Status you can trust
Every tab shows whether it is working, done, or waiting for you — read from the screen itself, so it works with any CLI rather than one vendor’s API.
A single portable .exe. No install, no admin rights, no API keys — it drives the AI
CLIs you already have logged in.
Scan a QR code and you can see what every tab is doing and send instructions — from the train, from a café, from bed. Over Tailscale only your own devices can reach it, encrypted, from anywhere.
Status you can trust
Every tab shows whether it is working, done, or waiting for you — read from the screen itself, so it works with any CLI rather than one vendor’s API.
Agents that hand off work
“When this finishes, send the result to the review tab.” Write it in Lua, or describe it in plain language and let an AI you already have installed write it.
Brakes that actually hold
A limit on how many times agents may pass work along, an emergency stop, per-tab input locks, and a sandbox with no file or network access by default.
A real terminal
SSH, Docker, WSL, jump hosts, key files, port forwarding, session logs, legacy encodings, IME input and the mouse. Not a wrapper around one tool.
Running one terminal AI is easy. Running four is not.
You end up with a window per agent, no idea which one is waiting for you, and a lot of copy-pasting between them. ShikishaTerm-AI is a terminal that knows the difference between working, finished and waiting for a human — and can move work between agents on its own.
It talks to whatever runs in a terminal, so it is not tied to one vendor: Claude Code, Codex CLI, Gemini CLI, Ollama, Aider, or a plain shell over SSH.
Shikisha-Term-AI.exe[e] to open the settings screen in your browser and pick which AI runs whereNothing is written outside that folder.