aigent-OS  ·  The AIgent

Stop running stock Claude.
Run it enhanced.

Same Claude Code, enhanced into an operator. aigent-OS adds a caddy that surfaces the right skill the moment your task needs it, a learning loop that turns every repeated mistake into a guardrail so it stops costing you twice, a committable vault you own, and a routed crew of 9 specialists. You stop hunting for the right tool. The system hands it to you.

Get Enhanced $79$49 Limited-time Founders price: $49. Save $30 off the regular $79, first come first served. One-time, not a subscription. 30-day money-back.
The enhancement

Same Claude. Enhanced output.

The Enhanced Games let athletes legally take what makes them faster. aigent-OS is that for Claude Code: a legal, packaged enhancement layer that turns a stock session into a high-performance operator. You keep the model you already pay for and add the system around it.

A caddy that surfaces the right one of about sixty skills at the exact moment it matters, so you are not the one remembering which tool to reach for. A learning loop that logs every repeated mistake into a durable guardrail, so the same wrong turn is far less likely to bite twice and the system gets sharper the more you run it. Body-state awareness that flags the pressure before it costs you a session. A committable vault and a 9-specialist crew you own and carry across machines. Same Claude. Enhanced output. One install.

Is this for you

Built for operators who live in the terminal.

For you if

You run Claude Code daily and you want it operating like a high-performance system, not a blank assistant you re-brief every session.

Not for you if

You use Claude occasionally, or you want one single-purpose bot. A single-purpose bot covers that. This is the full operator system.

Proof it runs

The proof is that it runs a real business.

aigent-OS is the system that produces The AIgent newsletter every single day. Not a demo, not a template, a live operation. Here it is working.

aigent-OS demo: a task comes in, the caddy surfaces the right skill the moment it is needed and the agent runs it, a guardrail catches a risky claim before ship, the work ships, ending on the Enhanced Claude card

2,563 readers every morning · a new issue shipped every single day · read the latest →

The two moats

What the demo is actually showing.

The caddy. The demo above is the caddy in action. You don't have to know which of about sixty skills fits the moment: it reads your task and surfaces the right one, right when it matters. You stop being the one who remembers the toolbox.

A filed Claude Code issue asked for exactly this: "the memory should function as a pre-action checklist, not just passive context." (anthropics/claude-code #37847)

The learning loop. Every repeated mistake becomes a guardrail. The system diagnoses the failure, writes the fix into a memory, a rule, a check, or a caddy trigger, and surfaces it before you hit the same wall again. The same wrong turn is far less likely to cost you twice, and it gets sharper the more you run it.

Start free

Not sure yet? Start with the free kit.

You don't have to start here. Our open operator-kit is free on GitHub, ★ 8 stars and climbing. It gives you the free rung: a routed starter crew and a context-loader so you stop re-explaining your project every session. Run it, feel how an operator setup works.

$ curl -fsSL https://raw.githubusercontent.com/wrg32786/operator-kit/main/install.sh | bash

aigent-OS is what that becomes once you're in Claude Code every day: the caddy that surfaces the right skill in real time, the learning loop, the committable vault, and the full specialist crew the free kit doesn't include. Start free. Get Enhanced when you're ready.

What's in the enhancement

The operator system you'd otherwise wire by hand.

The caddy
the headline enhancement
Surfaces the right one of about 60 skills the moment your task needs it. You stop being the one who remembers the toolbox.
The learning loop
compounds as you run it
Every repeated mistake becomes a durable guardrail, so the same wrong turn is far less likely to cost you twice and the system gets sharper the more you run it.
16-document kernel
days of architecture
Your agent reasons, delegates, and manages its own context like an operator, not a one-off chat.
9 specialist sub-agents
days of role wiring
Hand real work to a routed crew (build, design, research, stress-test, and more) instead of babysitting one generalist thread. Standard Claude sub-agents start with zero context; these ship configured.
About 60 slash-command skills
weeks of curation
Your operator toolbelt, one command each, surfaced by the caddy the moment a task needs them.
Committable vault + body-state awareness
rarely gets built
A human-readable vault you own and carry across machines, and a read on operational pressure before it costs you a session.
One-command install
the setup you skip
Live in minutes. Markdown and shell, no build step, no server, no database.

The harness is genuinely ours: Caddy, the memory architecture, the sub-agent roster. Bundled third-party skills are curated open-source, each credited with its license in the included credits file. You're buying the assembled, maintained, one-step-installable system, not a pile of files.

The difference

Stock Claude codes. Enhanced Claude operates.

Most kits ship skills and agents. The enhancement is what surrounds them: a caddy that surfaces the right rule and skill the moment it matters, and a learning loop that turns your mistakes into guardrails.

That's the difference between a folder of tools and an operating system, and it's the centerpiece of the demo above.


Pricing

If aigent-OS saves you 15 minutes of setup and tool-hunting per session, three sessions a day, it pays for itself in the first week. Every week after is profit.

Single-purpose AI bots sell for around $50 each. aigent-OS is the full enhancement, every agent and skill, for $49 during the founding window.
$79 $49 Founders
For the first 30 operators, then $79. Doors close when the cohort fills.
Everything in the enhancement: the caddy, the learning loop, 16-doc kernel, about 60 skills, 9 sub-agents, the committable vault.
Drag-and-drop install. Give Claude the file, say "install this and set it up." Running in minutes.
Runs in your own Claude Code, no API keys, no separate billing.
30-day money-back guarantee. If it doesn't end the re-explaining tax, full refund.
Get Enhanced. Install aigent-OS, $49

30-day money-back, no questions asked.

If aigent-OS doesn't end the re-explaining tax, email us and we refund every cent. No forms, no friction.

Questions

The honest answers.

Why pay when Claude Code has built-in memory now?
Built-in memory keeps machine-local notes. aigent-OS is the operating architecture on top: a caddy that surfaces the right skill at the moment it matters, a learning loop that turns mistakes into guardrails, a routed crew, and a committable vault you own across machines. Recall is not operation.
What does the install actually run?
Markdown and shell, nothing hidden. You can read our free kit's install script before you run anything. The paid OS installs the same way: read every file, then run it.
Isn't this just the free kit?
The free operator-kit is a great start. aigent-OS is the assembled, production-tested enhancement, with the caddy, the learning loop, and the architecture the free kit doesn't include.
Does the caddy run skills for me automatically?
It surfaces the right skill the moment your task needs it, so you are not the one remembering which to reach for. You stay in control of what runs.
Do I need Claude Code?
Yes. aigent-OS installs into Claude Code; it is the enhancement layer on top, not a replacement.
Will it work with my stack?
Yes. aigent-OS is markdown and shell that installs into Claude Code, so it's language and framework agnostic. The memory layer learns your project and stack as you use it; it doesn't assume one.
What's the refund policy?
30 days, no questions asked. If it doesn't end the re-explaining tax, full refund.

Stop running stock Claude. Get Enhanced.

Founding price $49 for the first cohort, then $79. It still runs a real business every day; every session you wait is another morning running stock.

Will Gwyn, founder of The AIgent

Built by Will Gwyn. I ship The AIgent to 2,563 readers every morning with this exact system.