Research with current sources
Use supported web search, bring PDFs and images into the conversation, and inspect citations beside the answer.
Built for OpenRouter on macOS
The native OpenRouter client for Mac
Use your OpenRouter models in a fast, native Mac app. Switch models, search the web, work with files, and run tools from one workspace.
No account required · Intel & Apple Silicon · macOS 13+
Quickly switch between AI providers & models
OpenRouter on your Mac
Find the right model for the task
Search the OpenRouter catalog, favorite the models you use, and choose a model for each chat or agent. Reasoning and model controls stay close when you need them.
Search and favorite
Keep a short list of regular models as the catalog grows.
Control each chat
Set reasoning effort, temperature, token limits, and other supported parameters.
Search, favorite, and switch models from BoltAI.
Native on macOS
Open BoltAI where the work is
Use a global shortcut from any app or full-screen Space. Drop in files, images, or selected text and continue in a native window.
A fast, focused Mac workspace
Native windows, menus, shortcuts, drag-and-drop, dictation, and familiar Mac controls keep the app out of your way.
Instant Chat Bar
Start a new or temporary chat without finding the main window.
AI Workflows
Transform selected text and preserve its formatting in Notes, Mail, Obsidian, and other Mac apps.
Built around real work
Put your OpenRouter models to work
Research current topics, keep ongoing work organized, and build repeatable workflows.
Keep the setup with the work
Projects keep instructions, files, chats, tools, and model settings together. Duplicate a Project when you want the same setup for a new stream of work.
Build repeatable workflows
Save instructions as agents, connect MCP servers, and enable BoltAI tools. Trigger AI Workflows with a keyboard shortcut from other Mac apps.
Everything in one AI workspace
On all your devices
Use BoltAI on your Mac, iPhone, and iPad with the same chats, agents, and projects synced securely through the cloud.
Local models, zero latency
Run powerful LLMs locally via Ollama and LM Studio for fast, private responses without per-token costs.
Privacy built in
Chats are stored locally, API keys can be encrypted with your passphrase, and nothing is ever used to train models.
Extend with tools & MCP
Connect BoltAI to local and remote MCP servers, toggle tools per agent, and keep your AI workflows configurable in code.
~/.cursor/mcp.json
~/.boltai/mcp.json
{
"mcpServers" : {
"filesystem" : {
"args" : [
"-y",
"@modelcontextprotocol/server-filesystem",
"~/Data"
],
"command" : "npx"
}
}
}OpenRouter sign-in
Connect your account from BoltAI
Sign in to OpenRouter from the Mac app, or configure an API key manually.
- 01
Choose OpenRouter
Open AI Services in BoltAI and select OpenRouter.
- 02
Sign in to your account
Sign in to OpenRouter from BoltAI, or configure an API key manually.
- 03
Choose a model
Pick a model from your OpenRouter account and start a chat.
Use other providers in BoltAI
Connect OpenAI, Anthropic Claude, Google Gemini, Mistral, xAI, Perplexity, Azure OpenAI, or Amazon Bedrock directly. BoltAI also supports local models through Ollama and LM Studio.
Frequently asked questions
