Documentation / 01
Search & Analyze a Saved Telegram Archive
Find the message. Check the source. Build the case.
Pull past messages of your enabled sources into the workspace.
Search, then open the saved message behind every hit.
Your analysis in one file, the signed evidence next to it.
Load past messages
- Sources → Chats in scope: check the enabled chats, start observation.
- Load full history. It takes the source list as it is right now.
- Pause history / Continue history any time. After a restart, resume by hand.
- Check results per source and the download queue, keep the signed progress report with the export.
This fills the workspace. A single-chat HTML/JSON export is a different thing. Details.
Search first, then decide about AI
- Journal searches locally, filter by source and time.
- Search a phrase or domain, open the record and its versions.
- For AI, the admin sets up a provider in Integrations. Then Ask the archive, pick chats and a period, look at Data sent to the model and untick what shouldn't go out.
- Check the citations, save the answer as a report, add your notes.
Search needs no AI. Reports keep their sources and revisions, apart from the signed journal. Provider setup.
Choose the connection you need
| Task | Open | Setup |
|---|---|---|
| Let an AI client read chosen chats | Integrations → MCP | Install MCP, make a scoped token, connect |
| Recognize text in saved media | A media.saved record → Recognize attachment | Set up the local Docker worker |
| Send events to n8n or a SIEM | Integrations → Outgoing webhooks | Add a receiver, check HMAC, dedupe IDs |
Which access token goes where?
Panel access is for people. MCP gets its own read-only tokens, webhooks their own HMAC secret. None of them needs a Telegram session.
Hand over sources and conclusions
Put the report next to the signed ZIP. The report is your reading of the sources, the ZIP is what the recipient verifies.