DM Sales Coach is a self-hosted Telegram bot that gives real-time sales coaching in DM conversations by remembering each prospect in its own forum topic, retrieving from a customizable sales knowledge base, and generating human-sounding reply options.

Stars

3

7-day growth

No data

Forks

0

Open issues

0

License

MIT

Last updated

2026-07-30

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It combines per-prospect memory, RAG over sales frameworks, and strict anti-AI writing rules into a self-hosted bot that learns your product through a chat interview rather than config files.

Who it is for

  • Sellers and founders who run sales conversations over Telegram DMs
  • Consultants and solo operators who want real-time reply coaching
  • Technical or sales teams willing to self-host a privacy-conscious AI assistant

Use cases

  • Pasting a prospect's latest message into a topic to get strategy and copy-paste-ready replies
  • Managing multiple prospects with per-client history, stage, temperature, and pain points
  • Teaching the bot your offer with /setup or /import and patching facts via /profile add
  • Improving coaching by adding your own sales transcripts and books to the knowledge base and re-ingesting

Strengths

  • Every prospect is a forum topic, so full history is included in every prompt and the bot tracks funnel state
  • Ships with 14 seed knowledge files covering SPIN, Voss, Cialdini, Hormozi, objection handling, pricing, and DM outreach; custom sources can be added
  • Hard anti-AI writing rules produce drafts that avoid tell-tale LLM patterns like em dashes, triads, and 'Hope this helps'
  • Self-hosted with two SQLite files, no inbound ports or webhook, and transparent cost estimates (~5-6 cents per default coaching reply)

Considerations

  • Requires your own Anthropic API key and incurs per-reply costs; an optional OpenAI key is needed for retrieval
  • Depends on Telegram forum topics and the bot being group admin with specific permissions; plain messages won't reach it otherwise
  • Without completing /setup or /import, replies contain placeholders like '[your price range]'; the bot is only as good as the profile you teach it

README quick start

DM Sales Coach

Русская версия →

A self-hosted Telegram bot that coaches you through sales conversations in DMs, in real time.

You paste what a prospect just wrote you. It replies with a read of what's actually going on, three copy-paste-ready reply options using different strategies, and the next move. Each prospect lives in its own Telegram forum topic, so the bot remembers the whole thread and tracks where they are in your funnel.

It learns what you sell by interviewing you in Telegram — seven questions, answered the way you talk. No company is baked into this repo, and you never have to edit a config file to teach it yours.

You  ──▶  [paste what the prospect said, into their topic]

Bot  ──▶  Arc: 2/4, short arc, warming fast
          Read: he's price-anchoring before scope. Answering now caps your ceiling.

          A — Reframe:        depends what we'd build. quick q: validating this, or scaling
                              something that already works?
          B — Anchor high:    most builds land $3-15k. giving you a number before I
                              understand the workflow would be guessing.
          C ★ — Light qualifier:  ballpark $3-15k. what's the actual task eating the
                              hours right now?

          Next: hold the line on no-price-before-scope. If he pushes again, he's qualified.

          📌 temp: 7  •  pain: manual invoice routing

Why it works

Three things, and the third is the one people skip:

  1. Per-prospect memory. Every prospect is a forum topic. Full history goes into every prompt, so advice on message 5 knows what happened on message 1.
  2. Retrieval over a sales knowledge base. Ships with 14 seed files covering SPIN, Voss, Cialdini, Hormozi, objection handling, pricing conversations, and DM outreach mechanics. Add your own books and saved DM transcripts on top.
  3. Hard anti-AI writing rules. No em dashes, no "not just X — it's Y", no triads, no "Hope this helps." The drafts are meant to look like a human typed them on a phone, because a prospect can smell an LLM in a DM.

Stack

  • aiogram 3 — Telegram bot framework
  • Claude — coaching generation, with prompt caching on the static prefix
  • OpenAI text-embedding-3-small — embeddings only, optional
  • SQLite + [sqlite-vec](https

Description

Self-hosted Telegram bot that coaches you through sales conversations in DMs. Interviews you about your business, then drafts replies that sound human. Claude + RAG, one process, your data stays yours.

Related repositories

Similar projects matched by category, topics, and programming language.

0xwilliamortiz
Featured
0xwilliamortiz GitHub avatar

openclaude-improved

OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.

AI & Machine LearningLarge Language Models
577
makecindy
Featured
makecindy GitHub avatar

cindy

Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.

AI & Machine LearningLarge Language Models
958
uzairansaruzi
Featured
uzairansaruzi GitHub avatar

hermex

Hermex is a native SwiftUI iPhone app that lets you control a self-hosted Hermes AI agent directly from your phone, with no subscriptions, tracking, or third-party relay.

AI & Machine LearningLarge Language Models
941