Native macOS Application

Every AI.
One interface.

oAI connects OpenAI, Anthropic, OpenRouter, Google, and local Ollama models into a single, beautifully native macOS experience — with smart memory, file access, and Git sync built in.

macOS 14+ · Native Swift · AGPL-3.0
oAI
💬

Powerful by default.
Extensible by design.

🤖

Multi-Provider Intelligence

Switch between OpenAI, Anthropic, OpenRouter (300+ models), Google Gemini, and local Ollama — all with a single keyboard shortcut. No context lost.

GPT-4oClaudeGeminiOllamaOpenRouter
🧠

Smart Memory

Reduce token costs by 50–80% with intelligent context selection, message starring, and progressive summarisation of long conversations.

🔍

Semantic Search

Find any conversation by meaning, not just keywords. AI embeddings let you search across your entire history with natural language.

📂

File Access via MCP

Grant the AI read (and optionally write) access to specific folders. Ask questions about your own code, notes, and documents directly.

🔄

Git Sync

Conversations export as Markdown and push to your Git repo automatically — free backup and cross-device sync with zero infrastructure.

📎

File Attachments

Drop images, PDFs, and text files directly into your message. Type @~/path to attach any file inline without leaving the keyboard.

🌐

Online Mode

Enable web search via DuckDuckGo or Google so the AI can pull real-time information alongside its training knowledge.

📧

AI Email Handler

Monitor your inbox via IMAP and let AI automatically respond to emails with a specific subject tag. Fully configurable with rate limiting and AES-256 encrypted credentials.

IMAPSMTPAES-256Rate limiting

Everything at your fingertips.

Type / to summon autocomplete for every feature. No hunting through menus — just type and go.

See all commands →
oAI — New Conversation
/model— Open model selector
/memory on— Enable smart context
/online on— Enable web search
/mcp add ~/Projects— Grant folder access
/save my-session— Save conversation
/export md— Export as Markdown
/stats— Token & cost report
/retry— Regenerate response
/system "You are..."— Set system prompt
300+
AI Models via OpenRouter
50–80%
Token reduction with Smart Context
5
AI Providers natively supported
Conversations backed up via Git

Ready to get started?

Read the full documentation to set up your first API key and start chatting in under a minute.