⚡ Launch in 5 minutes · no developers needed

AI assistant for business:
calls, chats and leads — 24/7

Sekretar24 is a virtual AI assistant for your business. It replies to customers on Telegram, WhatsApp, your website and over the phone, works from your knowledge base and pushes hot leads straight into your CRM.

No credit card · Full-feature trial · Cancel in one click

Works on:
Telegram WhatsApp Web widget Telephony Android

Every unanswered chat is lost revenue

📵

Missed call = lost customer

Nights, weekends, lunch breaks — calls go unanswered and prospects move on to your competitor.

🐌

Your team replies in an hour

By the time they get back, the customer has cooled off or already bought elsewhere. Reply speed wins deals.

🔁

Half the day goes to repeat questions

The same FAQs, manual qualification, copy-pasting into CRM — instead of selling and growing.

Sekretar24 answers instantly and 24/7 across every channel, qualifies the lead and creates a deal in your CRM — so your team can focus on what matters.

AI Employees

One engine — any role

From a single platform you can build an AI employee for any job — with its own prompt, knowledge base, voice and integrations. Proven scenarios:

📞

Call center

Inbound and outbound calls, speech recognition, voice replies, lead qualification, smooth handoff of complex cases to a human.

🛠️

Tech support

24/7 L1 line on Telegram, WhatsApp and your website chat. Answers from your knowledge base, ticketing, escalation to engineers, quality analytics.

📇

Secretary

Phone reception, booking meetings into Google Calendar, spam filtering, reminders, conversation and email summaries.

⚖️

Lawyer

Legal advice grounded in an up-to-date base (codes and case law for RU and KZ), contract review, document templates.

📊

Accountant

Answers on taxes and reporting, USN/VAT calculations, deadline reminders, first-pass document processing.

💼

Sales manager

Sales funnel on Telegram, WhatsApp and your widget, qualification, upsells, accepting payments, amoCRM integration.

🎨

Web agency

AI briefs, generating spec docs, stack selection, landing-page prototyping, ongoing client-site support.

👨‍💻

Dev team

Bridge to Claude Code: writes and reviews code, works with git, runs tests and deploys — right from chat.

Need a role that isn't on the list? Get in touch — we'll build one for your case.

How it works

From sign-up to a working assistant in one evening

1

Sign up

Create an account — your 14-day free trial starts immediately.

2

Configure the assistant

Pick a ready-made role, upload your knowledge base, set the prompt and voice.

3

Connect your channels

Telegram, WhatsApp, web widget and telephony — all in a few clicks.

4

Runs 24/7

Your assistant replies around the clock; hot leads fly straight into your CRM.

Features

Not a scripted bot — real AI

🤖

Best AI — Claude

By default runs on Claude by Anthropic — the smartest and most steerable model on the market. On request: GPT-4, Gemini, DeepSeek, Qwen, Llama or your own local model.

🧠

Knowledge base (RAG)

Upload documents, websites or RSS — your assistant answers strictly from your data, not hallucinations.

🎙️

Voice

Speech synthesis and voice cloning — your assistant sounds like a real member of your team.

🔒

Local and cloud AI

Run on cloud models or deploy the AI on your own server — data never leaves your perimeter.

🔗

Integrations

amoCRM, WooCommerce, Google Calendar, Drive and Gmail — your assistant lives inside your tools.

🌍

Multilingual

Russian, English and Kazakh — your assistant speaks to customers in their language.

🎯

Fine-tuning

LoRA fine-tuning on your data — the assistant picks up your company's tone and expertise.

Sekretar24 vs a regular chatbot

Regular botSekretar24
Understands speechrigid scenario treefree text, Claude AI
Knowledge basepreset answersyour documents (RAG)
Channelsusually oneTelegram, WhatsApp, web, phone
Voicenonespeech rec + synth + clone
Self-hostednoyes, MIT, GitHub

Open-source · MIT

Fully open-source. No lock-in

All Sekretar24 code is published on GitHub under the MIT license — download it, deploy on your own server and use it for free. Any Linux server with Docker and root SSH access is enough.

🆓

Download from GitHub

Open source, MIT license. Free forever. Modify for your niche.

Open on GitHub
📚

Detailed documentation

Repo wiki: installation, deployment, LLM setup, RAG, telephony, bots and integrations.

Open Wiki

🔒 Self-hosted means customer data stays on your server. Run on free OpenRouter models or plug in your own Claude/GPT-4 key.

Live example

What a real conversation looks like

The assistant grasps the question, asks clarifying details and drives the customer to the next action — booking, request or payment. No "command not recognized", no menu trees.

Try it with your own questions

📱 Android app

Sekretar24 — in your pocket

Native Android app. Voice chat with your assistant, push notifications for new messages and app updates, access to all your chats — from anywhere.

  • ✓ All your AI chats in one app
  • ✓ Voice input and TTS answers
  • ✓ Push notifications for new messages and app updates
  • ✓ Attach photos, PDFs, documents into the context
  • ✓ Shared team chats (admin / user roles)
  • ✓ Warm-brown dark theme
  • ✓ Open-source: source code on GitHub
📲 Download APK · v2.2

Android 8.0+ · auto-updates via push · free

💡 On iPhone our mobile browser version (PWA) works fully — all assistant features are available without installation. Native iOS app is on the roadmap.

Pricing

One assistant, every channel — one subscription

From freelancer to agency: cloud bots and widgets, local AI and on-premise — for any budget.

Monthly Yearly −20%

Start

For freelancers & bloggers

2 900 ₽/mo

billed monthly

Try free
  • 1 AI assistant with unlimited roles
  • Ready-made: ⚖️ lawyer and 📊 accountant
  • Coming soon: SMM manager, tax advisor for freelancers, short-video scriptwriter, SEO/copywriter/ad specialist
  • Channels: Telegram + web widget
  • Knowledge base (RAG) and conversation memory
  • Cloud AI: Claude + free OpenRouter models
  • 1 user · chat support

Team

Local AI and on-premise

On request

Pricing = setup + ongoing support

Talk to sales
  • Local models on your hardware (Qwen, Llama, DeepSeek via vLLM)
  • Deployment on your server or by custom spec
  • Voice and telephony (SIM7600 or SIP) — no cloud
  • Voice cloning · LoRA fine-tuning for your industry
  • Closed perimeter: customer data never leaves your network
  • Integrations with 1C and your internal APIs
  • Onboarding, support and SLA tailored to your scenario

After the trial

Trial ends — your assistant keeps working

The 14-day free trial runs on Claude by Anthropic — the market flagship. After the trial you pick one of two paths:

💎 Stay on Claude

Business+ subscription — max answer quality, best reasoning, long context.

🆓 Free powerful models

Switch to OpenRouter: DeepSeek R1, Llama 3.3 70B, Qwen 2.5 72B and more. The chain is configured from strongest to weakest — if the top model hits a rate limit, the assistant automatically falls back to the next one. No downtime.

💡 Free models cover most business tasks. Paying for the top tier makes sense only when you need complex reasoning and maximum expertise.

Questions

Frequently asked questions

How is this different from a regular chatbot?

Regular bots run rigid scenario trees. Sekretar24 is real AI powered by Claude (Anthropic): it understands free text, remembers conversation context and answers from your knowledge base, not from a script.

Which AI does Sekretar24 use?

By default — Claude by Anthropic, the smartest and most steerable model on the market. On request we plug in any other: OpenAI GPT-4, Google Gemini, Moonshot Kimi, DeepSeek, OpenRouter (dozens of models in one API) or local Qwen/Llama/DeepSeek via vLLM on your own server.

What happens to the AI after the trial?

The trial runs on Claude. After — two options: stay on Claude with Business+, or switch for free to OpenRouter's powerful models (DeepSeek R1, Llama 3.3 70B, Qwen 2.5 72B). The chain is configured from strongest to weakest: if the top model hits a limit, the assistant automatically takes the next one. For most tasks free models are more than enough.

Can I install it myself?

Yes. Code is open on GitHub under MIT, with detailed documentation. You need Docker and root SSH access on any Linux server. If you'd rather not bother — we install turnkey for 5,000 ₽.

How much does the AI cost?

For most business tasks OpenRouter's free models (DeepSeek, Llama, Qwen) are enough. Paying for top models (Claude, GPT-4) makes sense for complex reasoning and maximum expertise. On cloud plans the API is included; on self-hosted you plug in your own key or use the free models.

What's included in the 5,000 ₽ turnkey installation?

We deploy Sekretar24 on your server (Docker + root SSH required), configure the knowledge base (RAG), connect Telegram/WhatsApp/widget/telephony, and tune the assistant for your niche. Payment via YooMoney, Ozon Pay or Alfa-Bank.

Is my data safe?

Yes. Cloud models or your own server — your choice. Self-hosted means customer data stays inside your perimeter, and the open-source code can be audited.

Do I need my own server?

Not on Start or Business — both run in our cloud. A dedicated server is only needed for the Team plan (on-premise with local AI) or for self-hosted install from GitHub: any Linux with Docker (from 2 GB RAM for cloud mode, from 12 GB + GPU for local AI).

Which channels does the assistant work on?

Telegram, WhatsApp, web chat widget, telephony and the Android app. One assistant — every channel at once.

Can I connect telephony?

Yes, as part of the Team plan (on-premise). The assistant takes and makes calls via SIM7600 or SIP, recognizes speech and answers in voice — data never leaves your server.

Launch your AI employee today

Two paths — pick the one that fits.

Free

I'll install it myself

Clone the code from GitHub and deploy on your own server. You need Docker and root SSH access.

  • ✓ MIT license, open source
  • ✓ Detailed Wiki documentation
  • ✓ Community support
  • ✓ Free OpenRouter models out of the box
⚡ Turnkey
5,000 ₽

We'll install it for you

We deploy on your server and tune it for your task. From payment to a working assistant — one business day.

  • ✓ Deployment on your Linux server
  • ✓ Knowledge base (RAG) tuned for your niche
  • ✓ Connect Telegram, WhatsApp, widget
  • ✓ 14-day trial on Claude + OpenRouter fallback
💳 Pay and order

Payment: YooMoney · Ozon Pay · Alfa-Bank

Or leave a request — we'll help you decide

We'll reach out, answer your questions and activate your 14-day trial.

We'll reply within one business day. By clicking submit you agree to our privacy policy.