vibey

A queue-based, six-phase conductor for autonomous software delivery — with an optional visual-design interstitial and opt-in Azure deployment — built on top of the *loop autonomous session runners.

What problem this solves

An autonomous coding session is not autonomous software delivery. A single claudeloop run can finish a task, but it cannot interview you until the spec is sharp, split the work into parallel items, verify each one against gates it cannot game, survive its own credit exhaustion by handing off to a different vendor's engine without losing a single open question, or know that a review finding should reopen design rather than vanish into a transcript.

Vibey conducts all of that. You describe what you want; it interviews you until the spec is sharp, builds unattended across a pool of engines with real budget caps, reviews the result with you, and (only if you opt in) deploys. Every choice, finding, and handoff lives in an append-only PostgreSQL ledger — never in one vendor's chat session.

Install

Requires Python 3.12+, PostgreSQL, and at least one *loop engine on PATH. Windows is not a supported target.

uv tool install vibey          # or: pipx install vibey / pip install vibey
uv tool install claudeloop     # at least one engine; add codexloop, cursorloop, agyloop for rotation
vibey doctor                   # pre-flight: database, engines, auth

Quickstart

vibey doctor --conformance --record          # verify each engine's contract, persist health
vibey new my-app --repo ~/src/my-app \
  --max-cycle-dollars 15                     # real budget brake, enforced from the ledger
vibey worker --engines claudeloop,agyloop -j 2   # unattended build across the pool

# When vibey parks for your input (design gates, review, budget grants):
vibey answer <gate-id> --defaults            # accept the interview defaults, or:
vibey answer <gate-id> --raw '{"max_dollars": 25}'   # raise a tripped budget cap
vibey design accept <project-id> --no-visual
vibey answer <gate-id> --verdict accept      # review demo
vibey answer <gate-id> --choice local_only   # decline deployment → DONE (local)

The greeter live-demo runbook walks a full paid run end to end, including the zero-touch contracts.

The shape of it

  DELIVERY STAGE SET
  INTAKE → ① DESIGN ──┬─ no ───────────────→ ② BUILD ⇄ ③ REVIEW
                      │                       autonomous / interactive
                      └─ yes → [VISUAL DESIGN]
                                interactive, media generation + confirmation
                                          │ visual-ready
                                          └──────────────→ ② BUILD

  ③ REVIEW ── no deployment ─────────────────────────────→ DONE (local)
       │ opt in
       ▼
  DEPLOYMENT STAGE SET
  ④ DEPLOY DESIGN ⇄ ⑤ DEPLOY EXECUTE ⇄ ⑥ DEPLOY REVIEW → DONE (deployed)
       interactive       autonomous          interactive
             ▲                 │                    │
             └─────────────────┴────────────────────┘

Phases 1, 3, 4, and 6 talk to you. The optional Visual Design stage also talks to you and cannot hand work to BUILD until every planned visual is accepted or you explicitly waive the stage. Phases 2 and 5 run unattended, survive rate-limit windows and credit exhaustion, and rotate eligible engines/providers when one runs dry. Phase 3 asks whether to deploy; "no" is a successful local completion. Phase 6 accepts a successful deployment, requests changed deployment details in Phase 4, retries an unambiguous deployment in Phase 5, or routes an application defect back to the appropriate delivery phase.

Why it isn't just another agent framework

The hard part is not calling an LLM in a loop — claudeloop and its siblings already solve that, including the distinction between a waitable rate-limit window and exhausted credits that no amount of waiting will fix. Vibey adds the things those runners deliberately do not do:

1. A phase machine with loop-backs, so a review finding becomes a new design conversation rather than a lost note.
2. Round-robin engine rotation with lossless handoff — the conversation is an append-only event ledger, not a chat transcript locked inside one vendor's session, so any engine can pick up where any other left off. A handoff that would lose an open question, decision, assumption, or finding is rejected by a pure, deterministic no-loss gate — never silently accepted.
3. A durable queue, so work survives a laptop lid closing, a crash, or a provider outage, and so multiple work items build in parallel in isolated git worktrees.
4. Real money brakes — per-cycle dollar and turn caps summed from the ledger's own cost events, with parks that tell you the exact command to grant more.

Documentation

Status

Live-validated. The full pipeline has conducted real paid deliveries end to end: multi-worker builds (-j 2) with cross-engine rotation (claudeloop implements, agyloop verifies), the bounded verify-repair ladder, budget caps tripping and being granted live, and fully zero-touch DESIGN phases answered with nothing but --defaults. The validation campaign's findings — a blind budget brake, a repair-loop livelock, terminal gate-command failures — were each fixed and re-validated live.

Every architectural layer (domain, application, infrastructure, cli) holds a 100% branch-coverage floor, enforced as four separate CI gates. domain/ is pure stdlib, enforced by import-linter and an AST-walking purity test — the no-loss handoff gate is deterministic code, not a model's opinion.

Related projects

License

MIT © Adam Matthew Steinberger