DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to answer website chat and messaging apps from one assistant with Tel Agent

Serve web chat, WhatsApp, Telegram, email and SMS from a single AI assistant with notifications for staff.

Credentials. Each platform needs your own credentials, so treat WhatsApp, Telegram, Twilio and email tokens as secrets and keep them out of shared files.

Who it is forA support or sales lead whose customers write in through web chat, WhatsApp, Telegram, email or SMS and need one place to answer.

The problemMessages from different platforms arrive in separate inboxes, and replies are slow or inconsistent.

The outcomeEach conversation is answered by the AI assistant, stored in the conversation archive, and flagged in the notification tray so a person knows someone wrote in.

What you need first

  • Docker, or a native installer from the releases page (Windows, macOS or Linux)
  • API keys for an STT provider, an LLM and a TTS provider (or a GPU for local models)
  • For phone calls: a SIP endpoint such as a PBX extension, a SIP-registering router, or an ATA for analog lines, on the same LAN as the PBX
  • Network access to the PBX on 5060/UDP and an open RTP port range

Steps

  1. Clone the repo with git clone https://github.com/Dpro-at/Tel-Agent.git and run cp .env.example .env.
  2. Set ENCRYPTION_KEY in .env using openssl rand -hex 32, then start with docker compose up -d --build.
  3. Open http://localhost:38471, create the administrator, and add your own credentials for each channel you want, such as WhatsApp, Telegram or Twilio for SMS.
  4. Create an assistant and add knowledge and catalogue entries so it can answer common questions.
  5. Send a test message on each connected channel and confirm the reply streams and appears in the conversation archive.
  6. Check the notification tray to confirm staff are alerted to new messages.

Prompt for your agent

Using the Dpro-at/Tel-Agent repo, set up the messaging channels listed in the README for <channel names> with customer-owned credentials. Expected output: a test message on each channel that gets an AI reply and shows in the conversation archive and notification tray. Verify that each channel credential is stored and that the dashboard API docs load at http://localhost:38472/docs.

Caveat. The README says the channels are wired, but you must configure each one with your own provider credentials before it works.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page