Skip to main content

Your host. Your keys. Your repo.

Fragua is the opposite of a done-for-you platform. It's opinionated, Rails-deep, and self-serve — agents run on a host you manage, with your own credentials, and we never sit between you and your provider. The orchestration is ours; the keys, the code, and the repository stay yours.

Control plane · Fragua web app

Orchestration, the live timeline, cost roll-ups, the audit trail. Run it as managed SaaS or on your own hardware.

directs → ← events · cost
Your execution host

Your gh and Claude credentials, your repo, isolated git worktrees. Your keys and code never leave it.

never proxied →
Your AI provider

Tokens billed straight to your account. Fragua can't see the bill.

AI traffic runs host → provider directly. Fragua is never in the path.

A control plane you watch. A host you control.

Fragua is built around the two-plane split above. Orchestration and observability live in the web app; the agents — and the credentials they use — live on a host you run. A connector on your host picks up the work, runs it locally, and streams back only the events and cost. The web app directs; your host executes, and your access and your AI stay on infrastructure you own.

You register a machine by running fragua login on it. The web app sees it come online, bind to its workspaces, and report capacity — and you can forget it at any time.

Connected machines

2 machines
  • daniela-mbp.local Online
    last seen less than a minute ago · 1 / 3 sessions · darwin-arm64 · v1.0.0 · runner 2.1.170
    almighty-monolith marigold
  • mateo-studio.local Online
    last seen 2 minutes ago · 0 / 3 sessions · linux-x64 · v1.0.0 · runner 2.1.170
    nimbus
Connected machines · illustrative
daniela-mbp.local · ~/fragua-workdir
fragua status
Runner name
daniela-mbp.local
Runner uuid
03ga8dtatew7a6mmqt2a9w1lh
Control plane
https://fragua.app
Workdir
~/fragua-workdir
Concurrency cap
3
Authentication
token present
Daemon
running (since 2026-06-10T13:54:10)
Server reachable
true
Active sessions
1 / 3
Pending reports
0
Errors
0
Managed workspaces
brujula-6396/almighty-monolith (cloned)
brujula-6396/marigold (cloned)
fragua doctor
ok claude 2.1.172 (Claude Code)
ok git git version 2.54.0
ok gh github.com
ok control-plane reachable and authenticated
The fragua host CLI · illustrative

We never sit between you and your AI provider.

Agents run through the provider's own CLI on your host, using the credentials already configured there. Fragua orchestrates the run and parses the usage — it never carries your AI traffic.

Never proxied

Your AI calls go host → provider directly. Fragua isn't in the path.

Key never stored

Fragua never holds your key — the CLI reads it on your host.

Billed to you

Tokens bill straight to your provider account. We can't see your bill.

Runs on your host

Agents run on a host you manage; only events and cost flow back.

Pushes and pull requests use your own access.

When an agent commits work, pushes a branch, and opens a pull request, it does so through the GitHub access already present on your host — your gh and git credentials. Fragua doesn't hold a persistent token to your repositories.

The code stays in your repositories the whole time. Every network step soft-fails: if a push or a PR can't complete, the committed work stays safely on disk in its worktree rather than disappearing.

Isolated worktrees

Each feature runs in its own git worktree on its own branch — work on different features never overlaps.

Workdir outside the app

Agents run in a directory outside the Rails app, sharded per account and workspace — never inside Fragua's own tree.

Clean runner environment

The agent process is launched with Fragua's own Bundler context scrubbed, so it runs against your project's toolchain, not ours.

How agents read workspace context

A scoped callback token — never your AI key.

When an agent needs workspace context — like the Knowledge Base — it calls Fragua's own API with a per-user token that's stored hashed, scoped to that user, and revocable at any time. It's a Fragua-internal credential: it never touches your AI provider, and it carries none of your code or keys.

Self-serve, on your terms.

Fragua is in private beta. A human reads every access request before a seat opens.