Quick start Docs Hub

Vibestrate

Give it the whole feature.

Vibestrate is the frame your models work in. It plans the work, breaks out the TODOs, and ticks them off under your rules.

Show me how
Vibestrate

Give it the whole feature.

Vibestrate is the frame your models work in. It plans the work, breaks out the TODOs, and ticks them off under your rules.

Star

Long chats lose the plot.

One plan, every model reads it.

See how it works

So no task is allowed to get long.

They all work from one plan. Each item runs in its own session with no baggage from the six before it, and it still knows what was decided and what already landed, because that gets handed forward as real artifacts. You never explain the project twice.
Your rules, not its defaults. The standards you set are policy the run enforces, not advice a model talks itself out of. A supervisor reads every step and decides: carry on, send it round again, or stop and come get you.
You make the call at the end. It works to a finished, tested change and waits. Not sure where to look? Ask Consult, and it will tell you what it would check first.
Claude Code·Codex·Gemini·OpenCode·Aider·Cursor CLI·Ollama

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

You get a CTO on every step.

It reads the work between steps and 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.

Measured, not vibes

Same task. Same model.
Four identical runs.

Claude Code, bare

2/4

identical runs shipped stored XSS - and nothing stood between them and done

0/5

bare builds ever refused anonymous access to everyone’s billing

Claude Code, inside Vibestrate

0

XSS builds ever reached merge-ready - the two that wrote it were stopped at the gate

2/14

builds in the whole benchmark refused the billing read - both were Vibestrate runs

Bare Claude’s best run scored 110 of 120 in two minutes for fifty cents - code quality is not the difference. A Vibestrate run costs $2–3 and 7–8 minutes: a plan, an independent review, and a verifier that will not certify what it cannot check. Judged by a script, not a model. Fourteen scored builds, every score in the repo.

The whole scoreboard, including the rounds we lost →

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 flows hub install quality-arbitration
$ vibe flows hub install guy@deep-refactor
$ vibe flows hub 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, and light enough to drop into any repo. 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 rules
  • your machine
  • one shared plan
  • 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
A Vibestrate run at merge-ready: the flow's eight steps across the top, the supervisor's decisions beside the run-assurance verdict, and the per-step token and status table below.

One run, start to finish.

Eight steps across five seats. A model hits a rate limit and falls back to a backup mid-run. A reviewer fails and is tolerated. Nothing merges until you have read the diff.

View full size Run it yourself

© 2026 Vibestrate
v0.3.0 Shonshon - Evolving Technologies