A one-person AI tooling studio

Build it.
Understand it.
Share what works.

This is a workshop, not a company. I make things, figure out how they actually behave, and share the parts that turn out to be useful - mostly around terminals, AI systems, and how to bring them together without giving up control.

Meet ridinCLIgun Visit the Garden

security > privacy > cost > usability

⬡

Build and share

Working tools for a concrete problem. First up: ridinCLIgun, a terminal copilot that helps, warns, but never takes control.

◎

Understand and write it down

Notes on AI safety, usability, agent-assisted workflows, and what is actually useful. Public Garden content starts in German for now, with the current state linked from /de/garden/.

◇

Safe and open

Security first. Privacy second. Cost third. Usability follows from those constraints, not the other way around.

first product

ridinCLIgun

>_ridinCLIgun

A terminal tool for people who want to keep their shell, but occasionally want a second opinion before they press Enter. If you want to run agent systems on your own machine in a controlled way, you have to own the terminal. I built ridinCLIgun to fix my own problems with it - and it turned out other people had the same problems.

v0.4 shipped human in the loop local-first command knowledge room to grow

Direct product page

See ridinCLIgun Open the product page

Useful today, still growing.

Current build: offline command knowledge, typo detection, language-aware AI, and review history are already working.
Human in the loop: ridinCLIgun advises. It never presses Enter for you.
Room to grow: the next steps lean toward teaching, workflow support, and supervising agents - without taking control away from the operator.

zsh - ridinCLIgun v0.4

Inference-Garden/ ridinCLIgun on master MU is v0.4.0

> curl -fsSL https://docker.com | sh

DANGER

Downloading and executing code directly - you can't inspect it first.

Download the script first, review it, then execute:
curl -O script.sh URL && less script.sh && bash script.sh

curl

Transfers data from or to a server.

Example commands from the offline catalog:

curl https://example.com

curl -L --location -D- --dump-header - https://example.com

curl -O --remote-name https://example.com/file.zip

AI: on Secret: off Version: v0.4.0 Ctrl+G -> help zsh

/garden/ - what's growing here

What's growing here

A few subjects I keep coming back to. Garden content is currently available in German only. The current public set lives in the German /Garden: part 1 of the agentic coding series is online, while parts 2 and 3 are already queued.

German Garden hub

The first published Garden text currently lives in German, together with a growing glossary for the series.

Open the German /Garden

Part 2: protect system and data from the agent

Sandboxing, tool permissions, dedicated workspaces, and what an agent should never be allowed to do silently.

Coming Soon

Part 3: protect the agent

Prompt injection, untrusted input, and the design moves that keep an agent's working context clean.

Coming Soon

/garden/ is not a blog. it's a garden. it grows.

how I think about personal AI

Good tools make the user stronger, not more dependent.

Good tools make the user stronger, not more dependent. They explain what they do, and let the person learn and decide. They favour security first, privacy second, cost third, usability fourth - not because usability does not matter, but because the order decides whether the tool serves the person or the other way around. They do not promise more than they deliver. And they are fun - because getting things to actually work is one of the best feelings there is.

There is something of a civic duty in this: those of us who can figure these systems out should help others run their own agent setups safely, sovereignly, and affordably - participate in the discourse - and help make that the norm, not the exception.

inference-garden