antahkarana-cli 0.4.0

ant — the Antaḥkaraṇa governed-AI operator CLI: prompt your on-box copilot to investigate/operate a machine, read-only by default, with y/N approval for changes and catastrophic commands hard-blocked.

ant — Antaḥkaraṇa governed-AI operator CLI

Author — Deepak Soni. A tiny, dependency-free CLI that prompts your on-box copilot (the Antaḥkaraṇa model + control ring) from any terminal — Claude-Code style. It investigates a machine, reasons, runs read-only commands immediately, and asks y/N before any state-changing action; catastrophic commands are hard-blocked server-side.

Install

pip install antahkarana-cli

Use

ant connect http://YOUR-BOX:8090     # point it at your copilot (saved to ~/.ant/config.json)
ant                                  # interactive: banner + prompt
ant "what is listening on this server?"   # one-shot
ant status                           # connection + model health

In the REPL, slash commands: /connect <url> · /login <token> · /model · /status · /clear · /exit.

What you can ask

• what OS is this and what's listening on its ports? → runs read-only, reports
• create a file /tmp/demo.txt → proposes it, asks [y/N], runs only if you approve
• rm -rf /tmp/x → hard-blocked by the control ring
• assess example.com → passive web-recon → prioritized report

How it works

ant is a thin client over the copilot's /api/chat — the model (e.g. Qwen2.5-14B), the governed run_shell, the web-recon tools, and the control ring all live on the box (or a remote SSH target the copilot is pointed at). Nothing runs locally; every decision is governed and audited server-side.

Requires a running Antaḥkaraṇa copilot (see antahkarana-net/box/copilot/).