Skip to content

AI devs · Fleet

Your AI dev team. Your hardware. Your keys.

A fleet of fungible AI agents that triage issues, review PRs, and ship releases — triggered by GitHub events, bounded by your .maintainer.yml, audited on every action.

Install GitHub AppSee how it works

Live fleet

See work moving, not tickets waiting.

Every task in the fleet has an owner, a stage, a policy boundary, and an audit trail attached — across every repo the app is installed on.

Fleet / live3 active
Agent 01

Upgrade zod across services

  • Read repository context
  • Proposed implementation plan
  • Running checks
Agent 02

Fix auth redirect loop

  • Read repository context
  • Proposed implementation plan
  • Writing tests
Agent 03

Refresh the quickstart

  • Read repository context
  • Proposed implementation plan
  • Opening pull request

Assignment to review

  1. 01
    Issue triaged

    A GitHub event wakes the agent; it reads the report and talks to the reporter.

  2. 02
    Context mapped

    Repo, thread, and .maintainer.yml are read before anything acts.

  3. 03
    Coding delegated

    Implementation goes to your coding agent — Copilot, Claude Code, or OpenHands.

  4. 04
    PR watched

    The agent reviews the diff, chases CI failures, and keeps the thread moving.

  5. 05
    Gates passed

    CI green, review approved, branch protections satisfied — gates are machines.

  6. 06
    Merged and shipped

    Auto-merge lands it; the release loop ships it. Every action is in the audit log.

The output

Pull request #482

fix: refresh expired installation tokens

Ready to merge
6 files changed · +84 −19Policy checks passed

Built for teams that ship

  • BYOK — bring your own keys

    Connect Anthropic, OpenAI, OpenRouter, or any OpenAI-compatible endpoint. We never proxy or resell tokens. Your model bill, your call.

  • Your hardware (BYOC)

    Each ai-dev slot includes 3 self-hosted CI runners. Your VPS, your metal — zero cloud compute markup.

  • Zero quotas

    No task caps, no file limits, no per-seat add-ons. Flat $500 / ai-dev / mo during beta — everything included.

  • Every action audited

    Every tool call, decision, and merge gate is logged with full reasoning. If it isn't in the audit trail, it didn't happen.

  • Always discloses

    The bot never impersonates a human. Every comment, reply, and merge note identifies the agent clearly.

  • Policy, not state machines

    Drop a .maintainer.yml in your repo. The agent reads it as policy — no hardcoded workflows, no hidden defaults.