Every model.
Your workspace.

Chat with GPT, Claude, and local Ollama models in one native desktop app. Your keys. Your conversations. Your call.

Download for macOS

Free to start. No credit card. v1.1.4

Take a look around

Claude

Help me turn a big idea into a clear plan.

Let’s make it something you can act on.

Find the coreWrite down the problem and who you want to solve it for.
Start smallChoose one useful thing you can build and test this week.
Make it realShare it early. Let what you learn shape the next version.

Example response

Where do you want to take this?

Tools

Cloud model · Requests go to your selected provider

At home on
your desktop.

Chat history stays on your device. Not on our servers.

How privacy works

Find your flow.

Your models, together.

Connect the providers you use. Keep the workspace you love.

OpenAI

Anthropic

Gemini

xAI

Groq

Mistral

DeepSeek

Perplexity

Cohere

LM Studio

HuggingFace

Moonshot

Ollama

Custom

Local by design.
Yours by default.

Your thinking deserves a home of its own. Cosmo keeps your conversations on your device and lets you choose exactly how you connect to AI.

Set up your workspace

Your connection, your choice

Ollamalocalhost:11434

Local

LM StudioYour local model server

Local

Your API keysConnect directly to a cloud provider

Chat history lives on this device.

Local storage isn’t the same as local inference. Cloud prompts go to the provider you choose, under its privacy policy. Use a local model to keep prompts on your machine.

The full privacy picture

A wider workspace.

A focused place to think, with the tools to take things further.

Give your AI more context.

Connect MCP servers so your model can work with external tools and live data, not just the words in your prompt.

MCP connections

Tools from your servers

Tool callRead project context

Bring the right information into the conversation.

Context added to chat

Agent workspace

A space for your agents.

Install from the ACP registry.
Start a dedicated conversation.

Agent Client Protocol

Meet your local agents.

Install compatible ACP agents and give each one a dedicated workspace. Keep agent conversations right alongside your chats.

Stay in the flow.

Reach for slash commands without leaving your conversation. See model thinking, track tokens per message, and stop a response whenever you need.

/ Commands

Thinking & token insightsUnderstand each response.

Markdown, code highlighting, and a workspace that gets out of your way.

Next on the horizon.

In development, not included today.

Web Search
Workflow
Code Execution
Mobile App

Explore all features

Start free.
Stay in control.

Bring your own keys, not another AI subscription. Pick the workspace that fits how you work.

A little clarity.

Cosmo is your workspace. Model usage is billed separately by your cloud provider. Local models run on your hardware.

Community

Freeforever

Chat, local models, your own keys, MCP tools, ACP agents, commands, and personas.

Download Community

Professional

Coming soon

Planned: everything in Community, plus projects, RAG, automation, and more creative tools.

Good questions.

Read the full FAQ

Is my data private?

Chats are stored on your device. When you use a cloud model, your prompt is sent to the provider you selected under its own privacy policy; local models can run on your machine.

Do I need to pay for API keys?

Which AI providers can I use?

Is there a mobile app?

Can I sync my chats across devices?

Make room for
better work.

One desktop app. Your choice of AI.
A workspace that stays yours.