Baltor Get started

Hand off the big job before you log off

Run a local queue of tasks with your own model access. Set a call budget and time limit, keep task checkpoints and review a morning report.

Example morning report07:00

  1. 23:10Profile the columnsChecked
  2. 23:42Split the addressesChecked
  3. 01:15Find duplicatesChecked
  4. 02:03Propose mergesWaiting for you
Illustrative workflow, not a recorded run. Times and outcomes are examples.

Local overnight tools Public preview

Set model-call and time limits, preserve task checkpoints and review morning reports. Review interrupted attempts before restarting them. The local harness is free.

Read the overnight setup guide

Max · Public preview

Your run desk

Prepare a bounded queue for your own Linux, macOS or WSL worker. The same command works on a cloud machine you control. Download the task list, run the command there, and bring its status report back here.

Preparation and report inspection happen in this browser. Your task paths and imported reports stay here. The worker uses your model access and hosting. A queue limit counts calls reserved, so review your provider's token and spending controls separately.

Choose task files and limits for the worker you control.

Review the command to run on your worker

Save tasks.txt in your checkout. Configure your model access and follow the worker prerequisites and recovery guide before starting. Use Ctrl+C in that worker's terminal to interrupt its owned process group.

Read the worker's status

Save the command's JSON output as a status file. Reuse the same task paths and limits. The worker preserves reservations and holds uncertain outcomes for reconciliation.

Choose a queue status report to inspect its attempts.

Recorded task attempts. A finished process still needs its output checked.
TaskStateCalls reservedProcess exit
  • Keep an attempt record

    See which attempts finished, failed or need review, with their retained task checkpoints.

  • Review outputs before accepting them

    A finished process is not an accepted result. Check the artifacts against the task's acceptance criteria.

  • Your model access

    Use your provider account or local endpoint. Call limits control how many requests the queue can make.

How a night of work runs

  1. Choose the tasks. List your task files, permitted inputs and the checks that determine success.
  2. Set the limits. Choose model-call allocations and a queue deadline before dispatch.
  3. Choose reusable files. Search Baltor and make selected versions available to your harness.
  4. Keep task checkpoints. Preserve attempt state. Review interrupted or unknown work before retrying within the remaining allowance.
  5. Review the morning report. Inspect results and check the produced artifacts before accepting the work.

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. Can I run it?
  • An Agent Feeds + Harness Files account for the library

One harness per step, your choice

Turn it on with a qualified fresh-instance profile, or leave it off for a session-based setup. Check your selected harness's settings. Start with one short task and inspect its artifacts before leaving a longer queue unattended.

A fresh process separates context; it does not establish task success. The worker guide explains the supported profiles and their limits.

Try it on tonight's job

Pro, $49 a month. The Baltor Harness is free.

Get started