Claude Academy — Build With AI Agents

Talk to it.
Build with it.
Own everything.

From your first Telegram command to running a full server hive — Claude Academy teaches you to harness Gemi Prime, Super Claude, and Codex Max at every skill level. No jargon. Real outcomes.

Gemi Prime Academy Super Claude Academy Codex Max Academy
3Agents
30+Lessons
3Levels
0Prior Experience Needed

Built for the Operator Who Wants Control

Claude Academy bridges the gap between "I heard AI can do that" and actually doing it. Three tracks. Three power levels. One goal — you in command of every tool in the stack.

🎙️

No Code? No Problem.

Gemi Prime Academy starts from zero — if you can text, you can run a business AI. Learn to delegate research, calls, writing, and scheduling through Telegram in plain English.

Server Operators Graduate Fast.

Super Claude Academy turns your VPS into a one-person engineering firm. Manage WordPress, deploy APIs, run databases, and wire a multi-agent hive — all by Telegram.

🔐

Private by Default.

Codex Max Academy teaches fully local AI inference. Your data never leaves your server. Swap models, run code, analyse documents, and build pipelines with zero cloud dependency.

📈

Real Projects. Real Stakes.

Every module ends with something you actually ship — a running service, a published book, a deployed API, a live automation. The curriculum is built around outcomes, not theory.

🏗️

Beginner to Advanced.

Each track is layered. Beginners get clean wins fast. Intermediates learn orchestration. Advanced operators run the full hive — three agents, one command post.

🤝

We Set It Up. You Run It.

Every plan includes setup by our team. You don't learn in a simulator — you learn on your own live server with your own agents. Academy content is operational, not theoretical.

Choose Your Agent. Pick Your Level.

Three complete curriculums — Beginner, Intermediate, and Advanced. Start anywhere. Every lesson ships a real outcome you can point to.

Gemi Prime Academy

Your AI Partner on Telegram

Gemi Prime is a fully autonomous Gemini-powered agent that lives in your Telegram. It researches, writes, calls, books appointments, publishes books, and handles your inbox — all from a chat message. This track teaches you to wield it from day one to full automation mastery.

Beginner
GP · 01

Your First Command

Send your first message and understand how Gemi reasons, responds, and retains context across a full conversation thread.

→ Live conversation with your agent
GP · 02

Web Research on Demand

Ask Gemi to research any topic — competitor pricing, news, local businesses — and get a structured summary back in seconds.

→ Your first research brief
GP · 03

Writing at Scale

Generate proposals, emails, social captions, and job ads by describing what you need. Edit by conversation, export to PDF.

→ Sent proposal, live
GP · 04

Calendar & Inbox Control

"Schedule a call with John for Thursday at 2pm" — Gemi handles Google Calendar, reads your inbox, and confirms everything back.

→ Appointment booked automatically
GP · 05

Voice Call Setup

Configure your Gemi Voice plan. Learn how inbound calls route, how Gemi answers, and what it says to callers who reach your number.

→ First live call received by Gemi
Intermediate
GP · 06

KDP Book Publishing Pipeline

From a one-line concept to a formatted, published book on Amazon KDP. Outline, write, proof, export, upload — Gemi runs the entire pipeline.

→ Book live on Amazon KDP
GP · 07

Outbound Sales & Prospecting

Script, dial, and follow up. Gemi calls your prospect list, qualifies leads, notes responses, and sends you a daily summary with next steps.

→ First qualified lead from agent call
GP · 08

SEO Audits & Website Copy

Feed Gemi your URL. Get a full SEO audit, competitor keyword gap, and a rewritten meta deck — ready to paste into your CMS.

→ Published SEO-optimised page
GP · 09

Document Factory

Contracts, NDAs, proposals, invoices, reports — describe the document and context, Gemi drafts to legal standard, exports to PDF.

→ Professional document, signed
GP · 10

Multi-Step Automation Chains

"Research the market, write the report, send it to my three clients, and calendar a follow-up for next week." One message. Done.

→ Full workflow executed autonomously
Super Claude Academy

Your Dedicated Engineering Agent on a VPS

Super Claude runs Claude Code on your own dedicated server. It edits files, deploys services, manages databases, builds APIs, and monitors the entire stack — all via Telegram. This track takes you from zero VPS experience to running a full multi-agent hive.

Beginner
SC · 01

VPS Orientation

Understand the file system, user permissions, systemd services, and how your agents live as background processes. No terminal required yet.

→ Server mental model built
SC · 02

First Telegram → Server Round Trip

"List everything running on the server" — Super Claude reads systemd status, formats it cleanly, and sends it back to you in Telegram.

→ Agent proves server access
SC · 03

WordPress by Command

"Update the pricing on our site to $49" — Super Claude edits the page, flushes the cache, and sends you screenshot confirmation.

→ Live site change, zero dashboard
SC · 04

Deploying Your First Script

Describe what you want automated. Super Claude writes it, makes it executable, and installs the cron job — all from one Telegram message.

→ First automation running on server
SC · 05

RDP Remote Desktop

Connect to your server graphically. Super Claude can operate what you see — together or fully autonomously in headless mode.

→ Visual server access confirmed
Intermediate
SC · 06

FastAPI: Prompt to Live Endpoint

Describe an API. Super Claude writes it, tests it, deploys it behind nginx with SSL. Your endpoint is live with a real HTTPS URL.

→ Public HTTPS endpoint live
SC · 07

Service & Certificate Management

SSL certs, nginx configs, port routing, service restart on failure — Super Claude handles the entire DevOps layer via conversation.

→ New subdomain live with cert
SC · 08

Database Operations by Chat

Create tables, run queries, export backups, restore from snapshot — MySQL, SQLite, and PostgreSQL, all by describing what you need.

→ DB created, queried, and backed up
SC · 09

The Hamper System

Drop any file in Telegram. It routes to your server hamper, gets processed by the agent, and the result comes back — automatically.

→ File processed, output delivered
SC · 10

Multi-Agent Coordination

Wire Gemi Prime and Super Claude together. Gemi handles research and conversation. Super Claude handles execution. Learn the handoff patterns.

→ Two-agent pipeline running live
Advanced
SC · 11

Full-Stack Deploy: One Conversation

React frontend + Python API + PostgreSQL + domain + SSL + monitoring — the entire production stack deployed in a single Claude session.

→ Production web app live
SC · 12

Agent Hive Architecture

Four agents, one operator. Gemi, Super Claude, Codex Max, and a custom nanobot — wired to share context, hand off tasks, and report to one thread.

→ Full hive live and coordinated
SC · 13

Custom Skill Development

Build new capabilities: image search skills, CRM lookup skills, payment handlers. Package, deploy, and invoke by Telegram command.

→ Custom skill installed and working
Codex Max Academy

Private AI. Your Server. Zero Cloud.

Codex Max runs open-source AI models — Gemma, Mistral, Llama, DeepSeek — entirely on your dedicated VPS via Ollama. No API keys. No data sent to the cloud. Total inference sovereignty. This track teaches you to harness local AI for code, data, automation, and privacy-critical work.

Beginner
CM · 01

First Local Inference Round Trip

Send a prompt, watch it route to Ollama on your VPS, receive a streamed response — zero cloud, zero API keys, zero data exposure.

→ First private AI response
CM · 02

Model Roster: Know Your Weapons

Gemma 3 for conversation and code. Mistral for reasoning. DeepSeek for structured output. Llama for raw capability. Pull new models in seconds.

→ 3+ models installed and tested
CM · 03

Private Document Intelligence

Drop a PDF, CSV, or Word doc into Telegram. Codex reads it, summarises it, answers questions — entirely on your server, never uploaded anywhere.

→ Private document analysed
CM · 04

Code Generation & Execution

Describe a function or script. Codex writes it, runs it in a sandboxed shell, reads the output, fixes errors, delivers a working result.

→ Script written, tested, and running
CM · 05

Shell Automation by Conversation

Backup scripts, file organisers, log parsers — Codex handles the bash, runs it, and reports results. You describe intent; it handles terminal execution.

→ Automated shell task deployed
Intermediate
CM · 06

Docker Fleet Management

Spin up, manage, and tear down containers by Telegram. Codex builds the Compose file, starts services, and monitors health — no Docker knowledge required.

→ Containerised app running
CM · 07

Database Administration by Chat

Schema design, migrations, query optimisation, backup schedules, integrity checks — Codex acts as your DBA, described conversationally, executed precisely.

→ Managed DB with automated backups
CM · 08

API Analysis & Prototyping

Feed Codex an API spec. It reverse-engineers the schema, writes a client wrapper, mocks it for testing, and documents the full integration.

→ Working API wrapper shipped
CM · 09

Data Pipelines & ETL

CSV → cleaned → transformed → loaded into PostgreSQL → report generated. Describe the pipeline, Codex builds and schedules it end-to-end.

→ Scheduled data pipeline live
CM · 10

Model Hot-Swap Strategy

Learn which model wins at which task and switch models mid-conversation. Gemma for chat, DeepSeek for JSON, Mistral for reasoning chains.

→ Multi-model workflow built
Advanced
CM · 11

On-Premise RAG System

Local embeddings, local vector search, local LLM. Your internal knowledge base — accessible via Telegram, air-gapped from any cloud.

→ Private RAG system answering queries
CM · 12

Hybrid Stack: Local + Cloud

Route sensitive tasks to Codex locally, customer-facing tasks to Gemi in the cloud. Build the agent router that makes the decision automatically.

→ Intelligent routing system live
CM · 13

Automated Testing Pipelines

Codex writes code, writes tests, runs them, reads failures, fixes the code, repeats — autonomously. Full CI loop via Telegram, no GitHub required.

→ Self-testing service deployed

Your VPS. One Command Post.

Super Claude and Codex Max turn server management from a specialist skill into a Telegram conversation. Here's everything you operate — without ever opening a terminal.

🌐

Web Server & SSL

nginx config, Let's Encrypt cert issuance, virtual hosts, reverse proxies, gzip, rate limiting — managed by agent command.

🗄️

Databases

MySQL, PostgreSQL, SQLite. Create schemas, run migrations, backup, restore, optimise queries, and export reports — by description.

🐳

Docker & Containers

Compose files, image builds, container health, port mapping, volume mounts, rolling restarts — the agent handles the YAML.

⚙️

systemd Services

Create, enable, disable, restart, and monitor background services. Every agent on your server runs as a managed systemd unit.

🔒

Security & Firewalls

UFW rules, SSH hardening, fail2ban, audit logs, certificate rotation — described conversationally, applied precisely and verifiably.

🚀

CI/CD Pipelines

Git hooks, build scripts, test runners, deployment targets — Super Claude wires the release pipeline from codebase to live production.

📊

Monitoring & Alerting

Uptime watchdogs, Telegram alerts on service failure, disk/RAM/CPU thresholds, and automated restart logic — all configured by the agent.

📦

Backup & Snapshots

Automated nightly backups, on-demand snapshots, remote offload to S3-compatible storage, and restore drills — no manual scripts needed.

What Academy Graduates Build

These aren't demos. They're production systems built by real operators using the agents you're learning. Every project here is within reach on any paid plan.

Gemi Prime

AI Customer Service Desk

Inbound calls, live chat, appointment booking, and issue resolution — all handled by Gemi 24/7. Your customers get instant professional responses. You get a daily digest and escalations only.

voice · chat · calendar · crm · research
Super Claude

Full-Stack SaaS Product

React frontend, Python FastAPI backend, PostgreSQL database, SSL-secured domain, Stripe payments, and admin dashboard — built, tested, and deployed from Telegram. No DevOps team needed.

react · fastapi · postgres · stripe · nginx
Codex Max

Private Business Intelligence Suite

Connect your internal CSVs, PDFs, and databases. Codex builds a private RAG system — query your own data by Telegram, get structured answers, auto-generated reports, and trend alerts. Zero cloud exposure.

rag · vector-db · local-llm · dashboards
Gemi Prime

Book Publishing Factory

Gemi handles the entire KDP pipeline: title research, outline, chapter writing, back cover copy, Amazon keyword optimisation, ISBN registration, and final upload. Idea to published in hours.

kdp · writing · publishing · research · seo
Super Claude

E-Commerce Site + SEO Engine

WooCommerce store, product pages, full SEO audit, competitor keyword gaps, schema markup, and automated weekly content publishing — Super Claude manages the entire organic growth engine.

wordpress · woocommerce · seo · content · automation
Codex Max

Automated QA & Testing Pipeline

Feed Codex your codebase. It writes unit tests, integration tests, and end-to-end specs. Runs them, flags failures by Telegram, and opens a conversation to fix them autonomously.

pytest · playwright · ci · telegram-alerts
Gemi Prime

24/7 Sales Call Operation

Gemi dials your prospect list, qualifies leads with scripted conversations, handles objections, books demos, and logs every outcome to a CRM-ready spreadsheet. Human-sounding. Always on.

outbound · voice · crm · scheduling · notes
Super Claude

Multi-Agent Monitoring Hive

One orchestrator, four agents. Super Claude monitors all services, routes incoming tasks, deploys hotfixes, and sends you a morning briefing. Gemi handles comms. Codex handles data.

watchdog · systemd · hive · telegram · logs

One Price. Your Agent. Your AI.

Every academy plan is $50/month — server, setup, and training included. You bring your own AI subscription. We handle everything else. Classes run 3 days a week with VIP tech support throughout.

The API burden is yours, the expertise is ours. Your AI subscription goes directly to the provider — no markup, no middleman. We provide the server infrastructure, agent configuration, and 3‑day‑a‑week guided classes.
Gemi Prime
Gemi Academy
Telegram AI agent powered by Google Gemini. Voice, research, publishing, and automation — all from a chat message.
$50 /month

Server + training + support · AI plan not included

What's included
Dedicated VPS server configured for Gemi Prime
Gemi Prime agent wired to your Telegram
Full agent setup & Telegram onboarding
Classes 3 days/week — Beginner to Advanced
VIP tech support — direct line, fast response
Voice call pipeline configured
KDP & publishing stack ready from day one
Your AI Plan — Not Included
Google Gemini API
$300 free credit

Google gives new API accounts $300 in free credits — no charges until your credits run out. Based on typical Gemi Prime usage, credits last approximately 20 months. After that, estimated cost is ~$15/month on pay-as-you-go pricing. You pay Google directly — no markup from us.

Classes Mon · Wed · Fri  ·  VIP support included  ·  Setup within 24 hrs
MOST POPULAR
Super Claude
Claude Academy
Claude Code on your own VPS. Deploy services, manage databases, build full-stack apps, and run a multi-agent hive via Telegram.
$50 /month

Server + training + support · AI plan not included

What's included
Dedicated VPS with Claude Code installed
Super Claude agent wired to your Telegram
RDP Remote Desktop access configured
Classes 3 days/week — Beginner to Advanced
VIP tech support — direct line, fast response
nginx, SSL, domain setup handled for you
Full server management training included
Your AI Plan — Not Included
Claude Pro by Anthropic
$20 /month

Subscribe directly at claude.ai/upgrade. Claude Pro gives your Super Claude agent full access to Claude Sonnet and Opus models, extended context, and priority access — everything needed for server-level engineering tasks. You pay Anthropic directly.

Classes Mon · Wed · Fri  ·  VIP support included  ·  Setup within 24 hrs
Codex Max
Codex Academy
Private local AI on your VPS via Ollama, plus optional GPT integration. Maximum privacy, maximum control, zero cloud dependency.
$50 /month

Server + training + support · Cloud AI plan optional

What's included
Dedicated VPS with Ollama + Gemma 3 installed
Codex Max agent wired to your Telegram
Local inference — zero API keys required
Classes 3 days/week — Beginner to Advanced
VIP tech support — direct line, fast response
Docker + database admin training included
Model pull workflow — swap models any time
Optional Cloud AI Upgrade
OpenAI Plus Optional
$20 /month

Local Ollama inference is included free — no subscription needed. Optionally add OpenAI Plus at openai.com for GPT-4o access alongside your local models. Hybrid stack: private tasks go local, GPT tasks go cloud. You pay OpenAI directly.

Classes Mon · Wed · Fri  ·  VIP support included  ·  Setup within 24 hrs
Gemi Prime Academy

Welcome to Gemi Academy

Your autonomous Telegram AI agent, powered by Google Gemini. Classes three times a week. Your server and agent are live within 24 hours of enrollment.

What you pay us — $50/month
Dedicated VPS server — configured, managed, monitored
Gemi Prime agent installed and wired to your Telegram
Full onboarding call and agent configuration
3 live classes per week (Mon · Wed · Fri)
VIP tech support throughout — fast, direct responses
Voice call pipeline, KDP stack, skill suite all included
How to claim your $300 Google credit
1

Create a Google Cloud account

Go to console.cloud.google.com and sign in with a Google account. New accounts automatically receive $300 in free credits — no charge until the credits are exhausted.

2

Enable the Gemini API

In the Cloud Console, search for "Generative Language API" and enable it. This is the Gemini Flash API your Gemi Prime agent calls for every message and voice interaction.

3

Generate an API key

Go to APIs & Services → Credentials → Create Credentials → API Key. Copy this key — you'll send it to us securely via Telegram when enrolling.

4

After credits: ~$15/month estimated

Gemini Flash 2.5 is priced per token on pay-as-you-go. Based on typical Gemi Prime usage (research, writing, calls), you'll spend approximately $10–20/month — often under $15. You're billed monthly by Google, directly.

Your total estimated monthly cost
After free credit period · ~20 months of free AI usage first
~$65/mo
Message Us on Telegram to Enroll

We set up your server, configure your agent, and have you live in 24 hours. First class within 48 hours of enrollment.

Super Claude Academy

Welcome to Claude Academy

Claude Code on your own dedicated VPS. Deploy, build, and manage a full server stack via Telegram. Classes three times a week. Live within 24 hours.

What you pay us — $50/month
Dedicated VPS — installed, configured, managed
Super Claude agent wired to your Telegram + RDP
Full onboarding: server orientation + first lesson
3 live classes per week (Mon · Wed · Fri)
VIP tech support — direct line, fast response
nginx, SSL, domain, service management — all taught
Full engineering curriculum: Beginner to Advanced
How to set up Claude Pro
1

Subscribe to Claude Pro

Go to claude.ai/upgrade and subscribe to Claude Pro at $20/month. This gives your Super Claude agent access to Claude Sonnet and Opus — the models that power real engineering work.

2

Get your API key (for server-side use)

Go to console.anthropic.com → API Keys → Create Key. This is what Super Claude uses when running tasks autonomously on your server. Send it to us securely via Telegram.

3

We handle the rest

We install Claude Code on your VPS, wire up the Telegram bot, configure RDP access, and run a test conversation with you before your first class. You start building from Lesson SC·01.

Your total monthly cost
Academy + Claude Pro subscription · No hidden fees
$70/mo
Message Us on Telegram to Enroll

VPS live in 24 hours. First class within 48 hours. RDP shortcut delivered by Telegram.

Codex Max Academy

Welcome to Codex Academy

Private local AI on your own VPS. Zero cloud dependency. Run Gemma, Mistral, Llama, and DeepSeek on your hardware — with optional GPT hybrid mode. Classes three times a week.

What you pay us — $50/month
Dedicated VPS with Ollama + Gemma 3 installed
Codex Max agent wired to your Telegram
Local inference running from day one — no API key needed
3 live classes per week (Mon · Wed · Fri)
VIP tech support — direct line, fast response
Docker + database administration training
Model swap workflow — pull any open model any time
Your AI stack — local is free, cloud is optional
1

Local inference — included, zero cost

Ollama is pre-installed on your server with Gemma 3 4B ready to run. No API key. No subscription. No cloud. Your data stays on your hardware. You can pull additional models (Mistral, Llama, DeepSeek) any time with one command.

2

Optional: Add OpenAI Plus for GPT-4o

If you want GPT-4o alongside local models, subscribe to OpenAI Plus at $20/month. Get your API key at platform.openai.com → API Keys and send it to us. Codex will route cloud-appropriate tasks to GPT and private tasks to your local models automatically.

3

No cloud at all? You're still fully operational.

Codex Academy teaches you to get production-grade results from local models only. Many students never add a cloud subscription — local Ollama handles code, data, documents, and automation completely.

Your total monthly cost
Local only · No cloud subscription needed
$50/mo
+ optional OpenAI Plus $20/mo if you want cloud hybrid
Message Us on Telegram to Enroll

Server live in 24 hours. Ollama running and Codex wired to your Telegram before first class.

Let's Build Your Agent

Questions about Gemi Prime, VPS plans, or custom integrations? Drop us a line and we'll get back to you within a few hours.

Message Us on Telegram.
Your Agents Are 24 Hours Away.

Choose a plan, we set up your VPS and all agents, hand you the Telegram handles and RDP shortcut, and you start building from Lesson 1 on day one. No waiting. No configuration headache.

Talk to Gemi Prime Super Claude Plans See Pricing Above
@GemiPrimeBot
Find us in Telegram · We reply fast
Open in Telegram
ASK
GEMI
?