REPLACEMENT BRIEF

customer support

Can AI replace Eloqra?

EDITORIAL ANSWERKINDACurated prompt

The widget half takes one sitting: a script tag, a socket, and a bot that relays messages to your Telegram. The operator half does not. Juggling several conversations needs a real inbox, which in Telegram means a Mini App with its own auth, viewport, and text-selection quirks, all learned slowly on a phone.

One script tag injects a chat widget into your site, messages arrive in your Telegram, and replying to the bot message replies to the visitor · one conversation at a time.

Build the personal version →

AT A GLANCE

price
$4.99/mo
listed annual price
$59.88/yr
replaceable scope
One script tag injects a chat widget into your site, messages arrive in your Telegram, and replying to the bot message replies to the visitor · one conversation at a time.
build time
multi-day
Build promptreviewed prompt · not run

the prompt

Curated prompt
Build me a self-hosted live-chat widget whose inbox is Telegram. Requirements:

- Stack: a single Node + TypeScript service (Fastify) with SQLite via better-sqlite3.
  No Docker, no separate frontend build, no accounts system.
- Embeddable widget: GET /widget.js returns a script that injects a launcher button and
  chat panel into any page via one tag with data-site-id, rendered in a shadow DOM so the
  host page's CSS can't leak in. No iframe. Read theme (light/dark), accent color, and
  corner position from data- attributes.
- Transport: a websocket (ws) between visitor and server, with a long-poll fallback when
  the socket won't open. Persist every message. Give the visitor a signed cookie id so
  their thread survives a reload.
- On a conversation's first message, capture page URL, referrer, and user agent parsed to
  device/browser/OS, plus coarse IP geolocation from a free API.
- Telegram: a grammY bot posts each new conversation to OWNER_CHAT_ID with that visitor
  context. The operator answers using Telegram's native reply-to-message · map the
  replied-to message id back to its conversation and push the text to the visitor live.
- Typing indicators in both directions, and an optional pre-chat form (name + email)
  toggled per site.
- An /admin page behind basic auth listing conversations, each full thread, and a reply box,
  so the widget still works when Telegram is unreachable.
- Secrets in .env: BOT_TOKEN, OWNER_CHAT_ID, ADMIN_PASSWORD, ALLOWED_ORIGINS for CORS.
- Ship a README with the exact snippet to paste and VPS deploy steps (systemd + Caddy for
  TLS, since websockets need it).
- Deliberately out of scope: a phone operator console. That is a Telegram Mini App, a
  second project with its own rules (initData HMAC auth, viewportStableHeight sizing,
  safe-area insets); budget separate days for it. Also out: multiple operators,
  billing, canned replies, AI autoresponders, and analytics dashboards.
Copy or open in an agent

The prompt stays readable first. Choose a launch option when you are ready.

$ open in your agent (prompt prefilled, you press enter) or copy it raw

what AI can build

One script tag injects a chat widget into your site, messages arrive in your Telegram, and replying to the bot message replies to the visitor · one conversation at a time.

The prompt was editor-reviewed; no completed build is recorded.

The honest tradeoff

why people still pay

For a single site, nobody needs to pay: the hosted tier is free with unlimited conversations and the full Telegram inbox. The comparison is your weekend plus a server, TLS renewals, and reconnect logic against zero dollars. The only solid reason to build is wanting visitor chats on your own hardware.

what you lose

a real operator inbox · the Mini App console with a combined thread list across sites, unread badges, typing indicators and deep links from a notification straight into the conversation · bot replies cover one chat at a time, not five at once

the week you spend learning Telegram's webview rather than writing features · initData HMAC auth, sizing from viewportStableHeight because dvh overshoots, two safe-area insets to stay clear of the status bar in fullscreen, and text selection disabled so copying a message needs a hand-rolled long-press

a free tier · you would be spending days plus a monthly VPS bill to replace something that costs nothing for one site

everything that isn't the happy path · socket reconnects, duplicate sends, message ordering on flaky mobile networks, Telegram rate limits and retry queues, bot token rotation

always-on hosting · your widget is dead whenever your box, your TLS cert, or your websocket is, and a chat that silently stops connecting reads to visitors as you ignoring them

Start with existing software

prior art · use these instead of building, if you'd rather

EVIDENCE LEDGER

What this page can prove

The verdict judges replaceability. The evidence level records what DeepFeather actually checked.

Read the methodology →
evidence level
Curated prompt

The prompt was editor-reviewed; no completed build is recorded.

replacement boundaryOne script tag injects a chat widget into your site, messages arrive in your Telegram, and replying to the bot message replies to the visitor · one conversation at a time.

known limits · a real operator inbox · the Mini App console with a combined thread list across sites, unread badges, typing indicators and deep links from a notification straight into the conversation · bot replies cover one chat at a time, not five at once; the week you spend learning Telegram's webview rather than writing features · initData HMAC auth, sizing from viewportStableHeight because dvh overshoots, two safe-area insets to stay clear of the status bar in fullscreen, and text selection disabled so copying a message needs a hand-rolled long-press

editorial reviewawaiting manual review

BUILD FEEDBACK

Did you try this build?

Report the outcome. Submissions enter a manual evidence queue and never auto-upgrade the verdict.

questions

Can AI replace Eloqra?

Possibly for a narrower core workflow, but this catalog judgment is not a verified build. Expected gaps include: a real operator inbox · the Mini App console with a combined thread list across sites, unread badges, typing indicators and deep links from a notification straight into the conversation · bot replies cover one chat at a time, not five at once, the week you spend learning Telegram's webview rather than writing features · initData HMAC auth, sizing from viewportStableHeight because dvh overshoots, two safe-area insets to stay clear of the status bar in fullscreen, and text selection disabled so copying a message needs a hand-rolled long-press. Validate the prompt against your own acceptance criteria before committing.

How much does Eloqra cost?

Eloqra is listed at about $4.99/month (Pro, checked 2026-07-31), or $59.88 per year. This is a pricing reference, not evidence of a completed replacement or realized savings.

What do I lose by replacing Eloqra?

Honestly: a real operator inbox · the Mini App console with a combined thread list across sites, unread badges, typing indicators and deep links from a notification straight into the conversation · bot replies cover one chat at a time, not five at once; the week you spend learning Telegram's webview rather than writing features · initData HMAC auth, sizing from viewportStableHeight because dvh overshoots, two safe-area insets to stay clear of the status bar in fullscreen, and text selection disabled so copying a message needs a hand-rolled long-press; a free tier · you would be spending days plus a monthly VPS bill to replace something that costs nothing for one site; everything that isn't the happy path · socket reconnects, duplicate sends, message ordering on flaky mobile networks, Telegram rate limits and retry queues, bot token rotation; always-on hosting · your widget is dead whenever your box, your TLS cert, or your websocket is, and a chat that silently stops connecting reads to visitors as you ignoring them. If any of those are load-bearing for you, keep paying.

Is there an open-source alternative to Eloqra?

Yes — Chatwoot (self-hostable customer engagement suite · far heavier, but open source and battle-tested). Using prior art is also a valid exit; the prompt is for when you want it exactly your way.