Limzo Telegram Group Stats

Call this for network-wide numbers across all public Telegram groups tracked by Limzo (group count, messages, active users, replies, reactions, karma — 7-day and all-time) plus durable lifetime totals (messages analyzed, members tracked, spam messages removed) and the current top groups by Limzo Score. For finding a specific group, prefer list_groups.

Call this when the user asks about the activity, health, leaderboard, mood, or trends of a specific Telegram group tracked by Limzo. `slug` is the last part of the group's public page URL, limzo.com/s/<slug> (e.g. "hipo"). Returns the curated limzo.public_stats/v1 JSON: messages, replies, active members, daily series, top members, mood, reactions, language mix, the Limzo Levels ladder (lifetime XP + badge tiers), and weekly-league standings when the group has the league enabled. Optional `range`: 7d (default), 30d, all — the wider ranges only serve real data for groups on a paid plan and otherwise silently fall back to 7d, so check `range.key` in the result. Never includes verbatim member messages. For a private group (one with no public t.me handle) the member identities, the group description and member_count are withheld too: aggregates plus an anonymised leaderboard are all it returns.

Call this to discover Telegram groups tracked by Limzo — to browse the directory, filter by language, or find a group's slug for get_group_stats. Optional `query` filters case-insensitively over group title, username, slug, and description. Optional `lang` (ISO 639-1, e.g. "fa", "es") keeps only groups where that language is a meaningful share of what members write — the way to answer "find active Persian/Spanish groups". Omit both to list the top groups by Limzo Score. The directory covers PUBLIC groups only — a group with no t.me handle is never listed, though it may still have a /s/ page. Each row carries a `language` mix (primary language + top languages as percentages); rows also include slug, title, username, plan, member_count, 7-day messages and active members, score and page URLs, plus `total_matches` so you can tell when more groups matched than were returned.