Run your AI company.
You're the Chairman.
|
No credit card · Full access · Windows & macOS
macOS is supported for install and local setup. Windows remains our primary tested platform — Mac feedback helps us harden it faster. Tell us how Mac goes →
The only thing holding you back is you.
Helpmehelpyou.
— Jerry, your AI CEO
Before you start
4 things to know
ClickSorcery is powerful — but honest.
01
Jerry leads, you decide
Jerry guides the setup — what to teach, what tools to add, what your business needs. You bring the knowledge, Jerry brings the structure.
02
29 agents, one conversation
Jerry leads a full team of 29 agents — C-suite, specialists, security, and personal coaches. All available from day one.
03
Remembers everything
Obsidian memory means Jerry never forgets your context — across sessions, across projects.
04
Your pace, your rules
You control how much Jerry does on his own. Start slow — trust builds over time.
Your journey
Step by step
Jerry guides every move.
00
Install + setup
~10 min · free
Magic Installer walks you through Cloud or Local mode.
00
Learn the dashboard
~5 min guided tour
Projects, agents, tools, approvals — one workspace.
00
First project
60+ templates · est. €0.10–2 API cost
Pick a template. Jerry runs the plan with you.
00
Add integrations
Telegram ready · more channels as guided projects
Connect Telegram today. Email, WhatsApp, and others follow the same pattern as you need them.
Integrations
Jerry connects your world
Talk once Jerry's set up. Getting there takes a bit of teaching.
You
- "Post the update to Telegram"
- "Summarize today's emails"
- "What's blocking the launch?"
Jerry
Active
Our position
Your computer, your rules
01
Local by default
We prefer your company data stays on your own computer. On capable local hardware, Ollama, Obsidian, and OpenClaw run entirely free — your messages never leave your device.
02
Cloud on your terms
If you want more powerful models, add your own API key at any time — OpenRouter, DeepInfra, Claude, GPT-4o, and others. The dashboard stays on your computer; only conversation content travels to your chosen provider.
03
Your choice, always
The product works both ways. Start local, add cloud later — or the reverse. You can change your mind at any time.
Choose your engine
Cloud or local
Same Jerry. Different power source — and very different monthly bills.
What costs money — and what doesn't
Telegram and OpenClaw are free. You only pay when the AI brain runs in someone else's cloud.
| Component | Ollama (local home) | Claude / API (cloud brain) |
|---|---|---|
| Telegram bot | Free | Free |
| OpenClaw (software) | Free · open source | Free · open source |
| AI thinking (each message) | €0 API — your hardware + electricity | Pay per token (words sent + received) |
| Privacy | 100% on your machine | Prompts go to your API provider |
| Best for | 16 GB+ RAM or GPU — privacy, no per-message API bill | 8 GB laptops, smarter model, no hardware struggle |
Local: Telegram is free; thinking is free API-wise once Ollama actually runs. Cloud: every token counts — your question, Jerry's context, and the full reply. A short research chat can be ~€0.50; ~10 Claude questions with a small lookup has cost real users ~€5.
Cloud Commander
Add one API key. Jerry routes messages to the cloud — you pay per token, not per month. Memory and long replies count toward your bill too.
Monthly API cost — real-world, not wishful
| Barely use it | Few short chats per week | €3–10 |
| Regular use | Daily chat, some projects | €15–40 |
| Power user | Research, agents, integrations, full automation | €40–100+ |
Models Jerry can use
- Claude Sonnet — Best all-round — planning, code, nuanced replies
- GPT-4o — Fast general assistant for everyday tasks
- Gemini — Large context and multimodal workloads
- Groq / Llama — Ultra-fast bulk tasks at low cost
Why Cloud?
- ✓Start in minutes — no GPU required
- ✓One API key, 400+ models — including free ones, via OpenRouter or DeepInfra
- ✓Switch brains per agent in Settings
- ✓Works on Windows and macOS
No flat fee — your API provider bills per token. Real use often costs more than estimates.
Local Supercomputer
Ollama on a machine that can actually run it (16 GB+ RAM or a GPU). OpenClaw talks to your local model — €0 API per message. Telegram stays free.
8 GB RAM without GPU: we don't recommend local Ollama — models often fail to respond and the PC fans spin with no answer.
If Jerry lives on this hardware
| 8 GB system RAM · no GPU | → Cloud Commander | Local Ollama not practical — machine struggles, Jerry may never reply |
| 16 GB system RAM · no GPU | qwen2.5:7b | Minimum local setup — slow CPU inference, but €0 API |
| 8 GB VRAM GPU | qwen2.5:7b | Jerry + up to 3 specialist agents |
| 16 GB VRAM | llama3.1:8b | 8 agents, daily workflows, routines |
| 24 GB+ VRAM | qwen2.5:32b+ | Full agent company — maximum local power |
Why Local?
- ✓100% private — data never leaves your computer
- ✓€0 API cost after setup (electricity only)
- ✓Works offline for inference once models are pulled
- ✓You control which models run and when
GPU guide
| 4GB VRAM | Jerry mini |
| 8GB VRAM | 3 agents |
| 16GB VRAM | 8 agents |
| 24GB+ VRAM | Full company |
Est. cost: €0/month API + electricity
Give Jerry a home
What you get on real hardware — we're honest about what 8 GB cannot do.
Don't run Ollama here
Typical 8 GB Windows laptop: once Ollama loads a model, the machine maxes out and Jerry often never answers. Use Cloud Commander instead — same Jerry, API key, no local inference.
You get
- ✓Full Jerry on Claude / OpenRouter / other APIs
- ✓Telegram bot — platform still free
- ✓Works on the laptop you already have
- ✓Pay only when Jerry actually thinks (per token)
Limit: API costs add up fast if you research a lot. Not €0 per month unless you barely use it.
Real example: ~€5 for ~10 questions + small research · varies wildly
Minimum for local Jerry
16 GB system RAM (CPU-only, slow) or a PC with a dedicated GPU. Ollama can finally load a small model and reply — qwen2.5:7b class.
You get
- ✓Jerry chat + Telegram with €0 API per message
- ✓Light projects and templates
- ✓Private — data stays on your machine
- ✓Good spare PC on a shelf, not your only 8 GB daily driver
Limit: CPU-only is slow. Heavy automation and big agent teams need more hardware.
~€0 API · electricity only
Growing team
Desktop with a real GPU. Jerry runs 7B–14B models comfortably — specialist agents can work in parallel.
You get
- ✓Jerry + 3–8 agents on daily workflows
- ✓Telegram, email hooks, routines
- ✓Full autonomy with local approvals
- ✓Optional cloud API in Settings for hardest tasks only
Limit: Not the full 29-agent company at max speed — but serious daily work.
~€0 API · electricity · optional cloud for peak tasks
Jerry's headquarters
Dedicated workstation or small server — hardware you buy for the company, not rent per message.
You get
- ✓Full local agent company — largest Ollama models
- ✓Heavy automation, long context, full autonomy at scale
- ✓Telegram + integrations without per-message fear
- ✓Cloud API only when you choose
Limit: Upfront hardware cost. You own the asset.
~€0 API · higher electricity
Honest default: 8 GB laptops → Cloud Commander. Local Ollama needs 16 GB+ RAM or a GPU — otherwise Jerry may never answer.
Pricing
One price. Forever.
Launch price.
€49
one-time · API costs separate
- ✓Jerry CEO + 29 agents
- ✓50+ project templates
- ✓Voice control — Jerry talks back
- ✓Cloud Commander + Local Supercomputer
- ✓Obsidian memory vault — Jerry never forgets
- ✓Windows & macOS
- ✓Dashboard upgrade notifications
No credit card · All sales final after purchase
FAQ
Common questions
No. Setup wizard + Jerry guides everything.
€49 once for ClickSorcery. Cloud API: no flat fee — real users report ~€5 for ~10 Claude questions with research; daily use is often €15–40+. Local Ollama: €0 API if your hardware can run it (16 GB+ RAM or GPU).
Yes with Cloud Commander (API key). Local Ollama on 8 GB usually fails — PC maxes out and Jerry often never answers. Use cloud on 8 GB; use local on 16 GB+ or a GPU.
Yes — Jerry + 3 agents. 16 GB VRAM → 8 agents. 24 GB+ for full local company.
Local = 100% private. Cloud = your API provider only.
Yes. Export your AI Company (.zip) from Settings, install ClickSorcery on the new machine, unlock with your license, and restore. One active machine at a time.
7-day trial, full access, no card. All sales final.
29 on day one: Jerry (CEO) + 5 C-suite + Security + specialists + 3 personal coaches — the full team Jerry manages inside the product.
Jerry can suggest schedules when a project needs ongoing checks. You approve them on the Approvals page — not autonomous management. You can always disable an agent or routine.
Jerry uses Obsidian-based memory — your projects, preferences, and past conversations persist across sessions. He doesn't start fresh every time.
After purchase, you can ask Jerry directly — he knows everything about ClickSorcery and answers instantly.
We reply from help@clicksorcery.com.