- name
- slacrawl
- description
- Pull Slack workspace metadata and message history into local SQLite for offline search and agent queries.
- homepage
- https://github.com/vincentkoc/slacrawl
- metadata
- {"clawdbot":{"emoji":"💬","os":["darwin","linux"],"requires":{"bins":["slacrawl"]},"install":[{"id":"release","kind":"github-release","repo":"vincentkoc/slacrawl","asset":"slacrawl_*_darwin_arm64.tar.gz","bins":["slacrawl"],"label":"Install slacrawl (GitHub release)"}]}}
Slacrawl
Go-based CLI that pulls Slack workspace data — channels, threads, messages — into a local SQLite database so an agent can search and inspect history without the Slack UI.
Requirements
- Slack token. Two supported modes:
- App token (recommended): create a Slack app at https://api.slack.com/apps with channels:history, groups:history, im:history, users:read scopes; install to your workspace; copy the user OAuth token (xoxp-…). - Cookie token (no admin needed): extract xoxc-… token + d cookie from a logged-in Slack browser session. See slacrawl README for details.
slacrawlbinary on PATH (installed at~/.local/bin/slacrawl).
Setup
slacrawl init # create config at ~/.slacrawl/config.toml
# edit ~/.slacrawl/config.toml — add token + workspace
slacrawl auth check # verify token works
slacrawl sync --full # initial workspace syncState
- Config:
~/.slacrawl/config.toml - Database:
~/.slacrawl/slacrawl.db
Common Commands
slacrawl status --json
slacrawl sync --incremental
slacrawl channels list --json
slacrawl messages list --channel <id> --limit 100 --json
slacrawl search "release notes" --json
slacrawl sql 'SELECT count(*) FROM messages'Integration Notes
- Strictly local-first: token + data never leave the machine.
- Schedule
slacrawl sync --incrementalon a PaperFang cron for continuous mirroring. - For multiple workspaces, run with
--workspace <name>against separate config profiles.