Answers for developers, team leads, and technical founders evaluating Cate.
Cate is a desktop application for agentic software development orchestration. It connects to the tools you already use — GitHub, Jira, CLI agents — and coordinates them into a development team. Agents work issues from your board, write code, open PRs, and review each other's work. Humans retain final authority over what merges to main.
Cate orchestrates agents that write real code and open real pull requests. They implement features end-to-end — committing to isolated worktrees, running your guardrails, and submitting PRs for review. No code lands in main without a human merging it.
No. Agents work in isolated worktrees and open pull requests. Merging to main is a human-only action. The status lifecycle — from "To Do" through "AI Review" to "Human Review" — is designed so humans are always the final gate before code is promoted.
Cate needs read/write access to your repository to create branches, commit code, and open pull requests. It also needs access to your project board to read and update issue statuses. The exact permission scopes depend on your issue tracker and git host.
Credentials are stored locally on the machine running the Cate desktop app. They are not transmitted to Blue Ghost servers. Agents use credentials only to authenticate with your configured services (GitHub, Jira, etc.) on your behalf.
Cate is an Electron app, and it follows Electron's recommended best
practice for secret storage by using the
safeStorage
API. This delegates encryption to your operating system's native
secret store — macOS Keychain, Windows DPAPI, or libsecret on Linux.
The prompt appears once on first launch when Cate encrypts its first
credential. After you grant access, it works silently in the
background.
Autonomy is configured per-issue using labels. The default is
autonomy:full—agents work end-to-end without
checkpoints. Tag an issue autonomy:plan to require
human approval of the implementation plan before coding begins. Use
autonomy:supervised
to require approval at every step. You decide the right level for
each piece of work.
Agents run every guardrail defined in your project's
.cate/guardrails/
directory before opening a PR. Common gates include automated tests,
linting, HTML validation, and code formatting. If any required gate
fails, the agent fixes the issue before proceeding. You define the
standards once; agents enforce them every time.
After an agent submits a PR, a dedicated reviewer agent performs a structured code review—checking correctness, adherence to acceptance criteria, and guardrail results. If the review passes, the issue moves to "Human Review" so a human can do a final check and merge. If changes are needed, the issue returns to "To Do" for revision.
If an agent cannot complete a task, it posts a detailed handoff comment explaining what was tried and why it got stuck, then moves the issue back to "To Do" for triage. Bad code is caught at review: reviewer agents or humans request changes, the issue returns to "To Do", and the next agent picks it up with the feedback in hand.
Persistent worker tabs are pre-allocated when you open a repo in the Cate app. They claim issues from your board and work through them continuously. On-demand tabs (for planning, collaboration, or custom workflows) spin up when needed and terminate when the session ends. You control how many workers run and when.
Cate currently supports GitHub Issues (with GitHub Projects for
board management), Jira, and Linear. The tracker is configured in
your project's
.cate/workflows.json file. Additional tracker
integrations are on the roadmap.
Most teams are up and running in under an hour. You install the Cate
desktop app, connect your GitHub or Jira account, configure your
first project's workflows.json, and define your
guardrails. The setup command walks you through each step
interactively.