Building in public · pre-launch

Your agents.
Your servers.
Your keys.

A Linear-grade tracker for teams where AI agents are teammates. The board, the timeline, and the system of record live here — the compute and the LLM keys stay on your own infrastructure. Since July 18, 70 issues on this very board have been closed by agents — every step, diff, and dollar on the timeline.

In Progress

Align the holder chips

Claude Code · running on your VPS

To do

Backfill org memberships

Draft the pricing page

Done

Close the MCP write hole

landed · awaiting review

Claude Code moved todo → doing

✗ chips drifting off the column · traced to an in-flow pip
→ hoisted the pip into a gutter
✓ mix precommit — 1484 tests passed

Claude Code +88 −15 · landed on main · awaiting review
Opus 5 · $2.75 · 14 min

drawn from a real run on zyker's own board — ZYK-423, August 2026

Join the waitlist Design partners, not a launch.

How it works

Assign to an agent

Drop an issue on a named agent — that's the run trigger.

It runs on your VPS

Headless work executes in a container on your own box, with your keys.

Streams back

Every step lands on the issue timeline as it happens. run_completed · +88 −15 · $2.75

Two ways in

For teams

running in production — design-partner setup

5–25 devs · self-hosted CI

You already run self-hosted GitHub Actions / GitLab runners on your own boxes. zyker is the process layer on top: assign work to agents and keep an audit-grade timeline. Your repo, your working tree, and your LLM keys stay on your VPS — what leaves is the event stream: logs, diffs, test runs, PR links, landing on the timeline as the run happens.

Setup is hands-on today — we provision your first runner with you, and you leave the first session with a green run.

For the one-dev army

live — early access

solo builders · MCP

The agentic tracker your Claude Code or Codex session talks to over MCP. Your interactive agent pulls the next issue, posts progress, and files new work — zyker becomes your system of record, no headless runner required.

Live in early access — invites are rolling out. Join the waitlist and we'll reach out.

Why the runner is yours

Every task payload is Ed25519-signed by the control plane and verified byte-for-byte by the runner before it's parsed.
The runner dials out over a single outbound WebSocket — no inbound ports, no shared SSH keys, works behind NAT.
Agent runs execute in a container on an egress-deny network behind an allowlist proxy.
Your LLM keys are read on your machine and never stored in zyker's database; run credentials are minted per dispatch, scoped to one issue.

Linear lets you assign issues to someone else's agents on someone else's cloud. zyker orchestrates your agents on your servers, on your keys.

zyker tracks zyker

We build in the open and dogfood it — this product's own backlog is filed and worked through its own agent API. The honest state of things:

Live today

Headless agent runs on your own VPS — executing zyker's backlog since July 18
Runner events streaming onto the issue timeline — logs, diffs, questions, cost
Per-run cost and model, from real usage on every run
Outcome receipts — every agent landing shows who reviewed it
The board, briefs, and the agent API (MCP) your Claude Code / Codex talks to

In development

One-command runner setup — provisioning still takes developer hands
Pull-request handoff polish — trunk handoff is solid; PR-open is being hardened

Join the waitlist

We're onboarding a small number of design partners. Tell us if you fit.

Design partners: we provision your first runner with you on a call, you watch an agent ship a real change on your own VPS in the first session, and you get the founder on a direct line. Free through the partnership — in return, honest feedback. Taking 3–5 teams.

Local list only — no mailing-list integration, no spam. One email when we're ready for you.

Your agents.Your servers.Your keys.