beavergram
A read-only Telegram client that keeps everything. A userbot on your own account logs every incoming message into Postgres, including the ones later deleted or edited, along with media, reactions, presence and stories. A web client reads that archive back, and an MCP server hands it to agents.
Useful on its own: a Telegram where nothing disappears. In the beaver setup it is one of the agent's hands - the dispatcher reads chat history by the chat_id stored in a person's card.
What it keeps
- Messages with edits as versions and deletions as flags, so a message removed in Telegram is still in the archive with its history.
- Media on disk, content-addressed, with the versions of a replaced photo.
- Voice transcribed through Telegram's own transcription (Premium), queued when the quota runs out.
- Presence as a time series (TimescaleDB), read receipts, stories.
- Capture policy from your Telegram folders with per-chat overrides: channels nothing, groups messages only, private chats everything, by default.
- Annotations and watches: your notes on chats and rules that fire alerts, both yours to write in the web client.
Nothing is ever deleted from the archive.
Parts
backend/-userbot(kurigram, the capture loop and jobs) andapi(FastAPI: the web API, the MCP server, and the built frontend as static files).frontend/- SvelteKit,adapter-static; a chat client over the archive: folders, chat list, thread with media, versions and the deleted messages inline, search, stories, presence graphs.docker-compose.yml- includesbackend/(Postgres with TimescaleDB,userbot,api) andfrontend/(the dev server); profilesexternalandservices.
MCP
Read-only: search_messages_tool, list_chats, get_chat_history (with deleted messages included), get_deleted_messages, get_message_versions, get_media, get_callbacks, presence_history, get_peer_history, get_stories, get_annotations, list_watches, list_alerts. The one write is set_watch. There are no send, edit or delete tools and there will not be.
Run
make env # .env and docker-compose.override.yml from the examples
make -C backend session # log the account in once; the session file stays in backend/sessions
make deploy # build what changed, migrate, start the containers
COMPOSE_PROFILES in .env selects what runs on the machine, docker-compose.override.yml in each part holds the published ports and the caddy network aliases. The web client and the MCP endpoint are served by api; the bearer for both is AUTH__TOKEN.
Develop
make fmt
make check
make -C frontend dev