Introduction
Overlord is a management, work coordination, and review layer for AI-assisted engineering work. It keeps the ticket, progress, review, and delivery record in one place while your agents keep working in the tools you already use.
The mental model
The objective is the unit of work.
It carries the prompt, agent choice, checkpoint, attachments, and execution state for a single agent pass.
The ticket is the higher-level goal.
It groups objectives that share context, such as a feature, bug fix, investigation, or review thread.
The agent stays where it already works.
Overlord coordinates Claude Code, Codex, Cursor, OpenCode, and other setups instead of replacing them.
Humans stay in the loop.
Progress, questions, artifacts, and review decisions come back to the same ticket.
Product surfaces
Five parts serve the same ticket-centered workflow.
Web App
Manage tickets, projects, activity, artifacts, and review in one shared place.
Desktop App
Adds local machine capabilities so Overlord can work with real repositories and terminal sessions.
CLI
Gives agents and humans a stable terminal interface for attaching, updating, asking questions, and delivering work.
MCP Server
Lets remote or hosted agents work with the same tickets and protocol without depending on the desktop app.
Agent Plugins
Connects local and cloud agents directly into your ticket workflow from the tools they already run in.
How it works
Step 1An objective defines the agent pass
The objective is the unit of work. It keeps the prompt, agent choice, checkpoint, attachments, and execution state for the pass.
Step 2The ticket keeps the shared goal
Tickets are higher-level goals, like a feature or bug fix, composed of objectives that share context and delivery history.
Step 3Progress streams back into the ticket
Updates, blocking questions, artifacts, and session state flow back into the same ticket so humans can stay involved without hovering in the terminal.
Step 4Humans review before work lands
Review the output, inspect diffs and rationales, answer questions, and decide what should happen next.
Quick start
1. Create a project
Projects are initiatives that share a code repository, folders, and other resources. Link one to a local repository in the desktop app.
2. Write a ticket
Give it a clear objective, optional acceptance criteria, and enough context for an agent.
3. Launch the agent
Use the desktop app or the CLI and MCP workflow for a terminal-first flow.
4. Review what comes back
Watch updates, answer blocking questions, and review artifacts and diffs.