Inbox & communication

Ask Where You're Staying Next Week, Get an Instant Answer: Hermes Agent Reads His Bookings From a Local Email Database

  • Level Advanced
  • Setup1–3 hrs (estimated)
  • Evidence Some evidence
  • CostNot stated in source
  • No-codeNo
Hermes AgentSource-linked

What they did

Instead of having his agent search Gmail live, he syncs all his mail to a local IMAP server with mbsync. When a booking or purchase email arrives, a parser script (written once per merchant by a frontier model) adds it to SQLite. Asking Hermes 'what's the address of the place we're staying next week?' runs a quick SQL query instead of digging through emails. He says it's faster, cheaper, more reliable and avoids rate limits.

How it went

Instant answers about trips and purchases from a local database, without searching emails every time.

Worth knowing

  • Hacker News comment by sksksk (Oct 22, 2026 Denver time): Hermes Agent queries a SQLite table built from parsed booking/purchase emails synced locally with mbsync, which he finds faster and more reliable than live email search.
  • A local copy of all your mail is sensitive; encrypt the disk and keep the IMAP server local only.

Prompt

Cleaned version rewritten from the source — not a direct quote.

Help me set up a local copy of my email ([accounts]) with mbsync and a local IMAP server. Then, for booking and purchase emails from [merchants], write one parser per merchant that pulls date, place, address, confirmation number and price into a SQLite table. When I ask a travel or purchase question, answer by querying that table and cite the source email.

Recommended

Try it in Grok Bot

Grok Bot with email connected can keep a running bookings sheet the same way, adding each confirmation as it arrives.

  1. Copy the prompt (button below).
  2. Open Grok Bot chat and paste it. Replace any [bracketed] placeholders.
  3. Connect the listed tools (Gmail, Email) as connectors when Grok Bot asks.
  4. If the task repeats, ask: "Make this a daily routine."

Alternatives: the same prompt works in Hermes Agent, Claude, ChatGPT Agent, OpenClaw.

Set it up

Tools: Gmail, Email · Stack: Hermes Agent + local IMAP (mbsync) + SQLite

  1. Read the original source for full context.
  2. Connect the tools your agent needs.
  3. Paste the prompt and replace [bracketed] placeholders.
  4. Run once manually and check the output before scheduling it.

Generic suggested steps, not from the source.

Evidence

Hacker News comment by sksksk (Oct 22, 2026 Denver time): Hermes Agent queries a SQLite table built from parsed booking/purchase emails synced locally with mbsync, which he finds faster and more reliable than live email search. A local copy of all your mail is sensitive; encrypt the disk and keep the IMAP server local only

Source: HN · 2026-10-22 · Verified by us: not yet · Report broken or outdated

Related use cases

Inbox & communicationX · 2026-10

Ask your bot for a security review of an email that passed every check

An email from [email protected] landed in a Tesla engineer's inbox. It passed SPF, DKIM and DMARC (the checks that confirm who sent an email) and showed the blue check, but something felt off, so he asked his Grok Bot to do a security review. It found a hidden phishing link, explained why every safety check had passed, and wrote a report to xAI with a proposed fix. He then had it add a security routine that checks his email for anything phishy going forward.

  • Level Beginner
  • Setup~30 min*
  • Evidence Strong evidence
Grok BotSource-linkedBeginner-friendly
CodingX · 2026-10

Hermes Agent Nearly Doubled Speech-to-Text Accuracy on Hard Words: 99 to 183 of 240

A user turned his 15K saved Wispr Flow dictations into a test set for the local Whisper model behind his Hermes Agent. The agent turned his Wispr dictionary into a hint list, diffed raw vs corrected text to find words Whisper keeps mishearing, made find-and-fix rules, and tested every rule against the full history. With no fine-tuning, dictionary words went from 99/240 to 183/240 on Wispr clips and 19/45 to 43/45 on sentences he read aloud. It now archives the data nightly and looks for new fixes weekly.

  • Level Advanced
  • Setup1–3 hrs*
  • Evidence Strong evidence
Hermes AgentSource-linked
Inbox & communicationX · 2026-01

Clear a DM backlog and review docs in 2 hours

Within 2 hours, Claude Cowork answered 42 Telegram DMs asking for intros, revised 3 pitch decks, and reviewed 9 drafts with inline comments.

  • Level Beginner
  • Setup~30 min*
  • Evidence Some evidence
Claude CoworkSource-linkedBeginner-friendly