Minimal by design. Open source down to the prompt.
A coding agent for your Mac. Keep talking while it works on several tasks at once.
Free and MIT licensed. Use local models, your own API keys or a ChatGPT sign-in.

Why Wavefunction
Agent apps keep growing
Coding agents are turning into super apps, adding more with every release. Wavefunction goes the other way: less is more, simpler is better, and building comes first.
Free to choose
Pick any model and switch whenever you like. Run models locally or require zero data retention. You’re never tied to one provider’s plans or limits.
Open source, on the desktop
Most open-source agents shine in the terminal. Wavefunction is built to be a great desktop app: minimal, considered and fast, and open source down to the prompt.
Less is more
One agent. A conversation. More room to focus on your code.
Fewer sidebars. Fewer tabs.
Simple, clean, minimal interface. The conversation stays at the center.
Your browser, always
No built-in browser. Links open in your default browser, with the setup you already use.
Just a coding agent
No dots, bots, built-in apps of all kinds, or a million extra features. Just the tools to get things done.
Computer use in a container
Your own computer stays under your control. When the agent needs a desktop, it uses its own, in a local Docker container.
Optimized for parallel workflows
Keep the conversation going. Give it a task, then another, and another. Wavefunction splits the work across subagents, steers them as your plans change, and brings their work together.
The conversation keeps flowing
Send the next task while the last one runs. Each new piece of work that can run on its own gets a subagent, and nothing waits its turn.
Parallel without collisions
Every chat starts on its own branch, and subagents that could touch the same files each get a worktree. Wavefunction reviews their changes and brings them together.
Steer while it works
Change your mind mid-task. Your message reaches the subagent already on it, so it adjusts without starting over.
Fork or rewind
Start a new chat from any message, or put the code and the conversation back to how they were.
Computer use that leaves your Mac alone
Other agents take over your mouse, keyboard and screen to get things done. Wavefunction gets a desktop of its own, so you keep working while it clicks. Watch it, or take control at any time.
Your Mac stays yours
It never moves your pointer, types on your keyboard or records your screen. Its desktop is a local Docker container with its own browser and files, and a file reaches your Mac only when the agent hands it over, to a folder you allowed.
Secure sign-ins
When a site needs your login, you sign in privately. The agent pauses and never sees what you type, and the chat stays signed in for next time.
Files in and out
Downloads come to your Mac in the folder you choose, and files you add are ready to upload.
Needs Docker Desktop and a model that can read images.
Bring your own model
Sign in with ChatGPT, use your own API keys, or run models on your Mac. Pick a model for each chat and switch whenever you like.

ChatGPT
Sign in with Plus or Pro
Anthropic
API key
Google Gemini
API key
OpenAI
API key
OpenRouter
API key
Vercel AI Gateway
API key
Ollama
On your Mac or your server
OpenAI-compatible
LM Studio and other servers
Secure and private
Use local models or require zero data retention from your provider.
Local models
Your provider
ZDR
Open source, down to the prompt
Interested in contributing? We welcome new contributors.
Track every token and every dollar
Track token usage, cache usage, and provider-reported costs in one place. See what you use, what you spend, and how it changes over time.

Connectors and skills

MCP connectors
70+ ready-made connectors, plus any MCP server you add.
Skills and instructions
It follows your AGENTS.md and loads SKILL.md skills from .agents, .codex and .opencode folders.
Frequently asked questions
Is Wavefunction free?
Yes. Wavefunction is free and open source under the MIT license. You bring your own models or provider account; any model usage charges come from your provider.
Which models can I use?
Sign in with ChatGPT, use an API key from OpenAI, Anthropic, Google Gemini, OpenRouter or Vercel AI Gateway, or run models locally through Ollama, LM Studio or another OpenAI-compatible server. Choose the model that fits each conversation.
How do I keep my work private?
Your conversations and settings are stored on your computer. Use a local model to keep model inference local, or configure a provider with zero data retention. The models and connectors you choose determine which services receive your data.
How does parallel work happen?
Describe what you want in one conversation. Wavefunction can split work across subagents, take follow-up instructions while they run, and bring their work back together. You can keep talking as the work moves forward.
Can I use my existing tools and instructions?
Yes. Connect your tools through the built-in connector catalogue or add an MCP server. Wavefunction also reads your AGENTS.md instructions and loads SKILL.md skills, so it can work with the setup you already use.
Which platforms are supported?
Wavefunction is currently available for macOS. Download the app, connect a model, and start a conversation.