Introduction
Deploy AI software engineers from YAML files in your repository.
An Ellipsis agent is a YAML file in your repository. It runs Claude in an isolated cloud sandbox with your repositories cloned and your GitHub, Linear, and Slack integrations connected, on a schedule, in reaction to events, on @ellipsis mentions, or on demand.
Quickstart
Three commands to a running agent. Full walkthrough in the Quickstart.
brew install ellipsis-dev/cli/agent
agent login
agent session start --template welcome-to-ellipsis --watchGet started
Quickstart
Install the CLI and run your first agent in three commands.
Your first agent
Write an agent config from scratch and deploy it from your repository.
Guides
Run agents on a schedule
Cron triggers: weekly digests, daily triage, dependency checks.
React to repository events
Start sessions when PRs, issues, pushes, or Linear issues happen.
Answer @ellipsis mentions
Route mentions on GitHub, Slack, and Linear to an agent.
Bring secrets into a sandbox
Sandbox variables: inject credentials without putting them in the file.
Customize the sandbox
Bake tools into the image and run setup hooks before the agent starts.
Start sessions from CI and scripts
Trigger and watch sessions from the API and CLI.
Concepts
How a session executes
The session lifecycle: statuses, steps, costs, and what each session records.
Budgets and spend
Per-session budgets, trailing spend limits, and per-developer limits.
The sandbox
The isolated environment agents run in, and how to detect it.
Agents as code
Why GitHub is the source of truth, and how sync works.
Analytics
Engineering metrics across humans, bots, and AI agents.