Baltor Get started

Use case

Solve complex problems overnight.

Hand a big job to a small or local model before you log off, and come back to checked work and a record of every step.

How a night of work runs

  1. Describe the job. One task, with the files it works on and what a good result looks like.
  2. Small steps. The Baltor Harness breaks the task into small steps with clear inputs and outputs.
  3. Only what each step needs. Every step asks the library for its skills, tools and instructions, and gets only those.
  4. A fresh start per step. Each step can run in its own freshly started harness, so a long job never piles up in one crowded session.
  5. Checked results. An independent check accepts each result before the next step builds on it.

What you need

  • A model you can reach: a model on your computer, Ollama Cloud, a machine on your network or a provider key
  • The Baltor Harness on the machine that runs the job
  • A Baltor Pro account for the library

One harness per step, your choice

Starting a fresh harness for every step keeps each step small and focused, which is what lets a small model go the distance. Turn it on for long runs, and off for a quick task that runs in one session.