An AI code editor that runs on local models
If your code cannot leave your machine, or you would rather not pay per token, VibeCode.surf works with models running on your own computer. Point it at Ollama or LM Studio and the agents use those.
How it works
Connect in one step
Add Ollama or LM Studio as a provider, fetch the model list, pick a model.
Free and private
Local usage is counted as free, and nothing is sent to a hosted provider.
Mix local and hosted
Run routine work on a local model and send only the hard problems to a hosted one.
Honest about limits
If a local model cannot call tools, the app says so and falls back to plain chat rather than failing.
Everything else stays the same
Any model, your key
Claude, OpenAI, OpenRouter, Gemini, Groq, DeepSeek, Z.ai (GLM), Moonshot Kimi, Qwen, Together AI, Mistral, xAI, or local models through Ollama and LM Studio. A different model per agent.
Self-testing in a real browser
Agents open your project on localhost, take screenshots, click, type and read the console at desktop, tablet and phone size.
A plan and a memory in your repo
PLAN.md holds phases and task status; AGENTS.md is long-term memory, updated after each working turn.
Cost on screen
Tokens and cost under every reply, a total per project and per model, and each model's price in the picker.
What VibeCode.surf does not have yet
It is a beta. If you depend on any of these every day, keep your current editor alongside it for now.
- Autocomplete and go-to-definition from language servers
- Inline AI edits and tab completion inside the editor
- A debugger with breakpoints
- An extension marketplace
Good to know
Which local models work best?
Models trained for coding that support tool calling. Larger ones follow multi-step tasks more reliably; small ones are fine for simple edits.
Does it work with any OpenAI-compatible server?
Yes. Any server that speaks the OpenAI chat format can be added with its address.
Install it from your terminal.
One command installs the desktop app on macOS, Windows or Linux. Free during the beta; bring your own API key or a local model.
curl -fsSL https://vibecode.surf/install.sh | shirm https://vibecode.surf/install.ps1 | iexcurl -fsSL https://vibecode.surf/install.sh | sh