Frequently Asked Questions

OpenFlows is an autonomous AI software team that turns GitHub issues into reviewed, pull requests. Manager owns organization and tenant state, workspace lifecycle, runtime identity, and credential brokerage. Coder hosts the isolated workspaces where agents run. Nexus coordinates planning, review, and delivery inside a tenant.

Models are enabled in the platform’s AI settings (the Coder dashboard), and you then assign one to each role in the agent registry. Every AI call happens centrally through your own model gateway in the control plane, so you choose the models available to your team and can switch a role to a different model live, without a restart.

Model access follows the configured Coder and agent runtime settings. Manager brokers infrastructure credentials; it does not imply that workspaces never handle secrets. A workspace can receive a scoped bootstrap bundle and short-lived GitHub installation token. See the credential flow.

Each agent runs in its own isolated, disposable workspace provisioned from Coder. It registers with Manager, uses tenant-scoped runtime credentials, and exchanges task messages with Nexus through the hook and A2A path. Its authority is bounded by tenant, workspace, repository, and purpose.

Yes, when the GitHub App installation has access to that repository. Manager verifies the repository belongs to the tenant's organization and brokers short-lived, scoped installation tokens. Human GitHub OAuth is used for sign-in, not as the runtime Git token.

You can self-host Manager, PostgreSQL, Redis, and Coder in your infrastructure. The current GitHub integration needs network access to GitHub for OAuth, App installation, webhooks, and API calls, so a fully air-gapped deployment is not supported as described.

SENTINEL is instructed to attack the work for security holes, quality issues, and missing test coverage against the agreed plan. It reviews from its own isolated workspace and never touches the builder’s files. When it needs proof, it requests a safe, allowlisted command run for evidence. The posture is straightforward: when in doubt, don’t approve.

Recovery is built into the system. A central reconciliation loop retries failing work a bounded number of times. When retries are exhausted, the ticket is parked and escalated to a human - with a notification and links - rather than failing silently or spinning forever.

OpenFlows itself is open-source and free to run; the cost is your own model usage through your gateway. You control it by choosing a model suited to each role - for example, a more careful, higher-cost model for the reviewer and a general coding model for the builder - and tuning from there.

Yes. The agent registry sets how many workers a role may run at once (its concurrency ceiling). OpenFlows runs a fleet of worker workspaces in parallel and assigns work to whichever is free.

Code is available to the workspace and configured model provider. GitHub also receives repository API and Git traffic. Review the provider, Coder, and GitHub data paths before deploying sensitive repositories.

VESSEL, the DevOps role, watches CI and resolves merge conflicts. If a merge block is genuinely unresolvable, the work escalates to a human rather than being guessed at. Approved pull requests are merged when green.

Worker workspaces are short-lived and disposable. They are provisioned when work is assigned and can be torn down when no longer needed. Tokens expire or rotate, but workspace teardown and credential revocation should be verified in operations.

The coordination store is the single, durable record of truth for the whole team - every ticket, worker, approval, review, and pull request. Only the orchestrator and the worker command surface may write to it, and writes are validated. Because the whole team reads one consistent store, Manager can recover queued work after a process failure. Tenant isolation still depends on correct runtime identity and authorization checks.

A central reconciliation loop re-reads the whole system on a steady cadence, advances every piece of work, and repairs what is broken - with bounded retries. When it hits something that needs a human decision, it stops and escalates to you rather than guessing.

Add a skill, connect an MCP server, or enable a different model as a configuration-only change through the control panel - no restart or redeploy. Adding a brand-new role is the one extension that touches the system’s internals. See the Guides and the Agent Registry concept page.

OpenFlows is driven through the Command Surface reference, which covers the control panel and its command-line equivalent in plain language. There is no separate public HTTP API documented here.

Start with the Troubleshooting guide. It covers bootstrap failures, Coder connectivity, stuck tickets, and merge conflicts. If you cannot resolve the issue, open a report on the OpenFlows GitHub repository.