Sable Docs
sable v1.0 GitHub
For Linux servers

Your server's AI operator.

Talk to your server in plain English. Sable runs the work, watches it while you sleep, and pings your phone before anything risky.

Python 3.11+Linux Ubuntu 22.04+LLM Ollama · OpenAI · AnthropicMCP client + serverMIT licence
The problem

You know the machine. Not every flag.

So you leave the terminal, search, and paste back a command you haven't fully read, onto production. Sable removes that round trip, keeps routine work running on its own, and keeps you in command.

Without Sable
  1. Try to recall the flags
  2. Search the web
  3. Paste a command you haven't read
  4. Hope, then watch it for twenty minutes
  5. Set a cron job and forget what it does
  6. Relearn it next month
With Sable
  1. State the goal in plain English
  2. Read and edit the command before it runs
  3. Destructive ones need the word YES
  4. Nightly jobs and watchers run while you're away
  5. Risky steps wait for your tap, on your phone
  6. Next time, it already knows where the logs are
>.

You stay in command. Every command is shown before it runs. Anything risky waits for your approval, in the shell, in /inbox or from your phone, and every action lands in an audit log. scp, rsync and git push never touch the model.

What it does

An operator that lives on the box.

Sable runs where the work happens, keeps working after you log off, and owns the safety layer between the model and your server.

Try it in a container first.

The playground runs on Windows and macOS, and mock mode needs no API key.

← parthkomalwad.dev