": "1 service, 2 volume mounts, 4 env values to set, no elevated host access. Heuristic score 3 of 11: medium." }, "repository": { "owner": "ArchiveBox", "name": "ArchiveBox", "url": "https://github.com/ArchiveBox/ArchiveBox" }, "compose_check": { "status": "config_ok", "validated_at": "2026-10-22", "summary": "config_ok on 2026-10-22" }, "recipe": { "version": 1, "source_path": "docker-compose.yml", "source_repo": "ArchiveBox/ArchiveBox", "source_commit_sha": "c55089eaefcacf3439322eec897763f518588f37", "source_kind": "app_repo", "source_url": "https://github.com/ArchiveBox/ArchiveBox/blob/c55089eaefcacf3439322eec897763f518588f37/docker-compose.yml" }, "install_steps": [ { "order": 1, "kind": "prerequisite", "language": "text", "label": "Docker with the Compose plugin", "body": "A host with Docker and the Docker Compose plugin. This entry runs from a compose file.", "source_url": "https://github.com/ArchiveBox/ArchiveBox/blob/c55089eaefcacf3439322eec897763f518588f37/docker-compose.yml", "validation_status": "unvalidated" }, { "order": 2, "kind": "compose", "language": "yaml", "label": "Save the compose file as docker-compose.yml", "body": "# Usage\n#\n# mkdir -p ~/archivebox/data && cd ~/archivebox\n# curl -fsSL 'https://docker-compose.archivebox.io' > docker-compose.yml\n# docker compose up -d\n# Open /admin/ on the hostname or IP used to reach ArchiveBox e.g: http://admin.archivebox.localhost:5797/\n#\n# docker compose exec archivebox archivebox add --depth=1 'https://news.ycombinator.com'\n# docker compose exec -T archivebox archivebox add < ~/Downloads/bookmarks.txt\n# docker compose exec archivebox archivebox help\n#\n# More Info: https://github.com/ArchiveBox/ArchiveBox/wiki/Docker#docker-compose\n\nservices:\n archivebox:\n image: ${ARCHIVEBOX_IMAGE:-archivebox/archivebox:latest}\n restart: unless-stopped\n ports:\n - \"${ARCHIVEBOX_PORT:-5797}:5797\"\n volumes:\n - ./data:/data # Required: main data directory must be on a fast local SSD\n # - /mnt/archivebox/data/archive:/data/archive # Optional: store the bulky data/archive content on a slower HDD or remote network store\n - tmp:/tmp/archivebox # lets one-off `docker compose run` commands reuse main server's runners\n environment:\n # - ADMIN_USERNAME=admin # optional admin user to create on first run, skips first-time setup admin creation UI\n # - ADMIN_PASSWORD=SomeSecretPassword\n - BASE_URL # canonical URL users will access this server at, can be set up via first-run wizard in the UI as well\n - SERVER_SECURITY_MODE # defaults to \"auto\", can be set up via first-run wizard in the UI as well\n - PUBLIC_ADD_VIEW=False # set to True to allow anonymous users to submit new URLs to archive\n - ARCHIVEDOTORG_ENABLED=True # set to False if you dont want to send URLs to Archive.org\n - PUID # optional numeric UID for NFS/CIFS/FUSE mounts (defaults to collection owner or 911)\n - PGID # optional numeric GID for NFS/CIFS/FUSE mounts (defaults to collection group or 911)\n # For all other options, it's better to use data/ArchiveBox.conf or the new Personas config feature in the admin UI...\n # - TIMEOUT=60\n # - CHECK_SSL_VALIDITY=False # settings here data/ArchiveBox.conf to be able to edit it in the UI\n # - USER_AGENT=\"...\" # ... move any settings like these into \n # ...\n # For more info, see: https://github.com/ArchiveBox/ArchiveBox/wiki/Docker#configuration\n shm_size: 1gb # chrome runs better when it can use a decently sized shm pool\n pids_limit: 2048 # avoids low systemd task caps with Chrome and parallel extractors\n\n\n####################################################################################################################\n ### No Separate containers are needed for sonic or scheduled archiving, these are all optional addons: ###\n\n ### Optional: HTTPS ingress using Cloudflare\n # https://developers.cloudflare.com/tunnel/reference/run-parameters/\n #\n # cloudflared:\n # image: cloudflare/cloudflared\n # command: tunnel --no-autoupdate --loglevel debug --retries 15 --protocol http2 --overwrite-dns --url http://archivebox:5797 --hostname archivebox.io --name archivebox.io\n # volumes: # ^ (replace archivebox.io with your own domain)\n # # Download a cert.pem into this folder from https://dash.cloudflare.com/argotunnel\n # - ./etc/cloudflared:/etc/cloudflared\n \n\n ### Optional: ArchiveBox Bot + ArchiveBox AI Bot: save links and run archiving tasks from Slack, WhatsApp, etc.\n # https://github.com/ArchiveBox/archivebox-chat-bot\n #\n # archivebox-chat-bot:\n # build: https://github.com/ArchiveBox/archivebox-chat-bot.git#main\n # restart: unless-stopped\n # ports:\n # - \"127.0.0.1:5798:5798\"\n # # Open http://localhost:5798, choose a console password, then connect to http://archivebox:5797 with your API key.\n # volumes:\n # - ./archivebox-chat-bot:/data\n # # Optional: set ADMIN_PASSWORD to skip the first-run password setup UI.\n # # environment:\n # # ADMIN_PASSWORD: your-console-password\n\n\n ### Optional: container to run xvfb+noVNC so you can watch the ArchiveBox browser screen as it archives things /\n # remote control it to set up a chrome profile w/ logins for sites you want to archive\n # \n # https://github.com/ArchiveBox/ArchiveBox/wiki/Chromium-Install#setting-up-a-chromium-user-profile\n # https://github.com/ArchiveBox/ArchiveBox/wiki/Chromium-Install#docker-vnc-setup\n #\n # novnc:\n # image: theasp/novnc:latest\n # environment:\n # - DISPLAY_WIDTH=1920\n # - DISPLAY_HEIGHT=1080\n # - RUN_XTERM=no\n # healthcheck:\n # test: [\"CMD\", \"xdpyinfo\", \"-display\", \":0\"]\n # interval: 2s\n # timeout: 2s\n # retries: 10\n # ports:\n # # to view/control ArchiveBox's browser, visit: http://127.0.0.1:8080/vnc.html\n # # restricted to access from localhost by default because it has no authentication\n # - 127.0.0.1:8080:8080\n\n\n ### Optional: VPN to your home IP to avoid rate limits and captchas\n # https://tailscale.com/docs/features/containers/docker/how-to/connect-docker-container\n # tailscale:\n # image: tailscale/tailscale:latest\n # cap_add:\n # - net_admin\n # - net_raw\n # environment:\n # - TS_AUTHKEY=\n # - TS_STATE_DIR=/var/lib/tailscale\n # volumes:\n # - ./tailscale:/var/lib/tailscale\n # restart: unless-stopped\n\n ### Optional: Run ChangeDetection.io to watch for changes to websites, then trigger ArchiveBox to archive them\n # https://github.com/ArchiveBox/ArchiveBox/wiki/Change-Detection\n #\n # changedetection:\n # image: ghcr.io/dgtlmoon/changedetection.io\n # volumes:\n # - ./data-changedetection:/datastore\n\n\n### Optional: Set up remote network storage for your ./data/archive bulky files (to S3, B2, Google Drive, OneDrive, SFTP, etc.)\n# Follow the steps here to set up the Docker RClone Plugin https://rclone.org/docker/\n# https://github.com/ArchiveBox/ArchiveBox/wiki/Setting-Up-Storage\n#\n# $ docker plugin install rclone/docker-volume-rclone:amd64 --grant-all-permissions --alias rclone\n# $ nano /var/lib/docker-plugins/rclone/config/rclone.conf\n# [examplegoogledrive]\n# type = drive\n# scope = drive\n# drive_id = 1234567...\n# root_folder_id = 0Abcd...\n# token = {\"access_token\":...}\n#\n# volumes:\n# archive:\n# driver: rclone\n# driver_opts:\n# remote: 'examplegoogledrive:archivebox'\n# allow_other: 'true'\n# vfs_cache_mode: full\n# poll_interval: 0\n\n\nvolumes: # if you run multiple archivebox containers (or run multiple \"docker run\" commands)\n tmp: # this lets them share a single orchestrator instead of fighting over which one is the leader\n", "source_url": "https://github.com/ArchiveBox/ArchiveBox/blob/c55089eaefcacf3439322eec897763f518588f37/docker-compose.yml", "validation_status": "config_ok" }, { "order": 3, "kind": "env", "language": "text", "label": "Set the values the compose file needs", "body": "These variables have no default in the compose file: BASE_URL, PGID, PUID, SERVER_SECURITY_MODE. Compose reads them from the shell or from a .env file next to the compose file.", "source_url": "https://github.com/ArchiveBox/ArchiveBox/blob/c55089eaefcacf3439322eec897763f518588f37/docker-compose.yml", "validation_status": "unvalidated" }, { "order": 4, "kind": "shell", "language": "bash", "label": "Start it", "body": "docker compose up -d", "source_url": "https://github.com/ArchiveBox/ArchiveBox/blob/c55089eaefcacf3439322eec897763f518588f37/docker-compose.yml", "validation_status": "unvalidated" }, { "order": 5, "kind": "verify", "language": "text", "label": "Open the app", "body": "Open http://localhost:5797. The compose file publishes host port 5797 for the archivebox service.", "source_url": "https://github.com/ArchiveBox/ArchiveBox/blob/c55089eaefcacf3439322eec897763f518588f37/docker-compose.yml", "validation_status": "unvalidated" } ], "notes": [ { "kind": "gotcha", "title": "Some images use the latest tag or no tag", "body": "Images without a pinned version: archivebox: ${ARCHIVEBOX_IMAGE:-archivebox/archivebox:latest}. A later pull can get a different version.", "source_url": "https://github.com/ArchiveBox/ArchiveBox/blob/c55089eaefcacf3439322eec897763f518588f37/docker-compose.yml", "checked_at": "2026-10-22" }, { "kind": "gotcha", "title": "The compose file publishes host ports", "body": "Host ports: 5797 (archivebox). A port without a host address listens on all host network interfaces.", "source_url": "https://github.com/ArchiveBox/ArchiveBox/blob/c55089eaefcacf3439322eec897763f518588f37/docker-compose.yml", "checked_at": "2026-10-22" }, { "kind": "gotcha", "title": "The compose file mounts host folders", "body": "Host paths mounted into containers: ./data at /data (archivebox).", "source_url": "https://github.com/ArchiveBox/ArchiveBox/blob/c55089eaefcacf3439322eec897763f518588f37/docker-compose.yml", "checked_at": "2026-10-22" } ], "signals": { "captured_at": "2026-10-22", "stars": 28843, "forks": 1621, "open_issues": 157, "last_push": "2026-10-20", "days_since_push": 1, "latest_release": "v0.9.73", "latest_release_date": "2026-10-06", "days_since_release": 15 }, "links": { "html": "https://openlogs.fyi/tools/archivebox", "markdown": "https://openlogs.fyi/tools/archivebox.md", "json": "https://openlogs.fyi/tools/archivebox.json" }, "updated_at": "2026-10-22" }