Alfred is a team of coding agents that works from a spec, a Slack message, or a GitHub issue and turns it into a reviewed pull request. It autonomously plans the work, writes the code, opens the PR, and reviews it, on the Claude and Codex subscriptions you already pay for.
Alfred comes with an optional desktop app. See every agent and what it is working on, check how much of your Claude and Codex usage is left, and start a new request in plain English. Slack is still where you discuss and approve plans.
Each agent has one plain job. You can start with planning, implementation, and review, then add test coverage, reviewer-comment fixes, and safe automerge when your process is ready.
Leads large work that touches more than one repo: reads the parent issue or Slack plan, checks the affected repos, gets approval, files the repo-level work, and keeps the bundle moving.
[10:30] batman drafted bundle:billing-v2 [10:31] batman posted plan to Slack [10:34] scope approved [10:35] batman opened backend -> web -> mobile tasks
Picks up a scoped task, makes its own copy of the repo, runs Claude Code or Codex with the full project in context, and opens a pull request with tests.
[12:04] lucius claimed your-backend#247 [12:04] lucius worktree ~/.alfred/wt/12042118/ [12:18] lucius PR #1247 opened
Reads a Slack request, GitHub issue, or plain-text plan, asks for missing details, then files small tasks a coding agent can pick up on its own.
[09:02] drake refined settings plan [09:02] drake filed your-backend#248 agent:implement [09:03] drake linked acceptance checks
Reads the changes, runs your test suite in its own copy of the repo, leaves comments on the lines that need work, and marks the pull request ready or needs changes.
[12:18] ras-al reviewed PR#1247 [12:18] ras-al filed 2 inline nits [12:19] ras-al labelled needs-changes
Looks at recently changed files, finds the places that need coverage, and opens focused test PRs that stand on their own.
[15:10] bane found low coverage in billing [15:23] bane PR #1250 opened [15:24] bane labelled tests-only
Finds Alfred PRs with unresolved high-priority review comments, applies the fix in a clean worktree, and pushes the update back to the PR branch.
[16:01] nightwing found P1 on PR#1247 [16:08] nightwing pushed fix [16:09] nightwing asked for re-review
Alfred checks the Slack drafts, plans, and GitHub issues you marked for it, works in isolated repo copies, opens pull requests, routes review, and comes back to Slack when it needs a decision.
Alfred finds the next task, hands it to the right role, runs the work in an isolated repo copy, routes review, records memory, and comes back to Slack when a human decision is needed.
A Mac mini, an old MacBook on a dock, or a small Linux box is enough. Alfred runs locally, using the Claude Code and Codex subscriptions you already pay for.
Planning happens in a Slack thread. Reply with what you want, what should change, or questions of your own, and Alfred turns the discussion into the next task. Nothing big runs until you approve it.
Alfred keeps notes about each repo on your machine. New lessons wait for your approval before they shape future work, so a wrong guess never gets treated as fact.
Alfred can plan a single feature across several repos at the same time. It works the same way inside a monorepo, whether you use Turborepo, Nx, or Cargo workspaces.
Every line is on GitHub at github.com/luminik-io/alfred-os. Fork it, read it, run it locally, or audit the code.
Alfred keeps notes on your own machine: lessons you have approved, which files agents changed, what went wrong before, and what is in progress right now. You see and approve new lessons in Slack or the desktop app before they ever shape future work.
Agents and trusted teammates can suggest a lesson worth keeping. A suggestion waits for approval before it changes future work. That keeps a wrong guess from becoming part of the system.
Setup blockers, timeouts, and repeated test failures all land in one place. The next time something breaks, your agents start from what happened before instead of digging back through old Slack messages.
Alfred starts a local Redis Agent Memory Server for recalled lessons, then keeps FleetBrain as the review queue and reliability ledger. The memory loop stays on your machine.
Start with a Slack thread, a GitHub issue, or a plain-text plan. Batman leads multi-repo features, Lucius handles repo-local implementation, and Drake turns smaller requests into clear tasks.
Batman is the accountable lead for work that spans repos. It reads the parent issue, checks the affected repos, plans the rollout, gets approval in Slack, opens the repo-level work, and keeps the bundle visible until the implementation fleet can finish it.
From the moment a run starts to the pull request it opens. The same five stages happen every time an agent fires.
Slack is the planning and control surface. Trusted users can start requests, refine plans in a thread, approve big work, ask for status, pause agents, and keep context attached to the work. Slack never bypasses the approval gates.
Real output from one builder's setup on 2026-05-23: twenty agents, three paused on purpose, and one waiting on a Batman approval.
Alfred
alfred status output from a real Mac, captured 2026-05-23. Cost is $0.00 because Alfred runs on your own Claude and Codex subscriptions, not pay-per-token API bills. The amber row is Batman holding two large plans for your approval; the paused rows are agents that were stopped by hand.
Run doctor for setup health, then dry-run one agent to see the path it would take without touching GitHub, Slack, an engine, or your files.
In the last 30 days, Alfred helped merge 71 PRs across 9 Luminik repos. The impact page shows aggregate product totals and public examples.