CI/CD that fixes itself.

When a run fails, Hive collects the logs, diff, and failing checks, and dispatches an AI agent with that context. The agent reproduces the failure, writes a fix, re-runs the affected checks, and opens a PR on your branch with the diagnosis attached. You review and merge like any other PR — nothing lands without you.

Only to the model provider you configure, using your own API key. Hive never stores or trains on your code. Your source is checked out on the runners you connect, so with your own runners the code never touches our hardware at all — and artifacts, images and test databases stay on your disks unless you opt into storing them with us.

Hive is operated by Pulsar-Projekte GmbH, a German company registered in Bavaria. The control plane runs on a server in Germany; this marketing site is delivered as static files by Cloudflare. There is no analytics, no tracking and no cookie banner here — the Datenschutzerklärung sets out exactly what is processed and on what legal basis.

You bring your own model API key, so token costs go straight to your provider at their rates — no markup. Hive shows per-fix token spend and lets you set hard daily caps, so there are no surprise bills.

No — but you can use it, and it is free if you do. We host the control plane and the UI; you choose where the work runs. Connect your own machines as runners with a one-line install (Linux, macOS, Windows), rent capacity from us as booster packs, or mix the two and let the queue spill over onto ours when yours is full.

Yes, and that is the default. An agent launched onto your workstation gets a real git worktree there — your checkout, your toolchain, your credentials — so nothing is uploaded anywhere. The same agent can run containerised on rented capacity instead when you want your laptop back or need ten at once, and you choose per task. Either way you watch and steer it from the browser.

Compute you rent from us by the minute instead of buying. When a run needs capacity your own runners do not have, Hive starts a VM, runs the work on it, and stops billing when it shuts it down. You see what each run spent, and a wallet that runs out queues the next job rather than quietly charging you for it. Private-beta tenants get 50,000 CPU-minutes a month. Packs are denominated in compute rather than money, so a repricing changes what a new pack costs and never what you already hold.

No. A repo opts in by committing one file, and Hive starts in shadow mode — it posts its own status and requires nothing, so your existing pipeline keeps gating merges exactly as before. You compare the two on real commits for as long as you like. Making Hive a required check is a separate decision you make in your repo settings, and our own onboarding runbook tells you not to retire the old CI until a preflight check reports clean. Start with one repo, one job — a useful pipeline is a few lines — and widen it when it has earned that.

No — it runs them. Hive’s agents authenticate as you, with the subscription or key you already pay for: an Anthropic Claude or OpenAI Codex subscription, a Cursor account, or an OpenRouter key routing to whatever model you like. Your local setup is untouched, because CI runs server-side and needs nothing installed on your machine. And Hive exposes over a hundred MCP tools, so you can drive runs, read logs and diagnose failures from the editor and agent you already use instead of switching to our UI.

Actions runs your workflow and hands you a red X. Hive runs your pipeline and hands you a fix. Beyond the factory, you get pipelines as real code (Starlark, not YAML), warm caches by default, and the choice of whose hardware the work runs on — yours at no compute cost, ours by the minute, or both.

Hive is in private beta now. Waitlist members are invited in order and get early-bird terms; every beta tenant gets 50,000 CPU-minutes a month to run jobs on our hardware while they try it — about 12× GitHub Actions’ free tier.