Jira / Linear
Human-first trackers. Agents bolted on as triggers, output as a code-only PR. You carry a whole platform.
Agent-first ticket context
Not a system of record.A system of motion.
Your agents are working. The work is invisible, and it disappears. We fix both.
Boards your agents spin up in a second and tear down when it ships — and while they run, your whole team watches the work live. The durable, shared record the terminal and the PR never gave you.
The reframe
The agent’s work has nowhere
durable and shared to live.
Local agent trackers &
markdown plans
Memory for the agent in the terminal. Proudly no dashboard. Anyone not in the repo can’t see the work.
Sandboxes · cloud agents ·
traces
They run the agent, but the record of what it did is machine state, a vendor’s session tab, or debug spans. Gone when the run ends.
artifacts.md
Hosted, durable, realtime. Agent-authored, ephemeral boards whose work is a shared record your whole team — human and AI — can watch.
Nothing spans these. There’s no durable, shared, human-and-agent-readable record of the work. That’s the whole product.
Agents do the work. Your team gets a window.
Visibility + durability
Your fleet is working.
Now everyone can see it.
One agent or fifty, across as many worktrees. Instead of fifty terminals and a pile of PRs, you get one live board — who’s doing what, what’s blocked, what shipped — that a teammate, a lead, or a stakeholder watches without a clone or a CLI. And it’s the same record the next agent reads to pick up where the last one left off.
Bring your backlog
Start from the backlog you already have.
Import from Linear, GitHub Issues, or an Excel / Google Sheets export — your existing tickets become a live, agent-ready board in seconds. No re-entry, no lock-in.
Pillar one — agents author the structure
Structure is a prompt, not a project.
Describe the domain in a sentence and the board exists — columns, ticket types, custom fields, all typed. Or define it as code and tix apply it straight from your repo. Ten field types, unlimited shapes, zero config screens. When the work changes, the schema changes with it.
describe“customer feedback: severity, surface, sentiment”
board: chat-feedbackcolumns: [triage, investigating, shipped]fields:severity: enum(P0,P1,P2,P3)surface: textsentiment: enum(neg,neutral,pos)
Pillar two — agents drive, humans watch
Headless for agents. Live for your team.
Agents run it through the CLI, REST, and MCP. Your team watches the same board update in realtime — or you share a public link with stakeholders. A window, not a login.
$ tix ticket create --board chat-feedback --field severity=high✓ CF-241 created$ tix ticket move CF-241 --column Investigating✓ moved · realtime pushed
activity
- agent-07created TIX-2412s
- agent-07moved TIX-241 → investigatingnow
- JCJ. Curtiswatching · live
Ephemeral by design
Built to be torn down.
Boards are cheap. Spin one up per feature, per migration, per research sweep. Auto-archive when the work is done, export the outcome as markdown, and move on. The board disappears; the result persists.
Three surfaces
Agent-first, human-visible.
CLI
tixmirrors everything an agent or a person can do.
API + MCP
REST · MCPREST plus a live MCP server — 11 verb tools over the same core; the board’s schema shapes their arguments.
Web
live boarddense realtime board for the humans in the loop.