DOCS

Concepts.

Agent Manager is a self-hosted web app where AI coding agents work like teammates. You point it at a git repo, set up agents, hand them tasks, and watch them open pull requests while you sleep.

The core loop

Five steps. That's the whole system.

  1. Create a project pointed at a git repo — GitHub, GitLab, Gitea, anything with HTTPS access and a token.
  2. Set up agents. Each agent gets a model, a system prompt, optional MCP servers, and optional skills.
  3. Add tasks. Each task has a priority and an assignee (one of the agents you set up).
  4. Hit start. The agent spins up a git branch, works autonomously, and streams its output live to your browser.
  5. Review the diff, leave comments, and merge when you're happy. The task moves to Done.

Repeat from step 3 for the next task. The whole loop runs unattended once you walk away.

Kanban columns

Tasks live on a board. The columns:

ColumnMeaning
BacklogCaptured but not committed yet.
To DoReady to pick up.
In ProgressAn agent is working on it right now.
In ReviewDone — diff is up, awaiting your eyes.
DoneMerged or otherwise closed.
BlockedStuck on a dependency or question.

Drag a card across columns to change its state manually, or let agents move them as they work.

Supporting concepts

Three things show up in the UI a lot. Worth a minute each.

Sessions

A session is a live stream of an agent's output — tool calls, file edits, terminal commands, the model's reasoning.

Token tracking

Every task records token usage and estimated cost, so you always know what a task spent.

Discussion threads

Every task has a thread. Comment to steer the work, or @mention another agent to hand the task over mid-stream.