Quick start Docs Hub

Vibestrate

What if you had your own CTO?

Vibestrate is the orchestrated environment around your AI coding. An advisor that manages the crew and catches the problems, while you stay the one in charge. Bring one model or a whole roster.

Show me how
Vibestrate

What if you had your own supervisor?

It orchestrates your AI coding crew, catches the problems, and never ships without your say-so.

Star

AI coding needs a supervisor.

A second model reviews it.

See how it works

It doesn't just agree with you.

It argues with itself. A different model reviews the change with fresh eyes, so the one that wrote it is never the one that signs it off.
Your checks are the gate. "It looks done" is not enough. The change has to pass the tests you already set.
You make the call. It stops at merge-ready and never pushes or merges behind your back.
Claude Code·Codex·Gemini·OpenCode·Aider·Cursor CLI·Ollama

On its own, AI loses the plot. With Vibestrate, it ships.

Your supervisor never misses.

It tells you straight, not what you want to hear.

Show me how

How a run works.

Six steps, from one line to a finish you approve. Hover a step.

Task
Task

Just say what you want, like you'd tell a teammate. That's the whole brief.

Flow
Flow

A ready-made recipe of steps (plan, build, review, and so on). Pick one or grab one from the hub.

Crew
Crew

Every step gets a seat. You drop in a model for each, so the right one does the right job.

Run
Run

The steps run in order, and each model's work gets handed to the next. No copy-paste.

Review
Review

It stops at the risky moments and at the end. You approve, send it back, or let a check decide.

Trace
Trace

Every prompt, change, and dollar spent lands in a log you can read and replay anytime.

And you can ask Consult anything along the way - a read-only advisor that knows your project. It recommends; it never touches your code.

Read the full walkthrough

How a run works.

One line in, a finish you approve. Swipe through it.

Task
ship the new pricing page

Say what you want, like you'd tell a teammate.

Flow
ResearchDraftReviewShip
quality-arbitration · pulled from the hub

Pick a recipe of steps, or grab one from the hub.

Crew
  • PlanCClaude
  • ReviewGGemini
  • ShipXCodex

Drop the right model into every step.

Run
  • PlanClaude
  • BuildCodex
  • TestGemini

Each model's work is handed to the next. No copy-paste.

Review
+128−343 files

It stops at the risky moments. You approve, or send it back.

Trace
  • planClaude$0.04
  • buildCodex$0.09
  • testGemini$0.08
$ vibe run replay a3f2$0.21

Every prompt, change and dollar, logged and replayable.

A hub of flows that do the hard part for you.

Browse flows built by people further down the road, pull the one you need, and run it in seconds. Publish yours with one command and put your name on it.

A flow is a saved recipe of steps. Pull one that already works.

$ vibe flow pull quality-arbitration
$ vibe flow pull guy@deep-refactor
$ vibe flow publish my-flow

One flow,
any crew.

Fix the flaky checkout test
Plan Claude Sonnet
Build Codex
Test Gemini Flash
Review Claude Haiku
Fast Crew quick and cheap
Claude SonnetCodexGemini FlashClaude Haiku

One flow. Any crew.

quick · cheap
  1. Plan Claude Sonnet
  2. Build Codex
  3. Test Gemini Flash
  4. Review Claude Haiku

Free, open, and yours.

Free and open source under Apache 2.0. Read the code, fork it, ship your own flows. The best ideas from the community become everyone's setup.

  • open source
  • free forever
  • Apache 2.0
  • local-first
  • runs offline
  • no telemetry
  • your keys
  • your models
  • your machine
  • no lock-in
  • no SaaS
  • any model
  • multi-agent
  • any CLI
  • BYO keys
  • git worktrees
  • fully auditable
  • replayable runs
  • you approve
  • never auto-merges
  • cost ledger
  • no API keys
  • self-hosted
  • watch it work

See everything, in one place.

merge-ready rate 98% ▲ 4 pts this week
flow · quality-arbitration
Plan Architect Implement Review Verify
src/routes/health.ts + app.get('/healthz', () => reply.send(ok)) + export const ready = true - // TODO: add a health check 18 / 18 tests passing
run · healthz merge_ready APPROVED · 18/18 · $0.84 · 8m
merge-ready rate 98% ▲ 4 pts this week
flow · quality-arbitration
Plan Architect Implement Review Verify
src/routes/health.ts + app.get('/healthz', () => reply.send(ok)) + export const ready = true - // TODO: add a health check 18 / 18 tests passing
run · healthz merge_ready APPROVED · 18/18 · $0.84 · 8m
cost ledger
Claude Opus6.2k$0.11
GPT-512.4k$0.28
Gemini Pro8.0k$0.14
total36k$0.84
crew
Claude Opusplan · review
GPT-5implement
Gemini Proarchitect
runs / day
avg cost / run $0.84 ▼ 38% vs last week
cost ledger
Claude Opus6.2k$0.11
GPT-512.4k$0.28
Gemini Pro8.0k$0.14
total36k$0.84
crew
Claude Opusplan · review
GPT-5implement
Gemini Proarchitect
runs / day
avg cost / run $0.84 ▼ 38% vs last week
your control
✓ nothing ships without you
✓ runs on your machine
✓ your keys, your models
✓ no telemetry, ever
verification
✓ policy passed
✓ validation 18/18
✓ review approved
✓ never auto-merged
3 active worktrees
healthz-endpoint isolated
pg-16-migration isolated
search-latency isolated
awaiting your approval Add /healthz endpoint
ApproveSend back
tokens this run 36k 5 phases · 3 models
your control
✓ nothing ships without you
✓ runs on your machine
✓ your keys, your models
✓ no telemetry, ever
verification
✓ policy passed
✓ validation 18/18
✓ review approved
✓ never auto-merged
3 active worktrees
healthz-endpoint isolated
pg-16-migration isolated
search-latency isolated
awaiting your approval Add /healthz endpoint
ApproveSend back
tokens this run 36k 5 phases · 3 models
© 2026 Vibestrate · v0.68.0 Shonshon - Evolving Technologies