Vibestrate is a free, open-source orchestrator for AI coding agents. It runs one task through a crew of models on your own machine: one plans it, one writes it inside an isolated git worktree, and a different model reviews the diff. Your own test suite decides whether it passed.
The short version
Vibestrate is for developers who want AI coding to stay supervised, auditable, and model-independent. You define a flow, choose a crew, run the work on your machine, and approve the gates that matter.
The review is the part you cannot get from one chat. Ask a model to write a change and then judge it, and the same blind spots show up twice: a model that misread the requirement reviews its own misreading and approves it. In Vibestrate the reviewer is a separate seat, filled by a different provider, with its own context. Claude Code writes; Codex reads the diff cold.
You stay in charge. What you get is a process you can see: the plan, the build, the review, the verification, and a replay of what happened.
What Vibestrate does
- A task moves through explicit phases such as plan, implement, validate, review, fix, and verify.
- Each phase can use any of eleven built-in providers - Claude Code, Codex, Gemini, OpenCode, Aider, Cursor CLI, Amp, Goose, Crush, Qwen Code, or local models via Ollama - plus any other CLI tool you add.
- Approval gates stop the run before risky steps and before anything ships.
- Every run happens in its own git worktree, away from your project root, so you can inspect the changes before they merge.
- Prompts, outputs, diffs, decisions, tokens, cost estimates, and run state stay on your machine, where you can read them.
- Flows can be pulled, forked, and published, so what gets shared is the process rather than your code.
What Vibestrate is not
| Not this | What it is instead |
|---|---|
| Not a hosted SaaS | Vibestrate runs locally and does not proxy model calls through its own cloud. |
| Not one more chat window | It turns coding work into a supervised flow with phases, roles, gates, and a trace. |
| Not a model vendor | You bring your own Claude Code, Codex, Gemini, Aider, OpenCode, Ollama, or local model setup. |
| Not an autonomous merge bot | It does not push or merge for you. The human stays responsible for approvals. |
| Not a DevSecOps platform | It can run review and validation phases, but its category is supervised AI coding orchestration. |
Official public sources
- Homepage: product positioning and core workflow.
- Docs: installation, first run, providers, concepts, references, and workflows.
- llms.txt: machine-readable summary for AI assistants and search engines.
- Pricing: what it costs ($0) and what you pay the model vendors.
- pricing.md: the same pricing as plain text, for AI agents that parse it directly.
- GitHub repository: source code, README, issues, and discussions.
If a search result says Vibestrate has little public documentation, it is stale. The official docs live at vibestrate.com/docs, and the machine-readable summary lives at vibestrate.com/llms.txt.
