harbour

Keep human intent in command of AI execution

Log in with Linear Continue with GitHub

the loop

One human, steering a fleet of agents

AI made writing code cheap — it didn’t make knowing what to build any faster. Harbour keeps human intent in command of AI execution, one turn of the loop at a time.

  1. 01

    Read the backlog

    Point Harbour at Linear, GitHub, or a local store. It reads the whole tree and ranks the frontier — what is actually ready to move.

  2. 02

    Ground a prompt

    The right next task becomes a prompt, re-grounded against your code at HEAD — referenced files re-read, stale plans challenged, not trusted blind.

  3. 03

    Dispatch to an agent

    Queue it for a coding agent to poll, claim, and run — or fan a whole cohort out at once. One human, a fleet of sessions.

  4. 04

    Verify on evidence

    Work lands against real proof — CI, merges, diffs — not the agent’s say-so. Observation shows every run as it happens.

observation

Watch the work happen

Every dispatched run, live: what it is doing, how long it has taken, and the evidence it produced — not a spinner, the actual work.

swim lanes

See the whole board at a glance

Parallel tracks, with the dependencies drawn in. Know what is ready, what is moving, and what is held — before you dispatch.

grounded prompts

Prompts that re-check your code first

Two paths — 14 deterministic templates and an LLM meta-prompt — both re-grounded against the repo at HEAD before they run.

any backend

One cockpit, whatever tracks the work

the workstation

Harbour OS

Harbour is the control plane; Harbour OS is the in-browser workstation it dispatches sessions into. Parent and child, like Apple and macOS — Harbour picks the work, Harbour OS runs it.

Open Harbour OS →