Todo: update oe to these specs:

🐚 Ollama Bash Eval (oe)

oe is a minimal AI-powered Bash CLI tool that uses local Ollama models to generate and explain Bash one-liners, or create files like HTML, Markdown, etc.

Built to be:

• POSIX-friendly
• Bash 3.2 compliant
• Shell-native (no config files)
• Model-flexible
• Pipe-friendly

🧠 Example Usage

oe find all files over 10GB
oe -x how to show running processes
oe -c make a markdown file about SSH > ssh.md
oe -m llama3 list open ports
oe -m phi3 -x how to tail nginx logs

🧰 Options

🧠 Model Behavior

• -m <model> sets model for this call and updates OE_MODEL
• If -x is also used, prints:

  Using model: llama3
  To make this your default: export OE_MODEL=llama3

• If no -m, uses $OE_MODEL, or falls back to a random model

🪄 Example Prompts Used

🔹 One-liner generation (oe)

Generate a safe, POSIX-compliant Bash one-liner.
Task: {{TASK}}.
Return only the command.

🔹 One-liner with explanation (oe -x)

Generate a safe, POSIX-compliant Bash one-liner.
Task: {{TASK}}.
Add a short explanation as a Bash comment (# comment) before the command.
Output only the comment and command.

🔹 File creation (oe -c)

Create a plain text file based on this description:
{{TASK}}
Return only the raw content of the file.
Do not include explanations or formatting outside the file content.

🛡️ LLM Output Filtering

• Handles imperfect LLMs (chatty, markdown, etc)
• Strips markdown/code blocks
• Extracts:
  • First valid command
  • First # explanation (if -x used)
• Ignores intros like:
  • "Sure! Here's a bash command:"

🔄 Persistence

To persist model choice between calls:

export OE_MODEL=llama3

Or let oe show you how:

oe -x -m llama3 "list open ports"

✅ Requirements

• Bash 3.2+
• curl
• jq
• Local Ollama server running with your model(s)

🧪 Sample Output

$ oe -x how to list biggest files

# This lists the 10 largest files and directories in the current folder
du -ah . | sort -rh | head -n 10