Who it is forA channel owner reviewing whether a campaign or a content change raised discussion compared with the period before.
The problemJudging engagement by eye across weeks is unreliable, and manual counting from the app is slow.
The outcomeA comparison of comments, unique users, and comment reactions between the chosen period and the previous one.
What you need first
- Docker Desktop (recommended) or Python with the packages in requirements.txt
- Telegram API credentials: API_ID and API_HASH from https://my.telegram.org/apps
- A Telegram account session for Telethon, needed only for live exports
Steps
- Make sure a JSON export exists in
data/raw/, for example fromdocker compose run --rm cli export json. - Pick the period start and end dates. The end date is exclusive.
- Run
docker compose run --rm cli compare --from 2026-07-01 --to 2026-08-01 --file durov_dataset.jsonwith your own dates and file name. - Optionally open the dashboard and use the compare API at
/api/export/<name>/comparefor the same dates.
Prompt for your agent
In the TheMyxa/telegram-parser repo, run `docker compose run --rm cli compare --from <start-date> --to <end-date> --file <dataset-file>.json`. Expected output is the comment, user, and reaction counts for the period and the previous period. Verify that both date ranges match the requested dates before reporting.
Caveat. The comparison runs on the saved JSON file, so it reflects the export's state at the time it was last refreshed.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for TheMyxa/telegram-parser and "Compare comment and reaction activity across two periods"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer