The platform
The absence this makes loud: work that exists in two systems and reconciles in neither.
Self-hosting Graphban is free, unlimited, and genuinely complete — for one developer. The platform is what you want when the work stops being just yours: teammates, shared context, and a bridge into the tracker your company already runs on.
The fork
We're not holding features back to sell you an upgrade. Every mechanism on this site — the grill, the gates, collision clustering, the fleet, the code graph, the learning loop — runs in full when you self-host, with no quotas and no keys. Including multi-agent fleets.
What self-hosting does not have is a way to add a second human. There is no invite flow and no add-member endpoint in the open-source build; a project has one owner and as many agents as that owner mints keys for. That is a real boundary, and it's where the platform starts.
Everything the tool does, on your machine, unlimited and offline. One human owner, any number of agents. Free, and it stays free.
Teammates on the same project, shared memory across people, org roles and audit — and the bridge into Linear and Jira so agents can work the tickets your company already files.
The nuance that matters: multi-agent is not the same as multi-human. A solo developer running twelve agents across four worktrees needs nothing from the platform. Two developers sharing one backlog do.
The headline planned
Nobody is migrating off Jira because their agents find it awkward. So the plan is not to replace your tracker — it's to sit on top of it. Your tickets stay where your PM, your stakeholders and your reporting already live. Graphban becomes the surface your agents actually operate.
Status, plainly: this is designed and decided, not built. Linear is the first integration — cleaner GraphQL API — with Jira second. Webhook coverage, reconcile cadence and packaging are still open. Nothing in this section ships today except inbound GitHub issues.
The argument
You could point an agent straight at a Jira MCP server today. It would read tickets and write comments, and it would be missing everything that makes agent work safe.
Jira has no idea which files a ticket touches, so it cannot partition work between four agents. Touch-areas, clusters and reservations have nowhere to live in a tracker built for humans reading top to bottom.
A tracker will happily let the account that did the work move it to Done. The self-review ban, the independence ladder and the sabotage receipt need an authority that knows about agents as principals.
The grill, the frozen baseline and the completeness pass all operate on intent that has been sharpened and frozen. A ticket description is neither.
Lessons, described code, presence and the audit ledger are agent-native structures. They don't map onto issue fields, and shoehorning them there is how you get a custom-field swamp nobody maintains.
So the split is deliberate: your tracker keeps being the system of record for the business, and Graphban is the system of record for the work. Tickets flow in, status and links flow back, and everything agents need that a tracker was never going to model lives in between.
How it works shipped
The link between a local instance and the hub already exists and already works. Your agents keep talking to the local endpoint; only what's genuinely contended goes up.
Governance private beta
Chat and extraction providers are per-project and resolved from your own credentials. We don't meter token cost, because we aren't buying your tokens.
One append-only row per accepted change, naming the key or user — and for agent actions, the human principal behind the key. "What did my agents do last night" is a query, not an investigation.
Owner/member roles, emailed single-use invites bound to an address and time-bounded, and a project-access model that a key can never out-rank.
A plan is a set of counters — projects, seats, memory shards, metered calls per month. Public surfaces like the feedback intake and public roadmap are never metered, on any tier.
Honestly
A roadmap that reads like a feature list is exactly the failure the rest of this site is about. So every row says which it is. Accurate as of 2026-09-07.
| Capability | Status |
|---|---|
| The tool itself | |
| Tracker, PRDs, grill, gates, code graph, memory, learning loop | shipped self-host and hosted |
| Fleet roles, collision clustering, review pool, enrolment seats | shipped self-host and hosted |
| Local fleet supervisor — spawns a child per seat, reaps it, orphan sweep | shipped separate graphban-fleet package |
| gbfleet until — planner loop around the wave; takeover adopts live children | shipped self-host |
| Native install — launchd / systemd, no Docker | shipped self-host |
| Git delivery contract — agents are told the base branch, or that it is unmeasured | shipped self-host and hosted · v1 does not open PRs |
| Teams | |
| Adding a second human to a project | hosted only no self-host path exists |
| Organizations, roles, emailed single-use invites, seats | private beta |
| Plans, quotas, operator console | private beta |
| Cloud hub for linked local instances | private beta |
| The tracker bridge | |
| Inbound GitHub issues → work items (HMAC webhook, routed by repo) | shipped |
| Outbound: opening real GitHub issues | not built the endpoint is a stub |
| Linear sync — mirror in, constrained write-back | planned first integration, not started |
| Jira sync | planned after Linear |
| Full two-way custom-field sync | not planned deliberately out of scope |
| Other sync that already works | |
| PRD ↔ markdown folder (put it in Google Drive Desktop, no OAuth) | shipped |
| Local → cloud code-graph push, incremental and resumable | shipped |
If a row you need says planned, that's the most useful thing you can tell us on the waitlist — it's how the order gets decided.
Get access
It's running at cloud.graphban.dev and it is invite-only while the org and billing surfaces settle. Leave your email and tell us which tracker you're on — we're picking the first integrations from what people actually answer.
No spam — one email when it's ready. Already have access? Sign in. Prefer to just talk? [email protected].
Just you and your agents? You don't need any of this — self-host it, free and unlimited.