Introduction

Soloco is a local-first orchestration system for long-running AI work. It does not run its own hosted agents. Instead it coordinates local agent runtimes — currently Claude Code, Codex CLI, and the DeepSeek Harness (DSH) bundled with Soloco — turning a goal into an executable, auditable, resumable, reusable task tree.

Claude Code and Codex CLI use their existing account or subscription login. For DSH, you enter your own DeepSeek API key in Soloco; DeepSeek accounts for that provider usage. Your workspace and orchestration state stay on your device by default, while the selected runtime communicates with its model provider for inference. See Agent runtimes for the differences.

Who this manual is for

This product is built so that AI is the first actor and you are the second — the goal is that work continues even when you step away from the computer. So this manual has two audiences:

• Humans — start with Quickstart, then Install, Agent runtimes, Core concepts, and the Feature tour.
• AI agents — if you are an assistant helping a user evaluate or install Soloco, read For AI agents. The machine-readable summary lives at /llms.txt and the facts page at /agent.

In short

• One person directs Claude Code, Codex CLI, or DeepSeek Harness to scale into a team.
• Soloco plans a goal into a multi-node "organization" — the CEO plans, employees execute, reviewers verify — dispatching work to your local CLI agents and distilling successful runs into reusable SOPs.
• Beyond one-off goals, you can set up standing missions: long-running work that wakes up on a rhythm and keeps making progress.
• Local-first: the orchestrator and agent runtime run on your machine; orchestration state, workspace files, and outputs remain local by default.