PABLO

Documentation

Everything about installing, using and understanding PABLO, the orchestrator that watches your pull requests and launches the right AI agent, in the right worktree, when something needs doing.

⚡ Quickstart In a hurry? Install, add a project and start a task, all on one page. 1 Install PABLO One script, then a doctor that tells you what's missing. 2 Add a project Point PABLO at a repository and its issue tracker. 3 Start a task From an issue link to a merged PR, step by step.

I want to…#

Looking for something specific? Press / anywhere on the site to search.

Getting started

What is PABLO? PABLO (Personal Assistant for Boring Logic & Operations) watches your task branches and pull requests, and launches the right AI agent, in the right worktree, when something needs your attention. It does the noticing and the waiting, so you don't have to. Quickstart From nothing to your first task in four commands. Each step links to its full page when you want the details. Installation Install PABLO with one script, then let pablo system:doctor tell you which tool is missing or logged out. It takes a few minutes on Linux or macOS. Your first project A project tells PABLO about one repository: where its main checkout lives, which branch is primary, and which issue tracker holds its tickets. Set your global defaults once, then add each project with a short wizard. Your first task Follow one task from an issue link to a merged pull request. You make the decisions and write the code with your usual agent; PABLO handles everything in between.

Guides

Managing tasks A task is one branch, one git worktree and one state, tracked by PABLO until the pull request is merged. This page covers everything you can do with one, from starting it to closing it. Dashboard A local web page with the same picture as pablo task:list: what needs you, everything else, when the next poll happens and what the last sync did. It also has paste-ready Slack messages and token and cost analytics. Analytics PABLO keeps a local log of task lifetimes and agent runs, including tokens and cost, and summarises it with pablo stats or the dashboard's Analytics page. Nothing leaves your machine, and prompts are never stored. Backups & restore Everything PABLO knows lives in ~/.pablo/. Back it up in one command, and restore it on another machine with your task worktrees recreated: you pick up exactly where you left off. Troubleshooting Start with pablo system:doctor, then look at the logs. Below are the problems people actually run into, with the fix for each.

Concepts

How it works PABLO has two layers: the commands you run, and a background job that runs every 5 minutes, checks each project and does whatever is due. Agents run through your agent backend, and everything else is plain, deterministic code. Task states Every task is in exactly one of ten states. You move a task with two commands; the background poller moves it the rest of the way by watching CI, reviews and QA. This page lists every state and every rule behind the transitions. Agents PABLO ships five agents, run by OpenCode, Claude Code or GitHub Copilot CLI (see agent_runtime). Four read and analyse, and never touch your code; the fifth resolves rebase conflicts. Each one is launched by a specific state, with the right link and the right worktree, so you read results instead of writing prompts. Sync & rebase PABLO keeps two things up to date for every project: your task branches, rebased onto the primary branch, and the project's main checkout, fast-forwarded to the remote. Both are cautious: they report by default, skip anything with local changes, and never resolve a conflict in code.

Reference

Commands Every pablo command, grouped by what it acts on. Commands marked “in a worktree” act on the task of the current directory. Run pablo help <command> for the full usage of any of them. Configuration PABLO reads two kinds of YAML files: one global ~/.pablo/config.yaml with your defaults, and one file per project in ~/.pablo/projects/. A project can override any default, key by key. Providers PABLO talks to GitHub, Jira, Confluence and Linear through each service's own command-line tool. No API keys, no tokens in the configuration: every tool handles its own login, and when one isn't ready PABLO shows that tool's own message. Storage Everything PABLO creates at runtime lives in ~/.pablo/, never inside your repositories or worktrees. This page maps that folder and describes a task record.

Contributing

Development How the PABLO repository is organised, how the engine is built, and how to run the quality checks before sending a change. The engine is a Symfony application in app/; quality tools run through Castor.

Edit this page on GitHub